Water quality detection in static water meters using deep learning

Abstract

Methods and systems for detecting water quality may involve: classifying water quality using a water meter, incorporating data indicating changes in ultrasonic time-of-flight (ToF) behavior due to impurities or combinations of impurities mixed in the water; and classifying impurities in the water using a sequence learning unit. Data indicating changes in ultrasonic time-of-flight behavior can be obtained from one or more ultrasonic sensors associated with the water meter. The sequence learning unit can classify impurities in the water into water quality parameters, including one or more of the following: for example, TDS (total dissolved solids), pH value, residual chlorine data, turbidity information, and total organic carbon value. The data can be transmitted to the user via radio frequency frames.

Description

Technical Field

[0001] The implementation plan covers the field of water quality testing. It also involves using ultrasonic sensors and static water meters to detect impurities in the water. Background Technology

[0002] Poor water quality is a serious problem faced by most countries worldwide, impacting public health and productivity. In many countries, even purified water utilities remain non-compliant due to impurities dissolving during distribution, caused by human error or natural disasters. Water quality testing at the metering level will help consumers and utilities take appropriate action when impurities increase. Utilities are installing various water sensors and alarm systems to address this issue, but accurate measurement of water quality changes requires intelligent software solutions that can train themselves to adapt to existing water conditions and trigger alarms when different types of dissolved impurities are detected.

[0003] Poor water quality is a serious problem that can affect many countries around the world. It has a direct impact on public health and can hinder productivity. In several countries, even when water utilities are responsible for water purification, they often face non-compliance issues because impurities can enter the water during transmission and distribution due to human error or natural disasters.

[0004] To address this challenge, implementing water quality detection at the metering level could be beneficial. Such systems would be valuable to both consumers and utilities, as they would allow them to take appropriate action when impurities increase. Currently, utilities are combining various water sensing sensors and alarm systems to address this issue. However, to obtain accurate measurements of changes in water quality, intelligent software solutions are needed.

[0005] The solution should be able to train itself to recognize existing water quality standards and trigger alarms when different types of dissolved impurities are detected. Summary of the Invention

[0006] The following summary is provided to facilitate understanding of some features of the embodiments disclosed herein and is not intended to be an complete description. A full understanding of the various aspects of the embodiments disclosed herein can be obtained by considering the specification, claims, drawings, and abstract as a whole.

[0007] Therefore, one aspect of the implementation is to provide a method and system for impurity detection using an ultrasonic sensor.

[0008] Another aspect is providing methods and systems that can use machine learning models to detect impurities in water.

[0009] Another aspect of the implementation plan is to provide time-of-flight (ToF) data on the use and measurement of ultrasonic sensors for water quality detection.

[0010] Another aspect of the disclosed implementation is to provide a method and system for detecting impurities in smart water meters.

[0011] The above aspects and other objectives can now be achieved as described herein. In an implementation, a method for detecting water quality may involve: classifying the quality of the water using a water meter, incorporating data indicating changes in ultrasonic time-of-flight (ToF) behavior due to impurities or combinations of such impurities mixed in the water; and classifying the impurities in the water using a sequence learning unit.

[0012] The implementation scheme may also involve obtaining data indicating changes in ultrasonic time-of-flight behavior from multiple ultrasonic sensors associated with the water meter.

[0013] The implementation scheme may also involve obtaining the data indicating the time-of-flight variation behavior of the ultrasound from at least two ultrasonic sensors associated with the water meter.

[0014] The implementation plan may also involve using the sequence learning unit to classify the impurity in the water into water quality parameters, which include at least one of the following: TDS (total dissolved solids), pH value, residual chlorine data, turbidity information, and total organic carbon value.

[0015] The implementation scheme may also involve communicating data to the user via radio frequency frames, indicating the impurities in the water classified using machine learning algorithms.

[0016] In the implementation scheme, it may also involve: using the sequence learning unit to classify the impurities in the water into water quality parameters, which include at least one of the following: TDS (total dissolved solids), pH value, residual chlorine data, turbidity information, and total organic carbon value; and conveying the water quality parameters associated with the water to the user via radio frequency frames.

[0017] In the implementation scheme, the sequence learning unit can be a machine learning algorithm.

[0018] In the implementation scheme, the data indicating the classification of the impurity in the water may be based on Time of Flight (ToF), Time Difference of Flight (DiffToF), and / or temperature information.

[0019] In one embodiment, an apparatus for detecting water quality may include: an ultrasonic sensor, wherein a water meter may be used to classify the quality of the water by combining data indicating ultrasonic time-of-flight (ToF) changes caused by impurities or combinations of such impurities mixed in the water, wherein the data indicating such ultrasonic ToF changes can be obtained from the ultrasonic sensor associated with the water meter; and a sequence learning unit that can classify the impurities in the water.

[0020] In the implementation scheme, the sequence learning unit classifies the impurity in the water as water quality parameters, which include at least one of the following: TDS (total dissolved solids), pH, residual chlorine, turbidity, and total organic carbon.

[0021] In the implementation scheme, the data indicating the impurity in the water, classified using a machine learning algorithm, can be transmitted to the user via radio frequency frames.

[0022] In the implementation scheme, the sequence learning unit can classify the impurity in the water into water quality parameters, which include at least one of the following: TDS (Total Dissolved Solids), pH value, residual chlorine data, turbidity information, and total organic carbon value; and can communicate the water quality parameters associated with the water to the user via radio frequency frames. As discussed above, the sequence learning unit may include machine learning algorithms. Furthermore, the data indicating the classification of the impurity in the water can be based on Time of Flight (ToF), Time Difference of Flight (DiffToF), and temperature information.

[0023] In one embodiment, a system for detecting water quality may include at least one processor and a memory storing instructions to cause the at least one processor to perform: classifying the quality of the water using a water meter, incorporating data indicating changes in ultrasonic time-of-flight (ToF) behavior due to impurities mixed in the water or combinations thereof; and classifying impurities in the water using a sequence learning unit.

[0024] In an implementation, the instruction may also be configured to cause the at least one processor to perform: obtaining data indicating changes in ultrasonic time-of-flight behavior from a plurality of ultrasonic sensors associated with the water meter.

[0025] In an implementation, the instruction may also be configured to cause the at least one processor to perform: obtaining data indicating changes in ultrasonic time-of-flight behavior from at least two ultrasonic sensors associated with the water meter.

[0026] In the implementation scheme, the instruction may also be configured to cause the at least one processor to perform: classify the impurities in the water into water quality parameters using the sequence learning unit, the water quality parameters including at least one of the following: TDS (total dissolved solids), pH value, residual chlorine data, turbidity information and total organic carbon value; and communicate the water quality parameters associated with the water to the user via radio frequency frames. Attached Figure Description

[0027] The accompanying drawings also illustrate this embodiment and, together with the detailed description, serve to explain the principles of the embodiment, wherein similar reference numerals throughout the separate views refer to the same or functionally similar elements and are incorporated in and form part of the specification.

[0028] Figure 1 An operation flowchart illustrating the logical operation steps of a method for static instrument processing that can be implemented according to the implementation scheme is shown;

[0029] Figure 2 A table illustrating sample data collected as part of a water quality testing operation, according to the instructions of the implementation plan;

[0030] Figure 3 An example table is provided for visualizing water impurities according to the implementation plan;

[0031] Figure 4 A schematic diagram illustrating an impurity detection model that can be implemented according to the implementation plan is shown;

[0032] Figure 5 A flowchart illustrating the operations of a data preprocessing method that can be implemented according to the implementation scheme is shown;

[0033] Figure 6 A graphical representation illustrating an example of dataset preprocessing according to the implementation scheme is shown;

[0034] Figure 7 Example charts illustrating data on the classification of impurities based on ToF, DiffToF, and temperature information, according to the description of the implementation scheme;

[0035] Figure 8 A graphical representation of the model feature space according to the implementation scheme is illustrated;

[0036] Figure 9 A graph illustrating the training loss and accuracy data of the SWIC (Smart Water Impurity Classifier) ​​according to the description instructions of the implementation scheme is shown;

[0037] Figure 10 An example of a confusion matrix that can be implemented according to the implementation scheme is shown;

[0038] Figure 11A schematic diagram illustrating a mixing facility for commercial and domestic water supply according to the implementation plan is shown;

[0039] Figure 12 A schematic diagram illustrating a commercial facility on a loop pipeline for stabilizing water flow, according to an implementation scheme, is shown. This loop pipeline can also be used as a redundant supply pipeline with metering and quality measurement capabilities; and

[0040] Figure 13 A schematic diagram illustrating an example operating environment based on one or more specific implementations described herein is provided.

[0041] Similar reference numerals or symbols in the accompanying drawings may indicate similar or analogous elements. Detailed Implementation

[0042] The specific values ​​and configurations discussed in these non-restrictive examples are variable and are cited only to illustrate one or more implementations, and are not intended to limit their scope.

[0043] The subject matter will now be described more fully below with reference to the accompanying drawings, which form part of the subject matter and illustrate specific exemplary embodiments by way of illustration. However, the subject matter can be embodied in many different forms, and therefore the subject matter covered or claimed is intended to be construed as not being limited to any of the exemplary embodiments listed herein; the exemplary embodiments are provided merely for illustration. Likewise, the subject matter intended to be claimed or covered has a suitably broad scope. Among other things, the subject matter can be embodied as a method, apparatus, component, or system. Thus, embodiments can take the form, for example, hardware, software, firmware, or combinations thereof. Therefore, the following detailed description is not intended to be construed as limiting.

[0044] Throughout the specification and claims, terms may have nuanced meanings as the context dictates or implies, in addition to their expressly stated meanings. Similarly, phrases such as “in an embodiment” or “in one embodiment” or “in an exemplary embodiment” and their variations, as used herein, may or may not refer to the same embodiment, and phrases such as “in another embodiment” or “in another exemplary embodiment” and their variations, as used herein, may or may not refer to different embodiments. For example, the claimed subject matter is intended to include, in whole or in part, combinations of exemplary embodiments.

[0045] Generally, terms can be understood at least in part from their usage in the context. For example, terms such as “and,” “or,” or “and / or” as used herein can have a variety of meanings that can depend at least in part on the context in which such terms are used. Generally, “or,” when used in an associative list, such as A, B, or C, is intended to indicate A, B, and C used herein in an inclusive sense, and A, B, or C used herein in an exclusive sense. Furthermore, the term “one or more,” as used herein, depends at least in part on the context and can be used to describe any feature, structure, or characteristic in a singular sense, or to describe a combination of features, structures, or characteristics in a plural sense. Similarly, terms such as “a,” “an,” or “the” also depend at least in part on the context and can be understood to convey a singular usage or to express a plural usage. Moreover, the term “based on” can be understood not necessarily to convey a set of exclusive factors, but can depend at least in part on the context, allowing for additional factors that are not necessarily explicitly described again.

[0046] As used herein, the term "ultrasonic sensor" can refer to a type of device that uses sound waves with frequencies above the upper limit of human hearing (e.g., above 20,000 Hz or 20 kHz) to detect and measure objects, distances, or other properties. An ultrasonic sensor works by emitting high-frequency sound waves that bounce off an object and return to the sensor. By measuring the time it takes for the sound waves to travel to and return from the object, the sensor can calculate the distance to the object with high accuracy.

[0047] In the context of static smart water meters, ultrasonic sensors can be used to measure the flow rate and volume of water passing through the meter. An ultrasonic sensor emits a series of high-frequency sound waves (ultrasonic pulses) into the water flow. These sound waves travel through the water and bounce off the surface or any particles or impurities suspended in the water. The ultrasonic sensor measures the time it takes for the emitted sound waves to be reflected back to the sensor. This time measurement is extremely accurate and depends on the distance the sound waves have traveled.

[0048] By knowing the speed of sound in water and the time it takes for the sound wave to return, the ultrasonic sensor can calculate the distance the sound has traveled, and thus the flow rate of water passing through the meter. Over time, the ultrasonic sensor accumulates these flow measurements to calculate the total volume of water consumed.

[0049] Static smart water meters equipped with ultrasonic sensors offer several advantages, such as high accuracy, the ability to measure bidirectional flow (e.g., water entering and leaving a property), and abrasion resistance due to the absence of moving parts. They are also suitable for various water types, including clean or contaminated water, making them a reliable option for monitoring water consumption and quality. These meters can be integrated into smart water management systems that provide real-time data and analytics to help utilities and consumers manage water use more efficiently.

[0050] Note that the term "meter," as used herein, can refer to water meters, and more specifically to "smart" water meters, also known as smart water utility meters. These are digital devices used to measure and monitor water consumption in homes, businesses, and other locations. Unlike traditional water meters, which require manual reading and typically provide limited data, smart water meters are equipped with advanced technology to automatically collect, record, and transmit water usage data. Key features and benefits of smart water meters include the ability to remotely transmit water usage data to a central server or utility company. This eliminates the need for physical access to the location used to measure meter readings. Furthermore, users, utilities, and property owners have access to real-time data on water consumption, enabling better management and water conservation.

[0051] Smart meters can also be used to detect unusual usage patterns that indicate potential leaks or water waste. This early detection can help reduce water bills and prevent property damage. Smart meters are generally more accurate than traditional mechanical meters, resulting in more precise billing and data collection. Utility companies can streamline their billing process by automatically receiving consumption data from smart meters, thereby reducing errors and disputes.

[0052] Furthermore, by accessing real-time usage data, consumers can gain a better understanding of their water consumption habits, potentially guiding efforts to reduce water waste and conserve water. Smart water meters can be part of the broader IoT (Internet of Things) ecosystem, enabling the automatic control of water-related systems (such as irrigation or plumbing) based on real-time data. The collected data can be used for data analytics to identify trends, make predictions, and optimize water distribution systems. The methods disclosed herein allow smart meters to also monitor water quality and detect contaminants, providing additional safety and environmental benefits.

[0053] As will be discussed in more detail in this article, low-power static water meters can perform metering measurements without installing any moving parts. Ultrasonic sensing can be used with static water meters for metering measurements, which involve calculating the time of flight (ToF) of the ultrasonic waves between the transmitter and receiver and calculating flow information.

[0054] Primarily, ToF changes can occur due to water flow, with temperature and water quality also having significant influences. This additional information can be used as part of the water quality determination process. Water temperature can be calculated using existing electronic water meters, while water quality is supplementary information requiring additional processing for accurate detection. Therefore, the disclosed water quality detection method can utilize ToF information generated through ultrasonic sensing and can be subjected to software classification to detect different types of impurities / quality details.

[0055] The disclosed implementation provides additional capabilities for impurity detection in static smart water meters. This capability can be based on ultrasonic sensing involving time-of-flight (ToF) information and calculation of water flow. Water quality is an additional parameter that can be detected using sensor outputs and the application of machine learning algorithms (e.g., support vector machines / neural networks). This method can be used to detect water contaminants such as, for example, higher TDS (total dissolved solids), pH, chlorine residue, turbidity, and total organic carbon values ​​in flowing water.

[0056] The basic principle of the disclosed solution involves learning Time-of-Flight (ToF) data behavior during water flow when different impurities are present, and then using the trained model to classify impurities during normal water flow. Data collected from ultrasonic sensors can be provided as time-series data, which may include ToF changes as behavioral alterations caused by the presence of different impurities in the water. The implementation also includes impurity removal capabilities at the water surface level and has an additional mechanism for adequate water chlorination based on impurity classification (e.g., if pathogens / parasites are detected).

[0057] Figure 1 An operation flowchart illustrating the logical operation steps of a method 100 for static instrument processing that can be implemented according to the implementation scheme is shown. Figure 1 The method 100 shown can be implemented for impurity detection and may include the collection of time-series input data and a sequence learning unit for training and predicting water quality.

[0058] As in Figure 1 As shown in box 102, time-of-flight (ToF) calculations can be performed using two or more ultrasonic sensors, including a first ultrasonic sensor 96 and a second ultrasonic sensor 98. Data generated by the specific implementation of the steps or operations shown in box 102 can undergo steps or operations involving flow and volume measurements as depicted in box 104, and can also undergo time-series data collection (ToF) as shown in box 103. Data generated by the operations shown in box 104 can undergo steps or operations involving metrological calibration and alarms, as shown in box 106. Then, as shown in box 108, steps or operations involving frame construction can be implemented. That is, the operations shown in box 108 can involve constructing or building radio frequency (RF) frames.

[0059] It should be noted that after the operation shown in box 103, the collected data generated by this step or operation can be processed by a sequence learning unit, as indicated in box 105. That is, box 105 represents a sequence learning unit, which may include or implement a deep neural network. The data output from the sequence learning unit / deep neural network indicated in box 105 can be subjected to water quality classification to generate water quality classification data, as indicated in box 107. This water quality classification data can be provided to the frame construction operation shown in box 108 and can also be subjected to impurity correction operations, as shown in box 109. The data generated by frame construction operation 108 can then be transmitted via radio frequency (RF) communication (as shown in box 110) through a wireless network 11 (e.g., indicated as LoRaWAN in the figure).

[0060] exist Figure 1 In the example implementation shown, wireless network 112 can be implemented in the context of RF frames used in communication protocols such as, for example, LoRa (long-range) and wMBus (wireless M-bus), where an RF frame is a structured data unit used to transmit information via radio frequency. These protocols are designed for low-power, long-range wireless communication, and frames are a fundamental element of their communication schemes. LoRa is an example of a wireless communication technology known for its long-range capabilities and low power consumption.

[0061] It should be noted that Figure 1 The implementation shown is not limited to a specific "LoRaWAN" wireless network. "LoRaWAN" is merely an example of one type of wireless-based network or wireless protocol that can be implemented using this implementation. Implementations can be implemented using other types of wireless networks and / or wireless protocols.

[0062] Therefore, time-of-flight (ToF) and time-difference-of-flight (DiffToF) time-series data, as well as various water impurities such as hard water, RO water, brine, acidic water, water with added proteins, and water with added oil components, can be collected. The ToF difference and changes in the time-series provide a classification of impurities (e.g., box 107), where DiffToF can produce accurate predictions in stagnant water as well as in flowing water. Higher values ​​of DiffToF are an indication of flowing water. Ultrasonic sensors 96 and 98 are capable of capturing data per second, allowing high-dimensional log files to be classified for impurity type detection. It should be noted that the term "time series," as used herein, can refer to "time-series" data, which can be a sequence of data points that are typically collected, recorded, or measured at consecutive time points at equal intervals. Each data point in a time series can be associated with a specific timestamp or time period, which can then be used to represent and analyze how a particular quantity, phenomenon, or variable changes over time.

[0063] Figure 2 Table 120 illustrates example data collected as part of a water quality testing operation according to the instructions of the implementation plan. Figure 2 As shown, the first two columns tracked example ToF and DiffToF data respectively, the third column shows temperature data, and the fourth column shows water quality data. The water quality data includes indications such as potable water, hard water, and saline water.

[0064] Figure 3 Table 130 illustrates the visualization of water impurities according to the implementation plan. Figure 3 Table 130, as shown, comprises four columns. The first column graphically depicts the different ToF values ​​relative to the DiffToF data graphically displayed in the second column. The third column tracks the temperature, while the fourth column shows the type of impurity (e.g., RO water, seawater, tap water-acid, tap water-mud, tap water-oil mixture, and tap water-soap). Thus, Table 130 provides an overview of the characteristics of various water impurities. Figure 3 The example dataset shown was collected over an hour, with data for each impurity captured every second.

[0065] It should be understood that while Time-of-Flight (ToF) can provide some interpretable patterns for each type of impurity, DiffToF is difficult to interpret and is almost indistinguishable from data collection performed on static water. Humans cannot consistently interpret such high-dimensional log files to monitor water conditions at different geographical locations. Various classification schemes can be employed to automatically classify time-series data. However, with the exponential growth in sensor log dimensionality, deep neural networks (DNNs) appear to offer a suitable approach to meet the demand for accurate water quality detection, serving as either a sequence learning unit or a sequence network. Unlike physical models, which may require the development of different numerical formulas and may not be easily tuned to handle outliers, DNNs offer a data-driven approach. DNN models can learn general patterns for various classes of samples from complex training data by learning appropriate decision boundaries or hyperplanes.

[0066] In some implementation schemes, Figure 1 The sequence learning unit shown in box 105 can be implemented using a DNN or other types of sequence learning units or sequence networks. It can be used to implement... Figure 1 Of the several example DNN model types of sequence learning units shown in box 105 and elsewhere in this paper, sequence networks are perhaps best suited for temporal classification. Sequence learning units or sequences (such as, for example, recurrent neural networks (RNNs), long short-term memory (LSTMs), gated recurrent units (GRUs)) can also be used to develop sequence networks and / or as part of sequence learning units.

[0067] Figure 4 A schematic diagram illustrating an impurity detection model 200 that can be implemented according to the implementation scheme is shown. The impurity detection model 200 can be used to implement... Figure 1 The sequence learning unit is shown at box 105. The impurity detection model 200 can obtain ToF data as shown at dashed arrow 203 and time-series DiffToF data as shown at dashed arrow 203. Figure 5 In the example shown, ToF data can be supplied to node 204, and time-series DiffToF data can be supplied to node 205. The outputs from nodes 204 and 205 can be input to, for example, node 206 (e.g., this node could be a nonlinear activation unit (NLAU)). Note that nodes 206, 208, 210, and 216 are examples of nonlinear activation units (NLAUs).

[0068] The impurity detection model 200 may include several other nodes 208 through 244. Note that, for brevity, not every figurehead number and node will be discussed herein. Needless to say, data may be output from nodes 244, 246, 248, 250, 252, and 254 and input to node 256, which indicates potable water (e.g., a prediction of whether the water is drinkable), rather than nodes 258 (e.g., hard water) and 260 (e.g., brine). Note that nodes 244, 246, 248, and 254 are examples of Smax nodes.

[0069] Figure 5 A flowchart illustrating the operations of method 270 for data preprocessing, which can be implemented according to the implementation scheme, is shown. As shown in box 272, steps or operations involving sensor simulation and log file generation can be implemented. The data generated by this operation may undergo a feature selection step or operation, as indicated in box 274. The data generated by the feature selection operation shown in box 274 may undergo a sequence dataset formation operation, as shown in box 276. Then, the data generated by the sequence dataset formation operation may undergo normalization and mean subtraction steps or operations, as indicated in box 278.

[0070] Figure 6 A graphical representation of an example of dataset preprocessing 280 according to the implementation scheme is shown. Simulated sensor logs 282 are shown at the top of the figure. Example log data are shown in segments 283 and 285. Figure 6 Feature selection data 284 and sequence dataset formation 286 are also shown, which is then fed into sequence model 290. Sequence model 290 is a sequence learning unit (such as...) Figure 1 An example of a sequence learning unit shown in box 105.

[0071] Figure 7Example graphs 340 and 350 illustrate data for classifying impurities based on ToF, DiffToF, and temperature information, according to the description instructions of the implementation scheme. Figure 7 In the figures, Figure 340 depicts ToF data for different water types over a one-hour period. Figure 350, on the other hand, depicts DiffToF data for different water types, also over a one-hour period. The SWIC model 300 aims to classify impurities based on ToF, DiffToF, and temperature. Univariate characteristics are shown in Figures 340 and 350.

[0072] Figure 8 A graphical representation of the model feature space 360 ​​according to an implementation scheme is illustrated. In some implementations, the temporal dependencies of the various classes learned by the SWIC model 300 and in the model feature space can be viewed, with samples of the same class shown in the same color. However, it should be noted that... Figure 8 It is depicted in black and white, therefore lacking a specific color classification scheme. Instead, in Figure 8 In the example shown, different classes or types of data are represented by geometric features of different geometric icons (such as squares, triangles, and circles).

[0073] Figure 8 It presents an idealized and exemplary view of the model's feature space, along with accompanying example illustrations. Figure 8 The illustration 362 depicts various data labels, such as "ROWater", "SeaWater", "TapWater", "TapWater_acidic", "TapWater_MUD", "TapWater_OILMIX", and "TapWater_SOAP", which can be associated with the model feature space 360. It should be understood that having labels such as... Figure 8 The specific illustration 362 representing the example geometric features associated with the model feature space 360 ​​shown is provided for illustrative and exemplary purposes only and should not be considered as a limiting feature of the implementation.

[0074] Figure 9 Graphs 370 and 380 illustrate data indicating the training loss and accuracy of SWIC according to the implementation plan. The data shown in these graphs is based on SWIC, which was trained on 50 minutes of data across 7 classes and validated on 10 minutes of data, where each sample includes 30 time steps in the time dimension. Therefore, in Figure 9The training loss and accuracy of SWIC are shown in Figures 370 and 380. For example, in Figure 370, the training loss is indicated by data curve 371, and the validation loss is indicated by data curve 373. In Figure 380, the training accuracy is indicated by data curve 381, and the validation accuracy is indicated by data curve 383.

[0075] Figure 10 An example of a confusion matrix 390 that can be implemented according to the implementation scheme is shown. That is, it was tested on 2.5 minutes of data, with each test sample having 30 seconds of data. The SWIC model 300 is a sequence learning unit (such as...) Figure 1 The example shown is a sequence learning unit 105, which can be used to classify water impurity data with, for example, 81% classification accuracy. Figure 10 The confusion matrix 390 for the true and predicted classes is shown. As used in this paper, the term "confusion matrix" can refer to a table used in machine learning and statistics to evaluate the performance of classification algorithms. Confusion matrices can be particularly useful for evaluating the accuracy of model predictions when dealing with binary or multi-class classification problems. A confusion matrix provides a comprehensive summary of how well a model classifies instances from a dataset by breaking down the results into categories.

[0076] Figure 11 A schematic diagram of a mixing facility 400 for commercial and domestic water supply, according to an implementation plan, is shown. Figure 11 In the illustrated configuration, commercial water meter 402 is shown connected to commercial water supply line 406, which branches off to residential water supply line 408, which connects to residential water meter 412. An additional residential water supply line 410 is also shown connected to residential water meter 416. Residential water supply line 410 is also connected to residential water meter 414. It should be understood that one or more ultrasonic sensors, as discussed earlier, may be integrated with each water meter and / or associated with each water meter. It should also be understood that in some embodiments, the various water meters discussed above (and similarly below) may be implemented as static water meters.

[0077] Figure 12 A schematic diagram of a commercial facility 420 on a loop line 423 for stabilizing water flow, according to an embodiment, is illustrated. This loop line can also be used as a redundant supply line with metering and quality measurement capabilities. The commercial facility 420 shown in Figure 14 includes a commercial water line 421 connected to a commercial water meter 402 and a loop line 423 connected to a commercial water meter 403.

[0078] Therefore, the implementation described herein can provide additional capabilities for impurity detection in static water meters, and can be based on the use of ultrasonic sensing technology. Water quality is also a possible parameter, which can be detected using sensor output with the application of additional machine learning algorithms and the detection of water contamination such as higher TDS (total dissolved solids), pH, chlorine residue, turbidity, and total organic carbon in flowing water.

[0079] The basic principle of the implementation involves learning the Time-of-Flight (ToF) data behavior during water flow when different impurities are present, and then using the trained model to classify the impurities during normal water flow. The data collected from the ultrasonic sensor is time-series data, which can include ToF changes as behavioral variations caused by the presence of different impurities in the water. The implementation can be used for both domestic and commercial water supply purposes and can be arranged in various different configurations (such as...). Figure 13 The hybrid facility solution shown is installed on a loop line (which can also be used as a redundant supply line with metering and quality measurement) as shown in Figure 14 for stabilizing water flow.

[0080] Figure 13 Examples of suitable operating environments 800 for implementing various aspects of this disclosure are illustrated, and these examples may also include a computer 812. The computer 812 may also include a processing unit 814, system memory 816, and a system bus 818. The system bus 818 couples system components (including, but not limited to, system memory 816) to the processing unit 814. The processing unit 814 may be any of a variety of available processors. Dual microprocessors and other multiprocessor architectures may also be used as the processing unit 814.

[0081] System bus 818 can be any of several types of bus architectures, including memory bus or memory controller, peripheral bus or external bus, and / or local bus using various available bus architectures, including but not limited to Industry Standard Architecture (ISA), Micro Channel Architecture (MSA), Extended ISA (EISA), Intelligent Drive Electronic Devices (IDE), VESA Local Bus (VLB), Peripheral Component Interconnect (PCI), Card Bus, Universal Serial Bus (USB), Advanced Graphics Port (AGP), FireWire (IEEE 1094), and Small Computer System Interface (SCSI). System memory 816 may also include volatile memory 820 and non-volatile memory 822. The Basic Input / Output System (BIOS) is stored in non-volatile memory 822, and the BIOS contains basic routines such as transferring information between components within computer 812 during startup.

[0082] By way of illustration and not limitation, nonvolatile memory 822 may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, or nonvolatile random access memory (RAM) (e.g., ferroelectric RAM (FeRAM)). Volatile memory 820 may also include random access memory (RAM) used as external cache memory. By way of illustration and not limitation, RAM may be available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), direct Rambus RAM (DRRAM), direct Rambus dynamic RAM (DRDRAM), and Rambus dynamic RAM.

[0083] Computer 812 may also include removable / non-removable, volatile / non-volatile computer storage media. For example, Figure 13 A disk storage device 824 is illustrated. The disk storage device 824 may also include, but is not limited to, devices such as disk drives, floppy disk drives, magnetic tape drives, Jaz drives, Zip drives, LS-100 drives, flash memory cards, or Memory Sticks. The disk storage device 824 may also include a single storage medium or a storage medium combined with other storage media, including but not limited to optical disc drives, such as optical disc ROM devices (CD-ROM), CD recordable drives (CD-R drives), CD rewrite drives (CD-RW drives), or digital versatile disc ROM drives (DVD-ROM). To facilitate connection of the disk storage device 824 to the system bus 818, a removable or non-removable interface, such as interface 826, is typically used.

[0084] Figure 13Software acting as an intermediary between the user and the basic computer resources described in the suitable operating environment 800 is also depicted. Such software may also include, for example, an operating system 828. The operating system 828, which may be stored on a disk storage device 824, is used to control and allocate the resources of the computer 812. System applications 830 may utilize the operating system 828 to manage resources through program modules 832 and program data 834 (e.g., stored in system memory 816 or disk storage device 824). It should be understood that this disclosure can be implemented using various operating systems or combinations of operating systems. The user enters commands or information into the computer 812 through an input device 836. Input devices 836 include, but are not limited to, pointing devices such as a mouse, trackball, stylus, touchpad, keyboard, microphone, joystick, gamepad, satellite receiver, scanner, TV tuner card, digital camera, digital camcorder, webcam, etc. These and other input devices can be connected to the processing unit 814 via an interface port 838 through a system bus 818. The interface port 838 may include, for example, a serial port, a parallel port, a game port, and a universal serial bus (USB). Output device 840 can use some of the ports of the same type as input device 836.

[0085] Therefore, for example, a USB port can be used to provide input to computer 812 and output information from computer 812 to output device 840. Output adapter 842 is provided herein to illustrate that some output devices 840 may exist, such as monitors, speakers, and printers, as well as other output devices 840 that require special adapters. By way of illustration and not limitation, output adapter 842 includes a video and sound card that provides a means of connection between output device 840 and system bus 818. It should be noted that other devices and / or device systems provide both input and output capabilities, such as remote computer 844.

[0086] Computer 812 can operate in a networked environment using a logical connection to one or more remote computers (such as remote computer 844). Remote computer 844 can be a computer, server, router, network PC, workstation, microprocessor-based device, peer-to-peer device, or other common network node, and typically may also include many or all of the elements described relative to computer 812. For simplicity, only a memory storage device 846 with remote computer 844 is shown. Remote computer 844 can be logically connected to computer 812 via network interface 848, and then physically connected via communication connection 850.

[0087] Network interface 848 includes wired and / or wireless communication networks, such as local area networks (LANs), wide area networks (WANs), cellular networks, etc. LAN technologies include Fiber Distributed Data Interface (FDDI), Copper Distributed Data Interface, Ethernet, Token Ring, etc. WAN technologies include, but are not limited to, point-to-point links, circuit-switched networks and variants such as Integrated Services Digital Network (ISDN), packet-switched networks, and Digital Subscriber Line (DSL). Communication connection 850 refers to the hardware / software used to connect network interface 848 to system bus 818. Although communication connection 850 is shown internal to computer 812 for clarity, this communication connection may also be external to computer 812. For illustrative purposes only, the hardware / software used to connect to network interface 848 may also include internal and external technologies such as modems, including conventional telephone-grade modems, cable modems and DSL modems, ISDN adapters, and Ethernet cards.

[0088] The implementation scheme can be implemented at any possible level of technical detail integration as a system, method, apparatus, and / or computer program product. The computer program product may include one or more computer-readable storage media having computer-readable program instructions thereon for causing a processor to execute aspects of the implementation scheme. The computer-readable storage medium may be a tangible device that can retain and store instructions for use by an instruction execution device. The computer-readable storage medium may be, for example, but not limited to, electronic storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the foregoing.

[0089] A less complete list of more specific examples of computer-readable storage media may also include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory, portable optical disc read-only memory (CD-ROM), digital versatile disc (DVD), memory stick, floppy disk, mechanical encoding devices (such as punched cards or raised structures in recesses on which instructions are recorded), and any suitable combination of the foregoing. As used herein, computer-readable storage media should not be construed as transient signals, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmitting media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0090] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to a suitable computing / processing device, or downloaded via a network (e.g., the Internet, a local area network, a wide area network, and / or a wireless network) to an external computer or external storage device. This network may include copper cables, fiber optic cables, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. One or more network adapter cards or network interfaces in the computing / processing device receive the computer-readable program instructions from the network and forward them to a computer-readable storage medium within the suitable computing / processing device.

[0091] Computer-readable program instructions used to implement various aspects of the implementation scheme may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, configuration data for integrated circuits, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and procedural programming languages ​​such as the "C" programming language or similar programming languages.

[0092] Computer-readable program instructions can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet provided by an Internet service provider). In some implementations, electronic circuitry, including, for example, programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), can be customized to execute computer-readable program instructions by utilizing state information from the computer-readable program instructions to perform various aspects of the implementation.

[0093] This document describes aspects of embodiments of the invention with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that one or more blocks in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams.

[0094] These computer-readable program instructions may also be stored in a computer-readable storage medium that can instruct a computer, programmable data processing device, and / or other equipment to operate in a certain manner, such that the computer-readable storage medium storing the instructions includes an article of writing comprising instructions that implement aspects of functions / actions specified in one or more blocks of a flowchart and / or block diagram. The computer-readable program instructions may also be loaded onto a computer, other programmable data processing device, or other equipment to cause a series of operational actions to be performed on the computer, other programmable device, or other equipment to produce a computer-implemented process, such that the instructions executing on the computer, other programmable device, or other equipment implement the functions / actions specified in one or more blocks of a flowchart and / or block diagram.

[0095] The flowcharts and block diagrams illustrate the architecture, functionality, and operation of possible specific implementations of systems, methods, and computer program products according to various implementation schemes. In this regard, one or more boxes in a flowchart or block diagram may represent a module, segment, or part of an instruction, which includes one or more executable instructions for implementing the specified logical function.

[0096] In some alternative implementations of the scheme, the functions indicated in the boxes may not occur in the order shown in the figures. For example, two boxes shown consecutively may actually be executed substantially simultaneously, or these boxes may sometimes be executed in reverse order depending on the functionality involved. It should also be noted that one or more boxes illustrated in the block diagram and / or flowchart, and combinations of boxes illustrated in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system that performs the specified functions or actions or implements a combination of dedicated hardware and computer instructions.

[0097] While the subject matter has been described above in the general context of computer-executable instructions for a computer program product running on a computer and / or multiple computers, those skilled in the art will recognize that this disclosure can also be implemented in conjunction with other program modules. Generally, program modules include routines, programs, components, data structures, etc., that perform specific tasks or implement abstract data types. Furthermore, those skilled in the art will understand that the computer implementation of the methods of the present invention can be practiced with other computer system configurations, including single-processor or multi-processor computer systems, microcomputing devices, mainframe computers, handheld computing devices (e.g., PDAs, cellular phones, etc.), microprocessor-based or programmable consumer or industrial electronic products, etc. The aspects shown can also be practiced in a distributed computing environment, where tasks are performed by remote processing devices linked via a communication network. However, some (if not all) aspects of this disclosure can be practiced on a standalone computer. In a distributed computing environment, program modules can reside in both local memory storage devices and remote memory storage devices.

[0098] As used herein, the terms “component,” “system,” “platform,” “interface,” etc., can refer to and / or may include computer-related entities or entities associated with an operable machine having one or more specific functionalities. Entities disclosed herein can be hardware, a combination of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, a thread of execution, a program, and / or a computer.

[0099] For illustration, both the application running on the server and the server itself can be components. One or more components may reside in an executing process and / or thread, and components may be located on a single computer and / or distributed across two or more computers. Furthermore, corresponding components may execute from various computer-readable media on which various data structures are stored. These components may communicate via local and / or remote processes, such as based on signals having one or more data packets (e.g., data from a component interacting with a local system, another component in a distributed system, and / or interacting with other systems via signals across a network (such as the Internet).

[0100] As another example, a component can be a device having specific functionality provided by mechanical parts operated by electrical or electronic circuitry, which is operated by software or firmware applications executed by a processor. In this case, the processor can be located internally or externally to the device and can execute at least a portion of the software or firmware application. As yet another example, a component can be a device that provides specific functionality through electronic components rather than mechanical parts, wherein the electronic components can include a processor or other means to execute software or firmware that at least partially endows the electronic components with functionality. In one aspect, a component can be simulated via a virtual machine (e.g., within a server computing system).

[0101] Furthermore, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or." That is, unless otherwise specified or clearly apparent from the context, "X adopts A or B" is intended to mean any natural inclusive arrangement. In other words, "X adopts A or B" is satisfied in any of the foregoing cases if X adopts A; X adopts B; or X adopts both A and B. Additionally, the articles "a" and "an" used in this specification and figures should generally be interpreted as meaning "one or more," unless otherwise stated or clearly indicated from the context to be in the singular form. As used herein, the terms "example" and / or "exemplary" are used to indicate examples, instances, or illustrations. For the avoidance of ambiguity, the subject matter disclosed herein is not limited to these examples. Furthermore, any aspect or design described herein as "example" and / or "exemplary" is not necessarily to be construed as preferred or superior to other aspects or designs, nor is it intended to exclude equivalent exemplary structures and techniques known to those skilled in the art.

[0102] As used in this specification, the term "processor" can substantially refer to any computing processing unit or device, including but not limited to a single-core processor; a single-core processor with software multithreading capabilities; a multi-core processor; a multi-core processor with software multithreading capabilities; a multi-core processor with hardware multithreading technology; a parallel platform; and a parallel platform with distributed shared memory. Additionally, a processor can refer to an integrated circuit, an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a field-programmable gate array (FPGA), a programmable logic controller (PLC), a complex programmable logic device (CPLD), discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. Furthermore, processors can utilize nanoscale architectures, such as, but not limited to, molecular and quantum dot-based transistors, switches, and gates, to optimize space utilization or enhance the performance of user equipment. Processors can also be implemented as a combination of computing processing units. In this disclosure, terms such as "memory," "storage device," "data storage," data storage device, "database," and any other information storage component substantially related to the operation and functionality of a component are used to refer to a "memory component," an entity included in "memory," or a component that includes memory. It should be understood that the memory and / or memory components described herein can be volatile or non-volatile memory, or may include both volatile and non-volatile memory. By way of illustration and not limitation, non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM, electrically erasable ROM, flash memory, or non-volatile random access memory (RAM) (e.g., ferroelectric RAM (FeRAM)). Volatile memory may include RAM, for example, RAM can be used as external cache memory. By way of illustration and not limitation, RAM can be obtained in various forms, such as synchronous RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), direct Rambus RAM (DRRAM), direct Rambus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM). Additionally, the memory components of the systems or computer-implemented methods disclosed herein are intended to include, but are not limited to, these and any other suitable types of memory.

[0103] The foregoing description includes only examples of systems, computer program products, and computer-implemented methods. It is certainly impossible to describe every possible combination of components, products, and / or computer-implemented methods in order to describe this disclosure, but those skilled in the art will recognize that many other combinations and arrangements of this disclosure are possible. Furthermore, where terms such as “comprising,” “having,” and “possessing” are used in the detailed description, claims, appendices, and drawings, such terms are intended to encompass in a manner similar to “comprising,” as “comprising” is interpreted as “including” when used as a transitional term in the claims. The descriptions of various embodiments are presented for illustrative purposes and are not intended to be exhaustive or limited to the disclosed embodiments. Various modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein has been chosen to best explain the principles of the embodiments, their practical application, or technical improvements to technology found in the market, or to enable those skilled in the art to understand the embodiments disclosed herein.

[0104] Based on the foregoing, it is understood that this document discloses several different implementation schemes, including preferred and alternative implementation schemes. For example, in one implementation scheme, a method for detecting water quality may involve: using a water meter to classify the quality of the water in conjunction with data indicating changes in ultrasonic time-of-flight (ToF) behavior due to impurities or combinations of such impurities mixed in the water; and classifying the impurities in the water using a sequence learning unit.

[0105] The implementation scheme may also involve obtaining data indicating changes in ultrasonic time-of-flight behavior from multiple ultrasonic sensors associated with the water meter.

[0106] The implementation scheme may also involve obtaining the data indicating the time-of-flight variation behavior of the ultrasound from at least two ultrasonic sensors associated with the water meter.

[0107] The implementation plan may also involve using the sequence learning unit to classify the impurity in the water into water quality parameters, which include at least one of the following: TDS (total dissolved solids), pH value, residual chlorine data, turbidity information, and total organic carbon value.

[0108] The implementation scheme may also involve communicating data to the user via radio frequency frames, indicating the impurities in the water classified using machine learning algorithms.

[0109] In the implementation scheme, it may also involve: using the sequence learning unit to classify the impurities in the water into water quality parameters, which include at least one of the following: TDS (total dissolved solids), pH value, residual chlorine data, turbidity information, and total organic carbon value; and conveying the water quality parameters associated with the water to the user via radio frequency frames.

[0110] In the implementation scheme, the sequence learning unit can be a machine learning algorithm.

[0111] In the implementation scheme, the data indicating the classification of the impurity in the water may be based on Time of Flight (ToF), Time Difference of Flight (DiffToF), and / or temperature information.

[0112] In one embodiment, an apparatus for detecting water quality may include: an ultrasonic sensor, wherein a water meter may be used to classify the quality of the water by combining data indicating ultrasonic time-of-flight (ToF) changes caused by impurities or combinations of such impurities mixed in the water, wherein the data indicating such ultrasonic ToF changes can be obtained from the ultrasonic sensor associated with the water meter; and a sequence learning unit that can classify the impurities in the water.

[0113] In the implementation scheme, the sequence learning unit classifies the impurity in the water as water quality parameters, which include at least one of the following: TDS (total dissolved solids), pH, residual chlorine, turbidity, and total organic carbon.

[0114] In the implementation scheme, the data indicating the impurity in the water, classified using a machine learning algorithm, can be transmitted to the user via radio frequency frames.

[0115] In the implementation scheme, the sequence learning unit can classify the impurity in the water into water quality parameters, which include at least one of the following: TDS (Total Dissolved Solids), pH value, residual chlorine data, turbidity information, and total organic carbon value; and can communicate the water quality parameters associated with the water to the user via radio frequency frames. As discussed above, the sequence learning unit may include machine learning algorithms. Furthermore, the data indicating the classification of the impurity in the water can be based on Time of Flight (ToF), Time Difference of Flight (DiffToF), and temperature information.

[0116] In one embodiment, a system for detecting water quality may include at least one processor and a memory storing instructions to cause the at least one processor to perform: classifying the quality of the water using a water meter, incorporating data indicating changes in ultrasonic time-of-flight (ToF) behavior due to impurities mixed in the water or combinations thereof; and classifying impurities in the water using a sequence learning unit.

[0117] In an implementation, the instruction may also be configured to cause the at least one processor to perform: obtaining data indicating changes in ultrasonic time-of-flight behavior from a plurality of ultrasonic sensors associated with the water meter.

[0118] In an implementation, the instruction may also be configured to cause the at least one processor to perform: obtaining data indicating changes in ultrasonic time-of-flight behavior from at least two ultrasonic sensors associated with the water meter.

[0119] In the implementation scheme, the instruction may also be configured to cause the at least one processor to perform: classify the impurities in the water into water quality parameters using the sequence learning unit, the water quality parameters including at least one of the following: TDS (total dissolved solids), pH value, residual chlorine data, turbidity information and total organic carbon value; and communicate the water quality parameters associated with the water to the user via radio frequency frames.

[0120] It should be understood that the variations and other features and functions disclosed above, or alternative forms thereof, can be advantageously combined into many other different systems or applications. It should also be understood that various alternatives, modifications, variations, or improvements that are not currently foreseen or anticipated can subsequently be made by those skilled in the art, and these alternatives, modifications, variations, or improvements are also intended to be covered by the following claims.

Claims

1. A method for detecting water quality, the method comprising: The water quality is classified using a water meter, in conjunction with data indicating changes in ultrasonic time-of-flight (ToF) behavior due to impurities or combinations of such impurities mixed in the water; and The impurities in the water are classified using a sequence learning unit.

2. The method of claim 1, further comprising obtaining the data indicating changes in ultrasonic time-of-flight behavior from a plurality of ultrasonic sensors associated with the water meter.

3. The method of claim 1, further comprising obtaining the data indicating ultrasonic time-of-flight variation behavior from at least two ultrasonic sensors associated with the water meter.

4. The method according to claim 1, further comprising: The sequence learning unit is used to classify the impurities in the water into water quality parameters, which include at least one of the following: TDS (total dissolved solids), pH value, chlorine residue data, turbidity information, and total organic carbon value.

5. The method according to claim 1, further comprising: Data indicating impurities in the water, classified using machine learning algorithms, is transmitted to the user via radio frequency frames.

6. The method according to claim 1, further comprising: The sequence learning unit is used to classify the impurities in the water into water quality parameters, which include at least one of the following: TDS (total dissolved solids), pH value, chlorine residue data, turbidity information, and total organic carbon value. as well as The water quality parameters associated with the water are communicated to the user via radio frequency frames.

7. The method of claim 1, wherein the data indicating the classification of the impurities in the water is based on Time of Flight (ToF), Time Difference of Flight (DiffToF), and temperature information.

8. An apparatus for detecting water quality, the apparatus comprising: An ultrasonic sensor, using a water meter, classifies the quality of the water by incorporating data indicating changes in ultrasonic time-of-flight (ToF) behavior due to impurities or combinations of said impurities mixed in the water, wherein the data indicating said ultrasonic ToF changes is obtained from the ultrasonic sensor associated with the water meter; and A sequence learning unit that classifies the impurities in the water.

9. The apparatus of claim 8, wherein the sequence learning unit classifies the impurities in the water into water quality parameters, the water quality parameters including at least one of the following: TDS (total dissolved solids), pH, residual chlorine, turbidity, and total organic carbon.

10. A system for detecting water quality, the system comprising: A memory and at least one processor, the memory storing instructions to cause the at least one processor to execute: The water quality is classified using a water meter, in conjunction with data indicating changes in ultrasonic time-of-flight (ToF) behavior due to impurities or combinations of such impurities mixed in the water; and The impurities in the water are classified using a sequence learning unit.

Images