KR102085122B1 - Real-time smart management system for tap water using artificial intelligence based on big data - Google Patents

Abstract

The present invention was created to solve the problems of a prior art. The problem to be solved in the present invention is to provide a real-time smart management system for tap water using big data-based artificial intelligence, which is installed in a water supply pipe and detects turbidity, pH, water temperatures, redox potentials and conductivity to check whether the water supply pipe is corroded while removing the distrust of tap water supply through water quality prediction. To solve the above problems, according to the present invention, the real-time smart management system for tap water using big data-based artificial intelligence comprises: a sensor device which is installed in each of a water intake pipe, a water pipe, a water conveyance pipe, and a water supply pipe to sense a water quality state for transferred water; a relay device which receives and relays a sensing value detected by the sensor device; a collection device which collects, stores, and manages the sensing value transmitted from the relay device; an analysis device analyzing tap water based on the sensing value stored in the collection device, and predicting water quality; and a display device visually displaying the result value analyzed by the analysis device and predicted risk factors. The analysis device determines whether a pipeline from water intake to water supply is normal or abnormal based on the collected sensing values, builds patterned data through big data analysis, determines analysis/prediction for the possibility of risk factors occurrence related to water quality, and provides the determined analyzed/predicted result values as visualization information.

Description

Tap-real-time smart management system using big data-based artificial intelligence {REAL-TIME SMART MANAGEMENT SYSTEM FOR TAP WATER USING ARTIFICIAL INTELLIGENCE BASED ON BIG DATA}

The present invention relates to a real-time smart management system for tap water using big data-based artificial intelligence. More specifically, the state data of the tap water can be measured in real time, and based on the measured state data, it is possible to analyze and predict the possibility of tap water hazards. The present invention relates to a real-time smart management system of tap water using big data-based artificial intelligence.

As the population growth and industrial development accelerate, the environmental and environmental problems are rapidly becoming a social issue. In particular, since water pollution threatens the health of the human body in relation to drinking water use, more thorough management of drinking water joint facilities such as springs, wells, and groundwater is required.

In addition, anxiety about tap water has increased due to the recent safety problems with tap water, and there is an increasing tendency not to use tap water as drinking water due to vague anxiety even in areas where tap water is not abnormal.

Degradation of tap water quality due to rust water discharge due to internal corrosion of distribution water pipes that connect tap water to consumers is the biggest cause of consumers' distrust of tap water.

Accordingly, various technologies for managing the water quality of tap water have been developed, and as one of such technologies, an integrated corrosion management system for preventing corrosion of water pipes is disclosed in Korean Patent Publication No. 10-1469890.

The technology is a filter paper for filtering the water in which the solid impurity precipitated in the sedimentation basin, a carbon dioxide gas injection unit is installed on the conveying path of the water transported from the filter paper to the purified water, and injecting carbon dioxide gas into the water passing through the filter paper; Liquid lime injection unit for injecting liquid lime into the water injected with carbon dioxide gas, Dissolution tank for dissolving liquid lime injected by the liquid lime injection unit in water, Dilution stabilization tank containing water passed through the dissolution tank, Carbon dioxide gas The first pH sensor to measure the pH of the water before the injection, the second pH sensor to measure the pH of the water contained in the dilution stabilization tank, the water supplied to the purified water from the dilution stabilization tank is supplied through the tap water piping facility connecting the purified water and tap water CO2 injection unit and liquid on the basis of the results detected by the pH detector and the pH detector used to measure the pH of the tap water By controlling the injection of calcium hydroxide, each unit is characterized in that a control unit for controlling the carbon dioxide and the liquid injection amount of calcium hydroxide.

However, the above technique requires injection of carbon dioxide gas, liquid lime, etc., and the pH of tap water should be measured at the place of use, resulting in a burden caused by the use of drinking water, and a problem of rapid rise in pH and turbidity when using liquid lime. .

In addition, Korean Patent Application Laid-Open No. 10-2015-0129934 discloses a portable water quality testing apparatus and method, and a water quality monitoring system using the same.

The technique includes a water quality test strip that reacts with a sample contained in the water to be tested to generate a color reaction; And when the water quality test strip is mounted, characterized in that it comprises a strip analyzer for generating water quality information for the water to be tested based on the color reaction.

However, the above technique has to be equipped with a water quality test strip at each required place for the test object, and there is a disadvantage in that it is not possible to check whether there is an abnormality in the pipe to which the tap water is transferred.

KR 10-1469890 B1 (2014. 12. 01.) KR 10-2015-0129934 A (November 23, 2015)

The present invention was created to solve the problems of the prior art, the problem to be solved in the present invention is installed in the water supply pipe, the turbidity, pH, water temperature, redox potential and conductivity to detect whether the corrosion of the water supply pipe At the same time, it provides a real-time smart management system for tap water using big data-based artificial intelligence that can solve the distrust of tap water supply through water quality prediction.

In order to solve the above problems, the real-time smart management system for tap water using big data-based artificial intelligence according to the present invention is a sensor device for sensing the water quality of water that is installed in each of the water intake pipe, the water pipe, the water pipe and the water pipe. ; A relay device which receives and senses a sensing value detected from the sensor device; A collecting device for collecting and storing the sensing value transmitted from the relay device; An analysis device for analyzing the tap water and predicting the water quality based on the sensing value stored in the collection device; And a display device for visually displaying the result value and the predicted risk factor analyzed by the analysis device, wherein the analysis device determines whether an abnormality of the pipe from the water intake to the water supply is determined based on the collected sensing values. In addition, the data is constructed through big data analysis, and the analysis / prediction of the possibility of occurrence of a risk factor for the water quality state is determined, and the determined analysis / prediction results are provided as visualization information.

Here, the sensor device comprises a sensor unit consisting of a plurality of sensors for detecting the water quality state; A sensor selection unit for selecting an operation of a sensor of the sensor unit; An ADC unit generating a sensing value by converting an analog signal output from the sensor unit selected by the sensor selecting unit into a digital signal, and outputting the generated sensing value; A control unit controlling to transmit the sensing value output from the ADC unit; And a communication unit configured to transmit the sensing value through a communication network under the control of the controller.

In addition, the sensing value detected by the sensor unit is characterized in that the iron ion concentration, copper ion concentration, suspended matter particles, electrical conductivity, pH, turbidity and residual chlorine concentration.

The analysis device may further include: a data separation unit configured to store and manage the collected sensing values by identification information; A data building unit for constructing situational data by patterning the sensing values classified by the identification information in the data separating unit; A prediction determination unit for analyzing a sensing value corresponding to an abnormal symptom among the situation-specific data constructed by the data construction unit and determining a prediction direction; And a self-learning updating unit for updating the situational data constructed by the data building unit.

In addition, the collection device includes a sensing value receiving unit for receiving in real time the sensing value detected from the sensor device; A sensing value storage unit for classifying and storing the sensing values received by the sensing value receiving unit according to identification information; And a sensing value transmitter for transmitting the sensing value stored in the sensing value storage to the analysis apparatus.

According to the present invention, it is possible to collect the water quality status for all the pipes from which the purified tap water is sent to the consumer from the process of collecting the source water, and predict the abnormality of the water quality based thereon, thereby improving the reliability of the tap water. There is this.

In addition, since one can detect turbidity, pH, water temperature, redox potential, and conductivity through one sensor device, it is easy to install the sensor device in a conduit, and there is an advantage of relatively easy transmission and reception of the detected sensing value.

1 is a schematic configuration diagram of a tap water facility to which the real-time smart management system of tap water using big data based artificial intelligence according to the present invention is applied.
2 is a block diagram of a real-time smart management system for tap water using big data-based artificial intelligence according to the present invention.
3 is a block diagram of a sensor device applied to the real-time smart management system of tap water using big data-based artificial intelligence according to the present invention.
Figure 4 is a schematic circuit diagram of the ADC unit applied to the real-time smart management system of tap water using big data-based artificial intelligence according to the present invention.
5 is a block diagram of a collecting device applied to the real-time smart management system of tap water using big data-based artificial intelligence according to the present invention.
6 is a block diagram of an analysis device applied to the real-time smart management system of tap water using big data-based artificial intelligence according to the present invention.
7 is a block diagram for predicting the progress direction for the pH according to an embodiment in a real-time smart water management system using big data-based artificial intelligence according to the present invention.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings.

The present invention relates to a real-time smart management system for tap water using big data-based artificial intelligence that can measure the state data of the tap water in real time, and can analyze and predict the possibility of the risk of tap water based on the measured state data.

1 is a schematic configuration diagram of a tap water real-time smart management system using the big data-based artificial intelligence according to the present invention, Figure 2 is a real-time smart management system for tap water using the big data-based artificial intelligence according to the present invention It is a schematic diagram.

1 and 2, the real-time smart water management system using big data-based artificial intelligence according to the present invention includes a sensor device 100, a collection device 200, an analysis device 300, and a display device 400. It is configured to include).

Here, the general water treatment facility for water supply is a water intake (10) to take water from the water source through the intake pipe (11), a water purification plant to receive the water taken from the intake (10) through the water pipe (21) to purify (20), the customer receiving the water purified in the water purification plant 20 through the water supply pipe 31 and temporarily stored in the reservoir 30 and the water stored in the water reservoir 30 is supplied through the water supply pipe 41 40, including.

Although not shown in the drawings. The water purification plant 20 includes a sedimentation basin, an intake pumping station, an impregnating well, a pre-ozone treatment plant, a mixed flocculation settling battery, a sand filter paper, a post ozone treatment plant, an activated carbon filter paper, a chlorine input chamber, a water purification plant, and a pressurized plant.

The sensor device 100 is installed in each of the pipelines, such as a water intake pipe, a water pipe, a water pipe, and a water supply pipe, and detects the water quality of the water transferred through the pipe.

3 is a view showing the configuration of a sensor device applied to the real-time smart management system for tap water using big data-based artificial intelligence according to the present invention.

Referring to FIG. 3, the sensor device 100 includes a sensor unit 110, a sensor selection unit 120, an ADC unit 130, a control unit 140, a communication unit 150, and a memory unit 160. It is configured to include.

The sensor unit 110 performs a function of detecting a water quality state and includes a plurality of sensors.

Here, the sensor constituting the sensor unit 110 includes an iron ion concentration sensor for detecting the concentration of iron ions, a copper ion concentration sensor for detecting the concentration of copper ions, a floating particle sensor for detecting the particle size of the suspended solids, and electrical conductivity. Electrical conductivity sensor for detecting, pH sensor for detecting pH, Turbidity sensor for detecting turbidity and residual chlorine concentration sensor for detecting the concentration of residual chlorine.

If necessary, the sensor unit 110 is a hydrogen ion concentration sensor for detecting the concentration of hydrogen ions, a water temperature sensor (Temp) for detecting the temperature of the water, a flow rate sensor for detecting the flow rate and a redox to detect the potential of the redox It may further include a potential sensor (ORP).

The sensor selection unit 120 selects an operation of the sensor of the sensor unit 110, and an iron ion concentration sensor, a copper ion concentration sensor, a suspended matter particle sensor, an electric conductivity sensor (ECC), a pH sensor, and a turbidity sensor ( TU) and the operating time point for each residual chlorine concentration sensor.

That is, the sensor selector 120 controls the power applied to the sensor so as not to detect the water quality state from two or more sensors at the same time.

In this case, the sensor selection unit 120 has a different input time of power based on the set time according to the type of sensor.

For example, each of the iron ion concentration sensor, copper ion concentration sensor, suspended matter particle sensor, electrical conductivity sensor, pH sensor, turbidity sensor and residual chlorine concentration sensor has a sensing time for detecting a water quality according to the configuration and properties of the sensor. In another configuration, the sensor selector 120 is configured to assign the input time of the power applied to each sensor in consideration of the characteristics of the sensor, and to operate the sensor according to the assigned input time.

In addition, based on a user setting, some sensors may be configured not to operate by preventing power from being supplied.

The ADC 130 generates a sensing value by converting an analog signal output from the sensor unit selected by the sensor selecting unit into a digital signal, and outputs the generated sensing value.

4 is a schematic circuit diagram of an ADC unit applied to a real-time smart management system of tap water using big data-based artificial intelligence according to the present invention.

Referring to FIG. 4, the ADC 130 includes a sample amplification module 131 for sampling and amplifying the analog signal output from the sensor, and an input voltage and a reference for the analog signal output from the sample amplification module 131. Comparison results of the differential module 132 for calculating and outputting a difference in voltage, the first comparison module 133 and the first comparison module 133 for comparing the input voltage and the reference voltage output from the differential module 132. Generates 1 when the input voltage is higher than the reference voltage, and generates a reference voltage for the output voltage of the logic module 134 and the sample amplification module 131 that output 0 when the input voltage is lower than the reference voltage. And a second comparison module 136 comparing the input voltage output from the sample amplification module 131 and the half voltage which is 1/2 of the dynamic detection voltage.

At this time, the reference voltage generation module 135 generates a reference voltage by dividing the upper bit module and the lower bit module, and if the input voltage is higher than the half voltage according to the comparison result of the second comparison module 136, The reference module is configured to generate a reference voltage, and when the input voltage is lower than the half voltage, the lower bit module generates a reference voltage.

In the above configuration, the output of the digital signal to the analog input voltage is repeated by the set number of bits, and when the most significant bit to the least significant bit is determined, the combined digital signal is output from the most significant bit to the least significant bit.

For example, in the case of designing the ADC unit 130 having an output of 10 bits, the differential module 132, the first comparator 133, the logic unit 134, and the reference voltage generator for one sampled period. 135 rotates 10 times to generate and output a 10-bit digital signal.

However, such a signal conversion method requires N bits to be performed for one sampled period, which may cause an overload on the ADC 130.

In order to solve this problem, the ADC unit 130 applied to the present invention is provided with a second comparison module 136.

The second comparison module 136 detects the position of the input signal of the biosignal with respect to the dynamic detection voltage in advance by comparing the input voltage output from the sample amplification module 131 with a half voltage that is 1/2 of the dynamic detection voltage. Done.

For example, on the assumption that the dynamic detection voltage detectable by the ADC unit 130 is 0 to 10V, when the analog input voltage is converted into a 10-bit digital signal as described above, half of the input voltage and the dynamic detection voltage are as follows. By comparing the value of 5V (half voltage), if the input voltage is higher than half voltage, a valid value is assigned to the upper 5 bits, and conversely, if the input voltage is lower than half voltage, a valid value is assigned to the lower 5 bits. The digital signal can be output by the conversion operation for N / 2 bits during one cycle.

By providing the second comparison module 136 as described above, the reference voltage generation module 135 generates a reference voltage by dividing the upper bit module and the lower bit module, but the comparison result of the second comparison module 136 The reference voltage may be configured to generate a reference voltage in the upper bit unit 135a when the input voltage is higher than the half voltage, and generate a reference voltage in the lower bit module 135b when the input voltage is lower than the half voltage. .

The control unit 140 performs a function of controlling to transmit a sensing value which is a digital signal value output from the ADC unit 130.

In addition, the sensing value includes identification information including location information and pipeline information of a location where the sensor device 100 is installed, and the identification information is stored and managed in the memory unit 160.

That is, the control unit 140 is controlled to be transmitted in a state in which the identification information stored in the memory unit 160 is included in the sensing value which is a digital signal value output from the ADC unit 130.

In addition, the controller 140 controls the sensor selection unit 120 based on the sensor operation time stored in the memory unit 160.

The communication unit 150 transmits the sensing value generated by the ADC unit 130 under the control of the controller 140 through a communication network. The communication network may include a local area network such as Bluetooth, ZigBee, Radio Frequency Identification (RFID), Infrared Data Association (IrDA), and Ultra Wideband (UWB).

In the above configuration, the sensor device 100 is distributed in a very wide area as it is installed in the pipelines, such as water intake pipe, water pipe, water pipe and water supply pipe.

Therefore, it may be difficult to transfer the sensing value to the remote collection apparatus 200 through the communication unit 150 of each sensor device 100.

Accordingly, the relay device 101 may be configured to receive and sense the sensing value detected from the sensor device 100.

The relay device 101 is installed at a position close to the sensor device 100 to receive a sensing value transmitted from the sensor device 100, and collects the received sensing value through a wired / wireless communication method 200. To send).

The collection device 200 collects and stores the sensing values transmitted from the relay device 101.

5 is a view showing the configuration of a collecting device applied to the real-time smart management system of tap water using big data-based artificial intelligence according to the present invention.

Referring to FIG. 5, the collection device 200 includes a sensing value receiver 210, a sensing value storage 220, and a sensing value transmitter 230.

The sensing value receiving unit 210 receives the sensing value detected from the sensor device 100 in real time, and the sensing value includes identification information.

In addition, the sensing value receiver 210 includes a real time clock (RTC), so that the real time time information and the day and date information based on the RTC are also received.

The sensing value storage unit 220 performs a function of classifying and managing the sensing values received by the sensing value receiving unit 210 according to identification information.

For example, the sensing value storage unit 220 stores and manages the received sensing value based on identification information including location information and pipeline information.

The sensing value transmitter 230 transmits the sensing value stored in the sensing value storage unit 220 to the analysis device 300.

The analysis device 300 analyzes and predicts a risk factor based on a sensing value stored in the collecting device 200. The analysis device 300 classifies the collected sensing values by identification information and compares the sensing values classified by the identification information. It builds situational data and analyzes and predicts risk factors for sensing values through artificial intelligence analysis using the constructed situational data to provide visualization information.

6 is a view showing the configuration of the analysis device applied to the real-time smart management system of tap water using big data-based artificial intelligence according to the present invention.

Referring to FIG. 6, the analysis apparatus 300 includes a data separator 310, a data builder 320, a prediction determiner 330, and a self-learning updater 340.

The data separator 310 performs a function of storing and managing the collected sensing values by identification information. That is, the data separation unit 310 stores and manages the sensing value by dividing the identification information included in the collected sensing value.

The data builder 320 performs a function of constructing situational data by patterning the sensing values classified by the identification information in the data separator 310.

In the above, the patterning is to calculate a normal range for each sensing value based on the associated sensing value, and to define various situations in which the sensed value detected in the calculated normal range deviates from the warning limit value.

For example, looking at the patterning of the pH as an example, when the pH of the normal range is calculated, if the pH sensed in one pipeline is relatively higher than the pH sensed in the other pipeline, the pH inside the pipeline may be increased. It is designed to generalize various situations that can occur depending on the possible factors.

Accordingly, the data construction unit 320 calculates a normal range value under the same type of condition, but constructs situational data by patterning a trend in which a sensing value outside the normal range value changes according to various situations.

In the above-described method, the patterning of trends changed according to various situations refers to a method of analyzing a large amount of data through a machine learning algorithm, finding a pattern from the pattern, and predicting the pattern. Based on the empirical data accumulated through interaction, the model is automatically built and the model is built.

The prediction determiner 330 analyzes the sensing value corresponding to the abnormal symptom based on the related sensing value among the situation-specific data constructed by the data building unit 320 and determines a prediction direction.

Accordingly, the prediction determination unit 330 includes an abnormal symptom check module 331, an associated sensing value derivation module 332, a warning limit value setting module 333, and a prediction direction determination module 334.

The abnormal symptom check module 331 detects and checks a sensing value corresponding to the abnormal symptom among the sensing values.

That is, the abnormal symptom check module 331 performs a function of checking whether the detected sensing value is in the normal range, and confirms whether the detected sensing value is in the normal range calculated by the data building unit 320. If it does not belong to the normal range, it is judged as an abnormal symptom.

The related sensing value deriving module 332 determines a factor that affects the sensing value checked by the abnormal symptom checking module 331 as the related sensing value and performs a function of deriving the determined related sensing value.

The sensing value determined as an abnormal symptom may be related to the aging of purified water and pipelines used in water purification plants.

Therefore, the associated sensing value derivation module 332 derives the associated sensing values (iron ion concentration, copper ion concentration, suspended matter, electrical conductivity, turbidity, residual chlorine) of various elements associated with the sensing value determined as the abnormal symptom.

In this case, the associated sensing value derivation module 332 is configured to give a weight to the derived sensing value.

In one embodiment, since the direct cause of the element of temperature is heat, the weight of the associated sensing value for the element capable of generating heat is set to be high. That is, different weights are applied to each sensing value (element), but a higher weight is applied to a sensing value corresponding to a direct element, a lower weight is applied to a sensing value corresponding to an indirect element, and vice versa. In case of, the inverse weight (negative value) is applied.

The warning threshold setting module 333 calculates a warning threshold value for the sensing value checked by the abnormal symptom check module 331 based on the related sensing value derived from the related sensing value derivation module.

That is, the warning threshold value calculated by the warning threshold value setting module 333 is varied according to the factors affecting the sensing value, and the warning threshold value is changed according to the associated sensing value.

The prediction direction determination module 334 performs a function of predicting the direction in which the sensing value proceeds.

Figure 7 shows a block diagram for predicting the progress direction for the pH according to an embodiment in a real-time smart management system for tap water using big data-based artificial intelligence according to the present invention.

Referring to FIG. 7, the situation-specific data for each sensing value is constructed by patterning the trend that is changed from the sensing values detected by the plurality of sensor devices 100, and is appropriate from the range of the constructed situation-specific data. The normal range value is set.

Further, in the related art, when the sensing value falls outside the warning limit value while the warning limit value is fixed, it is determined as an abnormal symptom, whereas in the present invention, the warning limit value changes over time according to another sensing value associated with the sensing value. Therefore, an abnormal symptom for the sensing value may be determined based on the warning threshold value that changes over time.

As shown in FIG. 7, it can be seen that when the detection range of the sensing value is out of the normal range in the state where the warning threshold is calculated low, the sensing value approaches the warning threshold.

However, the prediction or determination as to whether to proceed to the risk range (1), maintenance (2) or normal range (3) with respect to the detected sensing value may be differently derived based on the associated sensing value associated with the detected sensing value. .

The self-learning updating unit 340 performs a function of updating the situational data constructed in the data building unit. The data accumulated through the update is used for various learning of the patterned situational data, and is also used as data of an algorithm for predictive judgment.

Next, the display device will be described.

The display device 400 visually displays the risk factors predicted by the analysis device 300 and performs a function of receiving and displaying visualization information provided from the analysis device 300 through wired / wireless communication.

In this case, when it is determined that a specific sensing value exceeds a warning limit, the analyzing apparatus 300 may be configured to generate an alarm signal according to the sensing value.

According to the present invention, since water quality can be collected for all the pipelines that deliver purified tap water to the consumer from the process of collecting the source water, and can predict the abnormality of the water quality based thereon, the reliability of the tap water can be improved. There is this.

In addition, since it is possible to detect turbidity, pH, water temperature, redox potential and conductivity through one sensor device, it is easy to install the sensor device in the pipeline, and there is an advantage that the transmission and reception of the detected sensing value is relatively easy.

Although the preferred embodiment of the present invention has been described above, the scope of the present invention is not limited thereto, and it should be understood that the scope of the present invention extends to the range that is substantially equivalent to the embodiment of the present invention. Various modifications can be made by those skilled in the art without departing from the spirit of the invention.

100: sensor device 101: relay device
110: sensor unit 120: sensor selection unit
130: ADC unit 140: control unit
150: communication unit 160: memory unit
200: collecting device 210: sensing value receiving unit
220: sensing value storage unit 230: sensing value transmission unit
300: analysis device 310: data separation unit
320: data construction unit 330: prediction determination unit
340: self-learning update unit 400: display device

Claims (5)

Sensor device for sensing the water quality of the water is installed in each of the water intake pipe, water pipe, water pipe and water supply pipe;
A relay device which receives and senses a sensing value detected from the sensor device;
A collecting device for collecting and storing the sensing value transmitted from the relay device;
An analysis device for analyzing the tap water and predicting the water quality based on the sensing value stored in the collection device; And
A display device for visually displaying a result value analyzed in the analysis device and a predicted risk factor;
It is configured to include,
The analysis device,
Based on the sensed values collected, it is determined whether there is an abnormality in the pipeline from intake to water supply, constructing patterned data through big data analysis, and determining the analysis / prediction of the possibility of occurrence of a risk factor for water quality. Provides the analyzed / predicted result value as visualization information,
The sensor device,
A sensor unit comprising a plurality of sensors for detecting a water quality state;
A sensor selection unit for selecting an operation of a sensor of the sensor unit;
An ADC unit generating a sensing value by converting an analog signal output from the sensor unit selected by the sensor selecting unit into a digital signal, and outputting the generated sensing value;
A control unit controlling to transmit the sensing value output from the ADC unit; And
A communication unit transmitting the sensing value through a communication network under the control of the controller;
Including,
The sensor selection unit,
At the same time, the power applied to the sensor is controlled so as not to detect the water quality from two or more sensors, but the input time of the power is different based on the set time according to the type of the sensor.
The ADC unit,
A sample amplifier module for sampling and amplifying the analog signal output from the sensor;
A differential module for calculating and outputting a difference between an input voltage and a reference voltage with respect to the analog signal output from the sample amplifier module;
A first comparison module for comparing an input voltage and a reference voltage output from the differential module;
A logic module that outputs 1 when the input voltage is higher than the reference voltage as a result of the comparison of the first comparison module, and outputs 0 when the input voltage is lower than the reference voltage;
A reference voltage generation module for generating a reference voltage for the output voltage of the sample amplification module; And
A second comparison module comparing the input voltage output from the sample amplification module with a half voltage that is 1/2 of a dynamic detection voltage;
Including,
The reference voltage generation module,
The reference voltage is generated by dividing the upper bit module and the lower bit module. When the input voltage is higher than the half voltage according to the comparison result of the second comparison module, the reference voltage is generated by the upper bit unit. If lower than half voltage, lower bit module generates reference voltage.
The sensing value detected by the sensor unit,
Hydrogen ion concentration, water temperature, flow rate, redox potential, iron ion concentration, copper ion concentration, suspended matter particles, electrical conductivity, pH, turbidity and residual chlorine concentration,
The analysis device,
A data separator configured to store and manage the collected sensing values by identification information;
The data separating unit calculates a normal range for each sensing value with respect to the sensing values classified for each identification information, and constructs data for each situation through patterning that defines a situation in which the detected sensing values deviate from a warning limit. Construction unit;
A prediction determination unit for analyzing a sensing value corresponding to an abnormal symptom among the situation-specific data constructed by the data construction unit and determining a prediction direction; And
A self-learning updating unit updating the situational data constructed by the data building unit;
Including;
The prediction determination unit,
An abnormal symptom check module for detecting and checking a sensing value corresponding to the abnormal symptom among the sensing values;
An associated sensing value deriving module configured to determine a factor that affects the sensing value checked by the abnormal symptom confirming module as an associated sensing value, and perform a function of deriving the determined related sensing value;
A warning threshold setting module configured to calculate a warning threshold value for the sensing value confirmed by the abnormal symptom check module, based on the related sensing value derived from the related sensing value derivation module; And
It includes a prediction direction determination module for performing a function for predicting the direction of the sensing value,
The associated sensing value derivation module is configured to give a weight to the derived sensing value,
The warning threshold value calculated by the warning threshold value setting module is varied according to factors influencing the sensing value.
Real-time tap water using big data-based artificial intelligence, characterized in that the abnormality of the sensing value is determined based on the warning limit that changes over time according to the warning limit that changes with time according to the other sensing value associated with the sensing value. Smart management system.
delete delete delete The method according to claim 1,
The collection device,
A sensing value receiving unit which receives the sensing value detected from the sensor device in real time;
A sensing value storage unit for classifying and storing the sensing values received by the sensing value receiving unit according to identification information; And
A sensing value transmitter for transmitting the sensing value stored in the sensing value storage to the analysis apparatus;
Tap water real-time smart management system using big data-based artificial intelligence, characterized in that comprises a.

Images