Method for predicting operations at a water treatment plant

Abstract

A method for predicting a process at a water treatment plant. The method includes receiving coagulation data from the water treatment plant and displaying the received data via a graphical interface, the display including a historical record of the received data. A prediction of the performance of the equipment within the water treatment plant may then be generated, the prediction of the performance including a predicted turbidity or UV transmittance of water after passing through the equipment. The prediction of the performance is based on the data received from the water treatment plant and a plurality of inputs received from the user via the graphical interface. The generated prediction of performance is displayed via the graphical interface, thereby allowing the user to perform an action including selectively activating the equipment, selectively adjusting equipment settings, and selectively adjusting conditions within the water treatment plant that are upstream of the equipment.

Description

Attorney Docket No.: IS24.1182-WO-PCTMETHOD FOR PREDICTING OPERATIONS AT A WATER TREAMENT PLANTCross-Reference to Related Applications

[0001] This patent application claims priority to U.S. Provisional Patent Application No. 63 / 699,939, filed on September 27, 2024, which is incorporated by reference.Background

[0002] Water sources often contain sediment, germs, chemicals, and toxins that are to be removed prior to being safe for drinking. Water treatment processes may vary widely in what steps are taken to treat the water, however, commonly, the first step of the process is coagulation and flocculation.

[0003] In coagulation, positively charged chemicals are added to bind with the negatively charged contaminants to form slightly larger particles, which then during flocculation form larger clumps of particles called flocs. The formation of flocs may be aided by the addition of flocculant chemicals. These flocs are then allowed to settle out in sedimentation tanks or clarifiers, leaving clear water on top. The clear water then passes on to the next steps of the process.

[0004] A conventional process for identifying the correct dosage of additives to be used for ensuring the efficient coagulation is a “jar” test. Ajar test may involve trying different dosages of different additives in a laboratory setting and then waiting for the coagulation to occur, after which the purity of water is determined.

[0005] Jar testing is essentially a scaled version of a water treatment system, which provides a means of estimating what will be needed to treat the water on a larger scale. However, even if a certain treatment performs well in jar testing, when applied to the scaled up process the behavior may be different and adjustments may be performed. Additionally, this is a slow and timeconsuming plus resource intensive process which does not adequately account for the inherent differences between the lab and the water treatment plant.

[0006] What is needed is a method for utilizing data collected in the past for identifying the resulting water properties in order to determine whether or not a certain coagulant dosage is optimal for specific raw water conditions.SummaryAttorney Docket No.: IS24.1182-WO-PCT

[0007] A method for predicting a process at a water treatment plant is disclosed. According to certain embodiments, the method includes receiving data from the water treatment plant. The received data may include coagulation data related to the water treatment plant, the coagulation data itself including a turbidity of raw water, a turbidity of treated water, a UV transmittance of raw water, a UV transmittance of treated water, temperature, a dosage rate for a variety of additives, and acidity or basicity. According to certain embodiments, the data may include human machine interface data, data received from sensors disposed within the water treatment plant, or data recorded via lab measurements of samples at various locations within the water treatment plant. According to certain embodiments, the data may be received by manually entering the data via a graphical interface on a screen associated with a user, or received automatically from a human machine interface and preprocessing sources before ingestion into the water treatment plant. The method may further include displaying the received data via the graphical interface. According to certain embodiments, the display may include a historical record of the received data. Displaying the received data may include filtering the data according to a range of at least one selected value or displaying the historical record of the received data as a plot. The method may also include generating a prediction of the performance of equipment within the water treatment plant. In certain embodiments, the equipment within the water treatment plant may include a clarifier.

[0008] According to certain embodiments, generating the prediction of the performance includes generating a predicted turbidity or a predicted UV transmittance of water after passing through the equipment. The prediction of the performance may be based on the received data, while generating the prediction of performance may include receiving a plurality of inputs from the user via the graphical interface. According to certain embodiments, the plurality of user inputs may include a turbidity of raw water, a UV transmittance of raw water, an acidity or basicity of raw water, a temperature of raw water, and a dosage rate of at least one additive. The method may further include displaying the generated prediction of performance via the graphical interface. Additionally, the method may include performing an action after the prediction has been displayed. According to certain embodiments, the action may include selectively activating the equipment, selectively adjusting equipment settings, and selectively adjusting conditions within the water treatment plant that are upstream of the equipment.

[0009] A method is provided for predicting an outcome of a water treatment process at a facility. The method includes receiving data related to a water sample at the facility, building a plurality ofAttorney Docket No.: IS24.1182-WO-PCT models for predicting an outcome of the water treatment process based on the received data, receiving user input related to the water treatment process, selecting at least one of the models by a user, generating a prediction of the outcome of the water treatment process based on the user input and the selected model, and displaying the generated prediction on a graphical interface.

[0010] Also provided is a computing system which includes one or more processors and a memory system having one or more non-transitory computer-readable media storing instructions that, when executed by at least one of the one or more processors, cause the computing system to perform operations. The operations may include receiving data related to a water sample at the facility, building a plurality of models for predicting an outcome of the water treatment process based on the received data, receiving user input related to the water treatment process, selecting at least one of the models by a user, generating a prediction of the outcome of the water treatment process based on the user input and the selected model, and displaying the generated prediction on a graphical interface.

[0011] Also provided is a non-transitory computer-readable medium storing instructions that, when executed by one or more processors of a computing system, cause the computing system to perform operations. The operations may include receiving data related to a water sample at the facility, building a plurality of models for predicting an outcome of the water treatment process based on the received data, receiving user input related to the water treatment process, selecting at least one of the models by a user, generating a prediction of the outcome of the water treatment process based on the user input and the selected model, and displaying the generated prediction on a graphical interface.

[0012] It will be appreciated that this summary is intended merely to introduce some aspects of the present methods, systems, and media, which are more fully described and / or claimed below. Accordingly, this summary is not intended to be limiting.Brief Description of the Drawings

[0013] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the present teachings and together with the description, serve to explain the principles of the present teachings. In the figures:Attorney Docket No.: IS24.1182-WO-PCT

[0014] Figure 1A illustrates an exemplary start up page of a graphical interface used to display received historical data and generate a corresponding prediction of performance, according to an embodiment.

[0015] Figure IB illustrates the graphical interface after the selection of a record tab, according to an embodiment.

[0016] Figure 1C illustrates the graphical interface after the selection of a history sub-tab, according to an embodiment.

[0017] Figure ID illustrates the graphical interface after the selection of an inspect tab and generating a plot, according to an embodiment.

[0018] Figure IE illustrates the graphical interface after making a selection of what data to display within a generated table, according to an embodiment.

[0019] Figure IF illustrates the graphical interface displaying a number of adjustable data filters and a resulting generated table, according to an embodiment.

[0020] Figure 1G illustrates the graphical interface after a predict tab has been selected along with a predict clarified turbidity model, according to an embodiment.

[0021] Figure 1H illustrates the graphical interface after a predict multiple slider has been selected, according to an embodiment.

[0022] Figure 2 illustrates a flowchart of generating a series of predictive models and a method of using those predictive models to predict the outcome of a process at a water treatment plant, according to an embodiment.

[0023] Figure 3 illustrates a flowchart of a method for predicting a process at a water treatment plant, according to an embodiment.

[0024] Figure 4 illustrates a schematic view of a computing system for performing at least a portion of the method(s) described herein, according to an embodiment.Detailed Description

[0025] Reference will now be made in detail to embodiments, examples of which are illustrated in the accompanying drawings and figures. In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the invention. However, it will be apparent to one of ordinary skill in the art that the invention may be practiced without these specific details. In other instances, well-known methods, procedures, components,Attorney Docket No.: IS24.1182-WO-PCT circuits, and networks have not been described in detail so as not to unnecessarily obscure aspects of the embodiments.

[0026] It will also be understood that, although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first object or step could be termed a second object or step, and, similarly, a second object or step could be termed a first object or step, without departing from the scope of the present disclosure. The first object or step, and the second object or step, are both, objects or steps, respectively, but they are not to be considered the same object or step.

[0027] The terminology used in the description herein is for the purpose of describing particular embodiments and is not intended to be limiting. As used in this description and the appended claims, the singular forms “a,” “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term “and / or” as used herein refers to and encompasses any possible combinations of one or more of the associated listed items. It will be further understood that the terms “includes,” “including,” “comprises” and / or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. Further, as used herein, the term “if’ may be construed to mean “when” or “upon” or “in response to determining” or “in response to detecting,” depending on the context.

[0028] Attention is now directed to processing procedures, methods, techniques, and workflows that are in accordance with some embodiments. Some operations in the processing procedures, methods, techniques, and workflows disclosed herein may be combined and / or the order of some operations may be changed.METHOD FOR PREDICTING OPERATIONS AT A WATER TREAMENT PLANT

[0029] According to certain embodiments, the current method may be used to predict the performance of a coagulation process in a specific or designated water treatment plant. The method may include a machine learning model that has been trained or based on operating data from the plant. According to certain embodiments, a portion of the data processing within the method is based on physics, thereby making the approach a hybrid model. The method may include use of aAttorney Docket No.: IS24.1182-WO-PCT graphical interface that combines the digital recording of the plant data with the generated predictions from the models. The method may be trained on historical plant operating data related to previous raw water conditions and coagulant dosages so as to predict a resulting treated water property of interest. With this method, operators or users may be able to explore how their current operation may be expected to perform without the risk of testing different parameters in the actual water treatment plant.

[0030] Currently, in a water treatment plant, the operating conditions related to the coagulation process in a clarifier within the plant may not be optimal, for example, the chemical dosage rates may be too high or too low, resulting in a less efficient process, higher operating costs, increased downtime, and higher wear and tear on equipment. Additionally, using conventional jar tests to evaluate these conditions may often be unreliable and inaccurate for the prediction of optimal dosages. Jar testing takes time and may be inaccurate where differences between the jar test and the actual process are not captured. For example, the water temperature may change more rapidly in the jar test than in the clarifier.

[0031] Experimenting with different operating conditions in the water treatment plant is also not feasible. Pushing the process to different operating regions may have consequences, such as damage to equipment, unexpected plant downtime, increased operating expenses, or worsened water quality. Water treatment plants are expected to supply high-quality drinking water to the nearby community, so the risk of disrupting this service is too great to allow for suitable exploration of different operating conditions.

[0032] According to certain embodiments, the current method may include the use of a digital model that is able to predict the performance of the water treatment process under various conditions. The model, being trained on the historical operating data from a specific water treatment plant, may be customized to predict a specific performance metric accurately. Using the current method, the water treatment plant operators may input their current raw water conditions, define their chemical dosage rates, and predict how the coagulation process might respond, according to certain embodiments. These generated predictions may help assess the impact of upstream changes on the operations of the water treatment plant, as well as optimize the chemical dosage rates so as to reduce overall costs and improve efficiency.Attorney Docket No.: IS24.1182-WO-PCT

[0033] According to certain embodiments, the current method may include two different models, namely one for predicting post-clarifier turbidity and one for predicting post-clarifier ultraviolet transmittance (UVT).

[0034] The turbidity of the raw water pre-clarifier and the treated water post-clarifier may be recorded electronically via a human machine interface (HMI), and / or in paper records which may be updated daily. The electronically recorded data may be collected at discrete time intervals each day, which allows for an average daily value to be obtained that mitigates any fluctuations in the data and allows the model to be trained based on values more closely representing ‘stable’ operating conditions.

[0035] However, the UVT of the raw water pre-clarifier and the treated water post-clarifier is only recorded via paper records according to certain embodiments. As a result, the ‘instantaneous’ operating point for each day may be used to train the model for the prediction of UVT. According to certain embodiments, the method further includes the collection of the daily records to be performed electronically instead of solely paper records, which may serve several purposes. In addition, the lab sample point from which the manually recorded data is obtained may be as soon as the raw water enters the water treatment plant, for example before the raw water has reached the strainers disposed within the water treatment plant. However, in certain embodiments, the sensors recording the data digitally may be disposed after the strainers and a bit farther into the water treatment plant, for example immediately before the clarifier disposed in the water treatment plant. When comparing the two sets of data, most of the parameters of interest remained fairly constant except for the temperature of the raw water. This in turn may have an effect on the predictions of the model since it is desired that the properties of the sample should be as representative as possible of the actual conditions in the clarifier, and if a parameter such as temperature is off by even a small margin, it is possible that the method may provide slightly different results. As such, for the UVT model, the temperature recorded by the HMI in certain embodiments may be used instead of the temperature recorded in the paper data, according to certain embodiments. In this manner, the temperatures being used within the model may be more representative of the actual conditions of the clarifier, thereby providing the model with more accurate data on which to base its prediction, according to certain embodiments.

[0036] According to certain embodiments, a graphical interface may be used to provide users such as water treatment plant operators with predictions from the generated models. For example,Attorney Docket No.: IS24.1182-WO-PCTFigure 1A illustrates an exemplary start up page 102 of the graphical interface 100 while Figure IB illustrates an example of the graphical interface 100 after the selection of a record tab 104 which includes several input fields for the user to input various types of data including but not limited to values related to acidity or basicity 106, temperature 108, turbidity 110, UV transmittance 112, color 114, and the flow 116, volume, and pressure at numerous positions along or within the water treatment process. With electronically recorded data, the operators may more easily inspect and compare the current operating conditions to historical trends, helping to inform decisions about what operating parameters best suit the current upstream conditions.

[0037] Figure 1C illustrates the graphical interface 100 after selecting a history sub-tab 118 which includes a table 120 displaying data that has been input into the graphical interface 100 over a series of consecutive days, that data including the input data seen in Figure IB, for example. According to certain embodiments, historical trends may be seen within a generated plot 124 as seen in Figure ID after an inspect tab 122 of the graphical interface 100 has been selected. The generated plot 124 may include input values such as temperature and UV transmittance and may be plotted over a specified period of time.

[0038] According to certain embodiments, the user may select to a display only select portions of the input data via the graphical interface. For example, as seen in Figure IE, the user may select to display data that is related to turbidity and UV transmittance of water within the clarifier, i.e. the data which may serve as the input / output of the current method. For example, the user may make a selection via a drop-down menu 126 portion of the graphical interface 100 to display “Clarifier Turbidity and UVT” and then select a table sub-tab 128 to display any previously recorded data related to clarifier turbidity and UVT in a tabular form. In Figure IF, the user may engage with a plurality of different adjustable data filters 130 which may further limit or highlight different portions or sub portions of the input data. In certain embodiments, the adjustable data filters 130 may include for example an adjustable range of values for raw water turbidity 132, raw water UV transmittance 134, raw water acidity or basicity 136, raw water temperature 138, ClearPac 180 dosage rate 140, polymer dosage rate 142, and sulfuric acid dosage rate 144, among others. In Figure IF, an illustrative desired range for raw water turbidity 132 and a desired range for raw water temperature 138 have been selected, leading to the graphical interface 100 to display a corresponding table 146 of input data which adheres to the ranges selected within the filters. This gathered data may be used in future engagements as well to develop digital solutions elsewhere inAttorney Docket No.: IS24.1182-WO-PCT the plant or to update and improve the existing solutions. According to certain embodiments, the current method enables the machine learning operations environment to leverage all the data in the best possible way from the very start of the process.

[0039] Because the digital entry of data related to the water treatment plant has already been completed, this helps facilitate data input into the models in order to predict results. For example, according to certain embodiments, the graphical interface 100 allows a user to select between providing either a turbidity or UV transmittance prediction, and then it provides a plurality of input fields related to generating that prediction. For example, Figure 1G illustrates where after a user has selected to generate a prediction related to post treatment turbidity within the water treatment plant by selecting a predict tab 148 and then selecting the appropriate model via a predict clarified turbidity button 170. Input fields 150 including but not limited to raw water turbidity 152, raw water acidity or basicity 154, raw water temperature 156, ClearPac 180 dosage rate 158, polymer dosage rate 160, and sulfuric acid dosage rate 162 may then be provided. According to certain embodiments, the user submits the input data into the input fields 150 and, through the use of the models of the current method which are trained on the specific historical data of the water treatment plant, a predicted turbidity outcome 164 is generated and then displayed within the graphical interface 100. Similarly and in certain embodiments, selecting a predict clarified UVT button 172 may display a similar or different series of input fields 150 which in turn may be used to generate a corresponding predicted UVT outcome.

[0040] Each prediction may be generated one at a time, however according to certain embodiments, multiple predictions may be generated at the same time via an appropriate series of input tables 166 within the graphical interface 100 by selecting a predict multiple slider 168 as seen in the exemplary illustration of Figure 1H.

[0041] Figure 2 illustrates a flowchart of the entire prediction process 200 for the operations within the water treatment plant, according to certain embodiments. The flowchart illustrates how manually recorded data from the plant at step 202 or digitally captured data from the plant at step 204 may be combined with historical data stored at step 206 for that specific water treatment plant. Specifically, the historical data record may then be used to build models related to predicting the turbidity and UV transmittance of post treatment water within the water treatment plant.

[0042] For example, according to certain embodiments, a user may enter data related to current conditions within the water treatment plant through a graphical or user interface 208. The data mayAttorney Docket No.: IS24.1182-WO-PCT be input by the user through a record step 210. The input data may be processed at step 212, for example by being displayed within a table as seen in Figure 1C. The processed data may be stored in a local central repository or database at step 214. In certain embodiments, the processed data may also be stored in a separate database as historical data in step 206.

[0043] In certain embodiments, the user may use the user interface to inspect the data that has been entered at step 216. In certain embodiments, the stored data may be further processed at step 218 to create relevant visualizations at step 220, for example the plot 124 as seen in Figure ID.

[0044] In certain embodiments, the data from the plant manually recorded at step 202, the data from the plant digitally recorded at step 204, and the data stored as historical data at step 206 may be aligned in step 222. The data may then be fdtered and cleaned in step 224, for example data determined to be an outlier may be removed. Next, the filtered and cleaned data may be used to build a UVT prediction model and a turbidity prediction model in steps 226 and 228, respectively. Within steps 226 and 228, each respective model may undergo data preprocessing 230, 230’, model training 232, 232’, and computing test metrics 234, 234’. Finally, the best UVT prediction model may be selected in step 236, while the best turbidity prediction model may be selected in step 238. In certain embodiments, the best UVT prediction and turbidity prediction models may be selected by comparing their generated outputs to prior or historical data from that specific water treatment plant.

[0045] The method may then use the previously built models selected at steps 236 and 238 to generate a prediction related to the turbidity and / or UV transmittance of post treatment water, given the parameters previously entered by the user. For example, the user may use the user interface to predict the UVT or turbidity of treated water at step 240. The user may select which model to use at step 242, for example by selecting the predict clarified turbidity button 170 or the predict clarified UVT button 172 seen in Figure 1G. In certain embodiments, the user may adjust the parameters to be used by the selected model accordingly at step 244. The model may then be ran at step 246 to generate a related prediction that is based upon the user’s input as well as the data unique to the water treatment plant that was used to train the model as detailed above. In certain embodiments, step 246 may be repeated using different parameters until a desired predicted result is achieved. According to certain embodiments, in step 248 the generated prediction may be stored in a local storage database, for example the same local databased used to store the processed data in step 214.Attorney Docket No.: IS24.1182-WO-PCTExemplary Method

[0046] Figure 3 illustrates a flowchart of a method 300 method predicting an outcome of a water treatment process at a facility, such as a water treatment plant. The method may include receiving data related to a water sample from the facility, as at 302. The water sample data may include coagulation data related to the facility. The coagulation data may include a turbidity of a raw water portion of the water sample, a turbidity of a treated water portion of the water sample, a UV transmittance of the raw water portion of the water sample, a UV transmittance of the treated water portion of the water sample, a temperature of the water sample, and an acidity or basicity of the water sample. The water sample data may be received from a human machine interface at the facility, from sensors disposed within the facility, and / or from a user manually entering data via a graphical interface. The data entered at the graphical interface may include lab measurements of water samples taken from a plurality of locations within the facility. In certain embodiments, water sample data related to the facility may be received automatically before the sample of water is ingested into the facility.

[0047] According to certain embodiments, the method 300 also includes filtering the water sample data according to a range of at least one selected value on the graphical interface, as at 304, and displaying the water sample data as a plot and / or as a table within the graphical interface, as at 306.

[0048] According to certain embodiments, the method 300 also includes building a plurality of models for predicting an outcome of the water treatment process based on the received data, as at 308. Building the models may include building a model to predict turbidity and / or a model to predict UV transmittance of the water sample after it has passed through the equipment disposed at the facility. In certain embodiments, building the models includes preprocessing the water sample data, training multiple models using the preprocessed data, and then selecting one of the trained models.

[0049] According to certain embodiments, the method 300 also includes receiving user input related to the water treatment process, as at 310. In an example, the user input may include selecting at least one of the models, as at 312. Selecting at least one of the models may include selecting between a model to predict turbidity and a model to predict UV transmittance of the waterAttorney Docket No.: IS24.1182-WO-PCT sample after passing through equipment disposed at the facility. In certain embodiments, the equipment disposed at the facility may include a clarifier.

[0050] According to certain embodiments, the method 300 also includes generating a prediction of the outcome of the water treatment process based on the inputs, as at 314. Generating the prediction of the outcome of the water treatment process based on the user input and the selected model may include generating a predicted turbidity or a predicted UV transmittance of the water sample after it has passed through equipment within the facility. In certain embodiments, generating the prediction of the outcome of the water treatment process based on the user input and the selected model may include receiving the inputs from the user via the graphical interface. The plurality of inputs may include a turbidity of raw water, a UV transmittance of raw water, an acidity or basicity of raw water, a temperature of raw water, and a dosage rate of at least one additive. In certain embodiments, the at least one additive may include at least one of a coagulant such as ClearPac 180, a coagulant aid such as a polymer, or sulfuric acid. In certain embodiments, generating the prediction may specifically include generating a plurality of predictions of the outcome of the water treatment process simultaneously. In certain embodiments, each of the predictions may be based on a corresponding set of inputs that are entered by the user.

[0051] According to certain embodiments, the method 300 also includes displaying the generated prediction on a graphical interface, as at 316.

[0052] According to certain embodiments, the method 300 also includes performing an action in response to the generated prediction, as at 318. The action may include generating or transmitting a signal that instructs or causes a physical action to occur. The physical action may include selectively activating the equipment, selectively adjusting settings of the equipment, and selectively adjusting conditions within the facility that are upstream of the equipment. More particularly, this may include enabling or disabling the addition of one or more of the additives such as a coagulant, a coagulant aid, and / or sulfuric acid by setting the dosage rate setpoint to a value greater than 0 making it enabling, or to 0 thereby making it disabling, or by turning the injection system on or off completely. In certain embodiments, the physical action may include increasing or decreasing the dosage rate setpoint of one or more of the additives such as a coagulant, a coagulant aid, or sulfuric acid which in turn increases or decreases the flowrate of the additives based on the flowrate of the raw water. In certain embodiments, the physical action may include increasing or decreasing the flowrate of the raw water into the process, which in turnAttorney Docket No.: IS24.1182-WO-PCT increases or decreases the residence time of the raw water in the equipment. Increasing or decreasing the residence time of the raw water in the equipment in turn increases or decreases the available time for the contaminants to settle out for removal. This may also affect the temperature of the raw water as it has a longer time to spend exchanging heat with the equipment and the ambient air in the water treatment plant, which may be a different temperature than the external temperature and therefore the raw water.Exemplary Computing System

[0053] In some embodiments, the methods of the present disclosure may be executed by a computing system. Figure 4 illustrates an example of such a computing system 400, in accordance with some embodiments. The computing system 400 may include a computer or computer system 401 A, which may be an individual computer system 401 A or an arrangement of distributed computer systems. The computer system 401A includes one or more analysis modules 402 that are configured to perform various tasks according to some embodiments, such as one or more methods disclosed herein. To perform these various tasks, the analysis module 402 executes independently, or in coordination with, one or more processors 404, which is (or are) connected to one or more storage media 406. The processor(s) 404 is (or are) also connected to a network interface 407 to allow the computer system 401 A to communicate over a data network 409 with one or more additional computer systems and / or computing systems, such as 40 IB, 401C, and / or 401D (note that computer systems 401B, 401C and / or 401D may or may not share the same architecture as computer system 401A, and may be located in different physical locations, e.g., computer systems 401A and 401B may be located in a processing facility, while in communication with one or more computer systems such as 401C and / or 401D that are located in one or more data centers, and / or located in varying countries on different continents).

[0054] A processor may include a microprocessor, microcontroller, processor module or subsystem, programmable integrated circuit, programmable gate array, or another control or computing device.

[0055] In some embodiments, computing system 400 contains one or more artificial intelligence module(s) 408. In the example of computing system 400, computer system 401 A includes the Al module 408. In some embodiments, a single Al module may be used to perform some aspects ofAttorney Docket No.: IS24.1182-WO-PCT one or more embodiments of the methods disclosed herein. In other embodiments, a plurality of Al modules may be used to perform some aspects of methods herein.

[0056] The storage media 406 may be implemented as one or more computer-readable or machine-readable storage media. Note that while in the example embodiment of Figure 4 storage media 406 is depicted as within computer system 401A, in some embodiments, storage media 406 may be distributed within and / or across multiple internal and / or external enclosures of computing system 401A and / or additional computing systems. Storage media 406 may include one or more different forms of memory including semiconductor memory devices such as dynamic or static random access memories (DRAMs or SRAMs), erasable and programmable read-only memories (EPROMs), electrically erasable and programmable read-only memories (EEPROMs) and flash memories, magnetic disks such as fixed, floppy and removable disks, other magnetic media including tape, optical media such as compact disks (CDs) or digital video disks (DVDs), BLURAY® disks, or other types of optical storage, or other types of storage devices. Note that the instructions discussed above may be provided on one computer-readable or machine-readable storage medium, or may be provided on multiple computer-readable or machine-readable storage media distributed in a large system having possibly plural nodes. Such computer-readable or machine-readable storage medium or media is (are) considered to be part of an article (or article of manufacture). An article or article of manufacture may refer to any manufactured single component or multiple components. The storage medium or media may be located either in the machine running the machine-readable instructions, or located at a remote site from which machine-readable instructions may be downloaded over a network for execution.

[0057] It should be appreciated that computing system 400 is merely one example of a computing system, and that computing system 400 may have more or fewer components than shown, may combine additional components not depicted in the example embodiment of Figure 4, and / or computing system 400 may have a different configuration or arrangement of the components depicted in Figure 4. The various components shown in Figure 4 may be implemented in hardware, software, or a combination of both hardware and software, including one or more signal processing and / or application specific integrated circuits.

[0058] Further, the steps in the processing methods described herein may be implemented by running one or more functional modules in information processing apparatus such as general purpose processors or application specific chips, such as ASICs, FPGAs, PLDs, or otherAttorney Docket No.: IS24.1182-WO-PCT appropriate devices. These modules, combinations of these modules, and / or their combination with general hardware are included within the scope of the present disclosure.

[0059] Computational interpretations, models, and / or other interpretation aids may be refined in an iterative fashion; this concept is applicable to the methods discussed herein. This may include use of feedback loops executed on an algorithmic basis, such as at a computing device (e.g., computing system 400, Figure 4), and / or through manual control by a user who may make determinations regarding whether a given step, action, template, model, or set of curves has become sufficiently accurate for the evaluation of the subsurface three-dimensional geologic formation under consideration.

[0060] The foregoing description, for purpose of explanation, has been described with reference to specific embodiments. However, the illustrative discussions above are not intended to be exhaustive or limiting to the precise forms disclosed. Many modifications and variations are possible in view of the above teachings. Moreover, the order in which the elements of the methods described herein are illustrated and described may be re-arranged, and / or two or more elements may occur simultaneously. The embodiments were chosen and described in order to best explain the principles of the disclosure and its practical applications, to thereby enable others skilled in the art to best utilize the disclosed embodiments and various embodiments with various modifications as are suited to the particular use contemplated.

Claims

Attorney Docket No.: IS24.1182-WO-PCTCLAIMSWhat is claimed is:

1. A method for predicting an outcome of a water treatment process at a facility, the method comprising: receiving data related to a water sample at the facility; building a plurality of models for predicting an outcome of the water treatment process based on the received data; receiving a plurality of inputs related to the water treatment process; generating a prediction of the outcome of the water treatment process based on the inputs; and displaying the generated prediction on a graphical interface.

2. The method of claim 1, wherein receiving data related to the water sample comprises: receiving water sample data from a plurality of sensors disposed within the facility; receiving water sample data entered into the graphical interface by a user; and receiving water sample data manually entered into a human machine interface at the facility.

3. The method of claim 2, wherein receiving water sample data entered into the graphical interface by the user comprises receiving lab measurements corresponding to a plurality of water samples taken from a plurality of locations within the facility entered into the graphical interface by the user.

4. The method of claim 1, wherein receiving water sample data related to the facility comprises receiving water sample data automatically before the sample of water is ingested into the facility.

5. The method of claim 1, wherein receiving the plurality of inputs related to the water treatment process comprises receiving a selection of at least one of the models made by a user.Attomev Docket No.: IS24.1182-WO-PCT6. The method of claim 1, further comprising displaying the water sample data as a plot and / or as a table within the graphical interface.

7. The method of claim 1, wherein building the models comprises building a model to predict turbidity and / or a model to predict UV transmittance of the water sample after passing through equipment disposed at the facility.

8. The method of claim 1, wherein building the models comprises: preprocessing the water sample data; training multiple models using the preprocessed data; and selecting one of the trained models.

9. The method of claim 1, wherein generating the prediction of the outcome of the water treatment process based on a user input and the selected model comprises generating a predicted turbidity or a predicted UV transmittance of the water sample after passing through equipment within the facility.

10. The method of claim 1, further comprising performing an action in response to the generated prediction.

11. A computing system, comprising: one or more processors; and a memory system comprising one or more non-transitory computer-readable media storing instructions that, when executed by at least one of the one or more processors, cause the computing system to perform operations, the operations comprising: receiving data related to a water sample at a facility; building a plurality of models for predicting an outcome of a water treatment process based on the received data; receiving a plurality of inputs related to the water treatment process;Attorney Docket No.: IS24.1182-WO-PCT generating a prediction of the outcome of the water treatment process based on the inputs; and displaying the generated prediction on a graphical interface.

12. The computing system of claim 11, wherein the water sample data comprises a turbidity of a raw water portion of the water sample, a turbidity of a treated water portion of the water sample, a UV transmittance of the raw water portion of the water sample, a UV transmittance of the treated water portion of the water sample, a temperature of the water sample, and an acidity or basicity of the water sample.

13. The computing system of claim 11, wherein receiving the plurality of inputs related to the water treatment process comprises receiving a selection between a model to predict turbidity and a model to predict UV transmittance of the water sample after passing through equipment disposed at the facility made by the user.

14. The computing system of claim 13, wherein the equipment disposed at the facility comprises a clarifier.

15. The computing system of claim 11, wherein receiving the plurality of inputs related to the water treatment process comprises receiving the plurality of inputs from the user via the graphical interface.

16. The computing system of claim 15, wherein the plurality of inputs comprises a turbidity of raw water, a UV transmittance of raw water, an acidity or basicity of raw water, a temperature of raw water, and a dosage rate of at least one additive.

17. The computing system of claim 11, wherein the operations further comprise generating a plurality of predictions of the outcome of the water treatment process simultaneously.

18. The computing system of claim 17, wherein each of the predictions is based on a corresponding set of inputs entered by the user.Attorney Docket No.: IS24.1182-WO-PCT19. The computing system of claim 11, wherein the operations further comprise performing an action in response to the generated prediction, wherein the action comprises generating or transmitting a signal that instructs or causes a physical action to occur, wherein the physical action comprises selectively activating the equipment, selectively adjusting settings of the equipment, and selectively adjusting conditions within the facility that are upstream of the equipment.

20. A non-transitory computer-readable medium storing instructions that, when executed by one or more processors of a computing system, cause the computing system to perform operations, the operations comprising: receiving data related to a water sample at a facility; building a plurality of models for predicting an outcome of a water treatment process based on the received data; receiving a plurality of inputs related to the water treatment process; generating a prediction of the outcome of the water treatment process based on the inputs; and displaying the generated prediction on a graphical interface.

Images