Remote monitoring method and system for intelligent water purification equipment

Abstract

The invention relates to the technical field of remote monitoring, in particular to a remote monitoring method and system for intelligent water purification equipment. The system comprises a sensing execution unit, a data routing unit, an intelligent central unit and an interactive service unit. The intelligent central unit is used for comparing underground water quality data collected in real time with corresponding month threshold values over the years, water quality fluctuation caused by natural changes such as seasonal replacement can be accurately distinguished, the water quality data interpretation accuracy is improved, when the water quality data deviates from a normal range and influences of natural laws are eliminated, the system introduces real-time weather data, and the water quality data interpretation accuracy is improved. And the analysis module considers the effect of weather on water quality by means of a dynamic structure equation model and resets a threshold value. The intelligent self-adaptive mechanism can effectively distinguish water quality abnormity caused by non-natural laws, for example, normal fluctuation of water quality after rainstorm is recognized, accuracy and intelligence of water quality monitoring are enhanced through multiple times of accurate judgment, and abnormity can be quickly recognized and early warned.

Description

Technical Field

[0001] The present invention relates to the field of remote monitoring technology, and in particular to a remote monitoring method and system for smart water purification equipment. Background Art

[0002] In today's urban development, ensuring the safety of groundwater purification quality is of vital importance. To achieve efficient water quality monitoring, remote monitoring technology has been widely used in pH value monitoring during urban groundwater purification. In existing remote monitoring systems, the device layer collects groundwater pH values daily through sensors. The values are processed and packaged into digital signals and transmitted to the cloud via a communication gateway and multiple protocols. The cloud platform layer receives and parses the data and stores it in a database for analysis. The application layer retrieves the data from the cloud through mobile or PC applications and presents it in an intuitive form for users to view. In urban groundwater quality monitoring systems, the pH threshold can be adjusted based on seasonal characteristics. This measure aims to effectively reduce the probability of false alarms caused by pH fluctuations due to regular natural changes, such as temperature and sunlight duration during seasonal changes. However, when irregularities occur compared to the same date in previous years, false alarms can easily occur due to weather factors. For example, in a certain region, under normal circumstances, the average rainfall in the region in a specific season in previous years is X mm. However, this year, due to a variety of complex factors such as abnormal atmospheric circulation, the actual rainfall in that season far exceeded X mm, reaching C mm (C>X). The excessive rainfall caused a large amount of rainwater to seep into the ground, changing the chemical composition and ion concentration of the groundwater and triggering the water quality pH value alarm. Moreover, due to the continuous natural rainfall process, the alarms continued. Such false alarms caused by irregular weather not only interfered with the judgment of the real water quality problem, but also greatly consumed human and material resources for verification, affecting the normal operation of the water quality monitoring system and the timeliness and effectiveness of urban groundwater quality security. In addition, irregular weather conditions can cause groundwater quality to exhibit complex and diverse variations, meaning that thresholds set based on fixed patterns are unlikely to meet the diverse actual water quality monitoring needs in different regions and under different types of irregular weather conditions. In order to solve the above problems, there is an urgent need for a remote monitoring method and system for smart water purification equipment. Summary of the Invention

[0003] The purpose of the present invention is to provide a remote monitoring method and system for smart water purification equipment. It collects the pH value of urban groundwater through sensors, combines it with comparative analysis of data from the same period in previous years in the data lake warehouse, introduces meteorological factors to determine the cause of water quality anomalies, dynamically adjusts the threshold and visualizes the results at the application layer, thereby improving the intelligence and accuracy of water quality monitoring and efficiently identifying potential water quality risks.

[0004] To achieve the above-mentioned objectives, one of the objectives of the present invention is to provide a remote monitoring system for smart water purification equipment, including a perception execution unit, a data routing unit, an intelligent central unit and an interactive service unit. The water quality data of groundwater is collected by the perception execution unit, processed by the data routing unit and the data is transmitted to the intelligent central unit. The intelligent central unit is used to analyze the transmitted data and provide the analysis results to the user through an intuitive interactive interface through the interactive service unit.

[0005] Furthermore, the intelligent central unit includes a data lake warehouse and an analysis and decision-making module. The data lake warehouse is used to hierarchically store the water quality data collected by the perception execution unit over the years, archive the structured water quality data through a time series database, and construct a data cube to realize multi-dimensional analysis; the dynamic mean and standard deviation of the monthly water quality parameters of each monitoring point are calculated based on the sliding window algorithm, and after removing the outliers in combination with the box plot rule, an adaptive threshold interval with "monthly mean ± 2 times the standard deviation" as the boundary is generated, which is recorded as the regular threshold; the final output regular threshold will be synchronized to the rule engine of the analysis and decision-making module as the basis for judging water quality anomalies, and the threshold iteration interface is retained for manual calibration.

[0006] Water quality data from previous years is stored in the data lake warehouse, and a hierarchical storage process is initiated. Then, structured data is archived using a time series database, and a data cube is constructed to implement multi-dimensional analysis. At the same time, monthly regular thresholds are generated and finally output to the analysis and decision-making module as a basis for comparison, enhancing the accuracy and intelligence of water quality monitoring and enabling flexible calibration.

[0007] As a further improvement of the present technical solution, the judgment module is used to compare the real-time monitoring water quality data generated by the edge computing module with the historical threshold data retrieved from the data lake warehouse. The judgment module adopts a hierarchical judgment technology. If the water quality data is within the regular threshold range, the monitored water quality data is directly synchronized to the interactive service unit. If the water quality data is outside the regular threshold range, the monitored water quality data will be transmitted to the analysis module. The analysis module receives real-time weather data and uses a dynamic structural equation model to determine whether the current weather factors have an impact on the water quality monitoring values. If the weather factors affect the water quality values, the expected water quality baseline value under the weather conditions is generated through correlation analysis and recorded as the adaptive threshold. The adaptive threshold is compared and analyzed with the real-time monitoring water quality data reported by the edge computing module. If the real-time monitoring data is within the range of the adaptive threshold, the data is synchronized to the real-time monitoring dashboard of the interactive service unit. If the real-time monitoring data exceeds the range of the adaptive threshold, a water quality abnormality warning signal is generated through the dynamic threshold method formula.

[0008] The judgment module captures the real-time monitoring water quality data generated by the edge computing module in real time, triggering a comparison process with the historical regular threshold data in the data lake warehouse; then, using dynamic matching and hierarchical judgment technology, if the water quality data is within the regular threshold range, it is directly synchronized to the interactive service unit; if it exceeds the range, it is transmitted to the analysis module. The analysis module combines real-time weather data and uses a dynamic structural equation model to determine the impact of weather on water quality. Through correlation analysis, an adaptive threshold is generated and compared with the real-time data. If it is within the allowable range, it is synchronized to the interactive service unit dashboard. If it exceeds the range, a water quality abnormality warning signal is generated, which enhances the accuracy and intelligence of water quality monitoring and efficiently identifies water quality abnormalities.

[0009] A second object of the present invention is to provide a method for a remote monitoring system of a smart water purification device, comprising the following steps: S1, the sensing execution unit obtains the pH value of water quality, cleans and calibrates abnormal values, and uploads the processed data to the intelligent central unit through the data routing unit; S2. Retrieve the data of the same period in previous years for the monitoring point and calculate the benchmark reference value; S3. Based on the rainfall and temperature fluctuation range in real-time meteorological station data, a dynamic adjustment model is established to automatically correct the reasonable fluctuation range threshold of the pH value; S4. Compare and analyze the real-time pH value of the water quality with the dynamically adjusted threshold value. If the pH value exceeds the threshold range, combine the current meteorological data to determine whether the anomaly is caused by natural factors. If natural factors are ruled out, the situation is marked as a potential pollution event; S5. Perform graded responses based on the degree of abnormality and highlight abnormal monitoring points in the interactive service unit.

[0010] Compared with the prior art, the present invention has the following beneficial effects: 1. In the remote monitoring method and system of this smart water purification equipment, the data lake warehouse of the intelligent central unit can compare the real-time groundwater quality data with the threshold values of the corresponding months in previous years. Through this operation, it is possible to clearly identify whether the changes in water quality conform to natural laws. For example, when the seasons change, the normal fluctuations of certain water quality indicators can be accurately distinguished to avoid misjudging water quality abnormalities due to routine natural changes. This greatly improves the accuracy of the interpretation of water quality data, lays a solid foundation for subsequent analysis, and allows users to intuitively understand the natural evolution trend of water quality in the time dimension.

[0011] 2. In the remote monitoring method and system of this smart water purification equipment, if the water quality data deviates from the normal range and the influence of natural laws is excluded, the system intervenes in the real-time weather data of the region. The analysis module uses a dynamic structural equation model to consider the impact of weather factors on water quality and reset the threshold. This intelligent adaptive mechanism can effectively distinguish water quality anomalies caused by non-natural laws. For example, if the water quality changes briefly after a rainstorm, the system can accurately determine that it is a normal fluctuation caused by the weather, rather than abnormal pollution. Through multiple precise judgments, the accuracy and intelligence of water quality monitoring are greatly enhanced. It can quickly and efficiently identify real water quality anomalies and issue early warnings in a timely manner, thereby enhancing the accuracy and intelligence of water quality monitoring and efficiently identifying water quality anomalies. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 It is a block diagram of the overall system structure of the present invention; Figure 2 This is a specific flow chart of the analysis and decision-making module of the present invention; Figure 3 Schematic diagram of the overall method of the present invention.

[0013] The meaning of each number in the figure is: 100, perception execution unit; 200, data routing unit; 300, intelligent central unit; 400, interactive service unit; 101. Water quality sensing module; 102. Edge computing module; 301. Data Lake Warehouse; 302. Analysis and Decision-Making Module; 310. Judgment module; 320. Analysis module. DETAILED DESCRIPTION

[0014] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0015] The terms used in the exemplary embodiments shown in the drawings are not intended to limit the present invention. In the drawings, the same units / elements are given the same reference numerals.

[0016] Unless otherwise specified, the terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art. Furthermore, it is understood that terms defined in commonly used dictionaries should be understood to have meanings consistent with the context of their relevant fields and should not be interpreted as idealized or overly formal.

[0017] The following are some definitions of terms: The interactive service unit 400 is a key unit used to present the analysis results of the remote monitoring system of the smart water purification equipment and realize convenient interaction between the user and the system. The user can access this unit through a mobile phone or PC. The user can intuitively obtain the system's analysis results of groundwater quality monitoring, such as real-time water quality status, abnormal warning information, etc.

[0018] Remote monitoring technology has been widely used in pH monitoring for urban groundwater purification. Existing systems collect data at the device level, transmit it to the cloud for analysis via communications, and then present it at the application level. While thresholds can be adjusted based on seasonal characteristics to reduce false alarms, irregular weather conditions can still easily trigger false alarms, and fixed thresholds are difficult to adapt to the complex and changing needs of water quality monitoring. Next, please refer to Figure 1-Figure 2 As shown, one of the purposes of this embodiment is to provide a remote monitoring system for smart water purification equipment, including a sensing execution unit 100, a data routing unit 200, an intelligent hub unit 300 and an interactive service unit 400; The perception execution unit 100 is used to collect urban groundwater quality data entering the water purification equipment. The data focuses on the pH value of the water. The perception execution unit 100 includes a water quality perception module 101 and an edge computing module 102. The water quality perception module 101 is used to obtain the pH value of the groundwater. The edge computing module 102 further processes the signal based on the work of the water quality perception module 101 to generate a structured data subset.

[0019] In specific use, the water quality sensing module 101 deploys a water quality sensor to capture the raw pH signal of the water in real time. This is the lowest level of the entire data processing process and directly interacts with the outside world. Water quality sensors are conventional technology that reflect the pH value of the solution through changes in electrode potential and output analog voltage signals. Hardware circuits ensure that the signal is transmitted to the analog-to-digital converter. Because the raw signal output by the sensor is an analog signal, it is difficult to be directly processed by the subsequent digital system. The water quality sensing module 101 needs to be processed by the analog-to-digital converter. The analog-to-digital converter uses a successive approximation conversion algorithm to sample the continuous analog signal at a fixed sampling frequency such as 100 Hz, collecting a corresponding number of data per second. The sampled analog values are then quantized according to the classified levels. Specifically, it is the connection between the water quality sensor and the data preprocessing layer, responsible for the cross-layer conversion from analog signals to digital signals. The successive approximation ADC (SAR ADC) uses internal registers for bit-by-bit approximation. For example, an 8-bit ADC requires eight comparisons to complete a conversion, with each comparison generating a 1-bit digital signal (0 or 1), which is ultimately combined into an 8-bit binary number (0-255). Sampling is performed 100 times per second to ensure that high-frequency signals (such as sudden changes in pH) are not missed, in line with the Nyquist sampling theorem (the sampling frequency must be greater than twice the highest frequency of the signal); Quantization level design: the 0-5V voltage range is divided into 256 levels (2 8 ), the corresponding voltage value of each level is 5V / 255≈0.0196V, and the quantization error is ±0.0098V, which reflects the precision control technology of the digital process.

[0020] The edge computing module 102 receives the digital signal, pre-processes it, and uses an interpolation algorithm to compensate for data that may be missing in data transmission. At the same time, it mines the changing trend, fluctuation amplitude and other characteristics of the pH value, and finally generates a structured water quality data subset to support subsequent data transmission and analysis.

[0021] Furthermore, the data routing unit 200 is used in the system to transmit data. It uses LoRa wireless communication technology to transmit the structured water quality data subset collected and preliminarily processed by the perception execution unit 100. During transmission, the data is encapsulated in accordance with the established Modbus communication protocol to ensure that the data can be correctly identified and parsed by the intelligent central unit 300. At the same time, it will monitor the network status in real time and use the AODV routing algorithm to plan the optimal path with the strongest signal, the least interference, and the shortest transmission delay, so that the water quality data can be transmitted to the intelligent central unit 300 quickly and stably.

[0022] The intelligent central unit 300 includes a data lake warehouse 301 and an analysis and decision module 302. When the data lake warehouse 301 hierarchically stores the water quality data collected by the perception execution unit 100 over the years, it performs data processing and threshold calculation: Data storage layer: accepts the structured water quality data generated after preliminary processing by the edge computing module 102, and archives and stores these data through a time series database. The time series database can process data with timestamps, which is convenient for subsequent query and analysis by time dimension. At the same time, a data cube is constructed to organize the water quality data according to different dimensions (such as time, monitoring point, water quality parameters, etc.). By reorganizing the water quality data according to multiple dimensions such as time, geographical location of the monitoring point, and category of water quality parameters, users can cross-analyze the water quality data from multiple angles, such as comparing the pH value differences of different monitoring points at the same time, or analyzing the correlation between different water quality parameters at the same monitoring point, thereby realizing multi-dimensional analysis of water quality data, so as to gain an in-depth understanding of the water quality conditions from multiple angles.

[0023] Threshold calculation layer: Based on the water quality data stored in the data storage layer, the water quality parameters of each monitoring point are processed monthly based on the sliding window algorithm to calculate the dynamic mean and standard deviation. The sliding window algorithm operates on the monthly data of each monitoring point. By setting a fixed time window (such as one month), the window slides on the time series, and the mean and standard deviation of the data in the window are calculated in real time, so that the statistical results are dynamically updated as new data flows in, rather than static fixed values. It can timely reflect the central trend (mean) and dispersion (standard deviation) of the water quality parameters of the month, providing a dynamic statistical basis for subsequent analysis. Then, the data is filtered in combination with the box plot rule to eliminate the Outliers, among which the box plot rule constructs the data distribution boundary based on the quartiles (Q1, Q3) and the interquartile range (IQR). Data smaller than Q1-1.5IQR or larger than Q3+1.5IQR are identified as outliers and eliminated. Extreme values caused by accidental factors such as sensor failure and transmission errors are filtered out to ensure that the data used to calculate the threshold can better represent the normal fluctuation characteristics of water quality and avoid the interference of abnormal data on the threshold calculation. Finally, an adaptive threshold interval is generated with "monthly mean ± 2 times the standard deviation" as the boundary, which is recorded as the regular threshold. This threshold can be dynamically adjusted according to the actual distribution of water quality data to better fit the actual fluctuation range of water quality. Based on the normal distribution theory in statistics (approximately 95.4% of the data fall within the range of ±2σ of the mean), and combined with the characteristic that water quality data in natural conditions usually presents an approximately normal distribution, the threshold interval is generated with the dynamic mean as the center and 2 times the standard deviation as the fluctuation range. Since the sliding window algorithm causes the mean and standard deviation to change with monthly data updates, the threshold interval can adapt to the actual distribution of water quality data in real time. Compared with fixed thresholds, it can more accurately reflect the natural fluctuation patterns of water quality in different months and different monitoring points, and effectively distinguish normal fluctuations from true anomalies.

[0024] Output layer: The regular threshold generated by the threshold calculation layer is synchronized to the rule engine of the analysis and decision-making module 302. The rule engine will judge the real-time water quality data based on the regular threshold, and use it as an important basis for determining water quality anomalies. At the same time, in order to increase the flexibility and controllability of the system, the threshold iteration interface is retained, allowing manual calibration and adjustment of the regular threshold according to actual conditions to ensure the accuracy and reliability of water quality anomaly determination.

[0025] The judgment module 310 in the system is used to compare and analyze the real-time water quality data generated by the edge computing module 102 with the historical regularity threshold data retrieved from the data lake warehouse 301. It uses a hierarchical judgment technology to accurately judge the water quality status. Because the water quality data in the same region and the same month are relatively stable, the historical regularity threshold data in the data lake warehouse 301 is constructed based on the average value of the same month in previous years. The grading judgment technology divides the water quality conditions into different levels according to the degree of difference between the real-time monitored water quality data and the historical regular threshold data. When the real-time monitored water quality data is within the regular threshold range determined by the average value of the month in previous years, this indicates that the water quality condition is in a normal fluctuation range and is consistent with the historical water quality change pattern of the region for the month. At this time, the judgment module 310 will synchronize the monitored water quality data directly to the interactive service unit 400. The interactive service unit 400 will display these water quality data to the user in an intuitive form through a mobile phone or PC application, such as presenting the real-time values of various water quality parameters, drawing water quality change trend charts, etc., so that users can grasp the normal water quality situation in a timely manner.

[0026] Once the real-time monitored water quality data is not within the regular threshold range constructed by the average value of the month in previous years, it means that the water quality may be abnormal. The judgment module 310 will transmit the monitoring data that exceeds the threshold to the analysis module 320.

[0027] The analysis module 320 can obtain real-time weather data. These data sources include authoritative forecast information from meteorological departments and measured data from surrounding meteorological monitoring stations, covering multiple key meteorological elements such as temperature, precipitation, wind speed, and humidity; After receiving real-time weather data, the analysis module 320 uses a dynamic structural equation model to perform calculations, which can comprehensively consider the complex relationships between multiple variables. In the water quality monitoring scenario, the model will incorporate variables in weather factors (such as precipitation intensity and frequency, temperature fluctuations, wind speed, and humidity changes, etc.) and pH values in water quality monitoring values into an analysis framework. Through mathematical operations and logical deductions, it is determined whether the current weather factors have an impact on the water quality monitoring values. For example, in heavy rain weather, the flushing of a large amount of rainwater may cause surface sediment, pollutants, etc. to enter the groundwater with runoff, thereby affecting the pH value of the water quality; or in continuous high temperature weather, microbial activity in the water body may intensify, causing changes in the dissolved oxygen content.

[0028] The above-mentioned method uses the dynamic structural equation model as the core tool to construct a multivariate correlation analysis framework, taking meteorological variables (precipitation, temperature, etc.) and water quality indicators (pH value) as endogenous and exogenous variables, and reveals causal relationships through path analysis, such as the transmission chain of heavy rain → surface runoff → pollutant migration → pH value fluctuation, which reflects the ability to mathematically model complex environmental mechanisms.

[0029] If the dynamic structural equation model determines that weather factors have an impact on water quality values, the analysis module 320 will mine the correlation between weather variables and water quality parameters under similar weather conditions based on a large amount of historical data, and then calculate the correlation between weather variables and water quality parameters according to the multivariate linear regression formula. , where Y is the dependent variable, and are independent variables, namely temperature and rainfall, is the intercept, which represents the value when both temperature and rainfall are 0. and are the regression coefficients of temperature and rainfall, is an error term. For example, by studying historical data on water quality changes after past rainstorms, it was found that when precipitation reaches a certain level, the concentration of a certain pollutant in the water quality will show a specific growth trend. Using these patterns, the analysis module 320 can generate an expected water quality baseline value under these weather conditions. We record this as the adaptive threshold. This adaptive threshold is not fixed but will be dynamically adjusted as the real-time weather conditions change, fully demonstrating its adaptability to complex and changing environments. On the basis of confirming the influence of weather, the numerical relationship between variables is quantified through multivariate linear regression (for example, for every 10mm increase in rainfall, the pH value is expected to change by ±0.2). The regression coefficients are trained using historical data to make the threshold generation process data-driven and objective. Real-time access to meteorological data triggers dynamic updates of the threshold, realizing a closed-loop response of "weather change-model calculation-threshold adjustment", breaking through the adaptability limitations of fixed thresholds to environmental dynamics.

[0030] Next, the analysis module 320 will conduct a detailed comparative analysis of the generated adaptive threshold value with the real-time water quality data reported by the edge computing module 102. If the real-time monitoring data is within a reasonable range of the adaptive threshold value, this means that the current water quality change is within the normal fluctuation range allowed by the weather conditions. At this time, the analysis module 320 will synchronize this data to the real-time monitoring dashboard of the interactive service unit 400. On the dashboard, users can intuitively see the real-time display of water quality data and understand that although the current water quality is affected by the weather, it is still normal. The real-time monitoring dashboard of the interactive service unit 400 will display a green prompt icon generated using SVG (Scalable Vector Graphics) dynamic rendering technology. SVG technology ensures that the icon can be displayed clearly and accurately on any device with any resolution, whether it is a mobile phone, tablet computer, or computer. The threshold comparison is used to achieve a binary judgment between "normal fluctuations under weather influence" and "abnormal changes". When synchronizing the results to the interactive layer, SVG dynamic rendering technology is used, leveraging the characteristics of vector graphics to ensure display consistency across multiple terminals. The visual encoding of the green icon conforms to the common warning rules in the field of human-computer interaction (green represents safe / normal), which improves the user's efficiency in quickly identifying information. However, if the real-time monitoring data exceeds the adaptive threshold, this indicates an abnormal change in water quality, possibly due to other interfering factors besides weather, such as industrial pollution emissions and agricultural non-point source pollution. In this case, the analysis module 320 generates a water quality anomaly warning signal using a dynamic threshold method. The interactive service unit 400 then uses SVG dynamic rendering technology to draw the user's attention with a striking red warning prompt. The color red itself has a strong visual warning effect. With SVG dynamic rendering technology, the red warning prompt can be presented in a gradient flashing, rotating, or other dynamic forms, further enhancing the warning effect. This ensures that users can quickly detect abnormal water quality signals regardless of the viewing environment, and promptly alerts relevant personnel to further evaluate and treat the water quality to ensure the purification of urban groundwater. When the data exceeds the adaptive threshold, the system automatically eliminates the possibility of weather factors as the main cause and attributes the anomaly to human factors such as potential pollution. It generates an alert using a dynamic threshold method (e.g., setting alarm boundaries based on historical abnormal data distribution). The dynamic rendering capabilities of SVG are also used to enhance the visual impact. This conforms to the principle of "abnormal states must be clearly distinguishable" in industrial design, achieving a full-process technical implementation from data anomaly detection to human-computer interactive warnings.

[0031] It should be noted that in the interactive service unit 400 of the system, when the pH value of water is transmitted to this unit within the regular threshold range, the display font color is consistent with the regular font. If the real-time monitoring data is within the reasonable range of the adaptive threshold, the data will be displayed in green to convey that the water quality is normal; if it exceeds the adaptive threshold range, the data will be presented in red to warn of abnormal water quality, thereby improving the user's perception and response efficiency of water quality conditions.

[0032] For example, in a city’s remote monitoring system for water purification equipment, on a certain day in July, the sensor of the water quality sensing module 101 captures the original analog signal of the pH value of water in the water purification equipment in real time, converts it into a digital signal through an analog-to-digital converter and transmits it to the edge computing module 102. The edge computing module 102 compensates for possible missing data, mines features such as pH value change trends, and generates a structured water quality data subset; the data routing unit 200 uses the LoRa technology and Modbus protocol to plan the optimal path using the AODV algorithm and quickly transmits the data to the intelligent central unit 300; the threshold calculation layer of the intelligent central unit 300 is based on the A regular threshold is constructed based on the average value of July in previous years. At this time, the judgment module 310 compares the real-time monitored water quality data with the regular threshold and finds that the pH value on that day is within the regular threshold range. The data is directly synchronized to the interactive service unit 400. However, a sudden rainstorm occurred in the afternoon of that day, and the deviation of the water quality pH value from the regular threshold was detected in real time. The analysis module 320 obtains real-time weather data, uses the dynamic structural equation model to determine the impact of weather on water quality, generates an adaptive threshold, and concludes that the real-time monitored pH value is within the adaptive threshold range. The real-time monitoring dashboard of the interactive service unit 400 is displayed with a green mark, informing the user that the water quality is normal, but there are normal fluctuations due to the heavy rain.

[0033] like Figure 3 As shown, the second purpose of this embodiment is to provide a method for a remote monitoring system of a smart water purification device, including the following method steps: Step 1: The sensing execution unit 100 obtains the pH value of the water quality, cleans and calibrates the abnormal values, and uploads the processed data to the intelligent central unit 300 through the data routing unit 200; Step 2: retrieve the data of the monitoring point in previous years and calculate the benchmark reference value; Step 3: Based on the rainfall and temperature fluctuation range in real-time meteorological station data, a dynamic adjustment model is established to automatically correct the reasonable fluctuation range threshold of the pH value; Step 4: Compare and analyze the real-time pH value of the water quality with the dynamically adjusted threshold. If the pH value exceeds the threshold range, the current meteorological data is combined to determine whether the anomaly is caused by natural factors. If natural factors are ruled out, the situation is marked as a potential pollution event. Step 5: Perform graded response according to the degree of abnormality, and highlight abnormal monitoring points in the interactive service unit 400.

[0034] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are merely preferred examples of the present invention and are not intended to limit the present invention. Various changes and improvements may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and improvements fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. The remote monitoring system of smart water purification equipment is characterized by: It includes a sensing execution unit (100), a data routing unit (200), an intelligent central unit (300) and an interactive service unit (400); Groundwater quality data is collected through the sensing execution unit (100), processed by the data routing unit (200), and the data is transmitted to the intelligent central unit (300). The intelligent central unit (300) is used to analyze the transmitted data and provide the analysis results to the user through the interactive service unit (400) through an intuitive interactive interface, wherein: The intelligent central unit (300) includes a data lake warehouse (301) and an analysis and decision module (302). The data lake warehouse (301) is used to store water quality data over the years. The data processed by the perception execution unit (100) enters the data lake warehouse (301) and is compared with the data of the corresponding time therein. The analysis and decision module (302) includes a judgment module (310) and an analysis module (320). The judgment module (310) performs a threshold analysis on the compared data. If the analysis value is within a normal range, it is directly transmitted to the interactive service unit (400) for result display. If the value exceeds the normal range, the compared data enters the analysis module (320), the weather factor is introduced for re-analysis and a new threshold is generated. After re-judgment, if the value returns to normal, it is marked green for transmission display; if it is still in the abnormal range, it is marked red and an early warning prompt is issued.

2. The remote monitoring system for smart water purification equipment according to claim 1, characterized in that: The sensing execution unit (100) is used to read the numerical value of water quality, and the sensing execution unit (100) comprises a water quality sensing module (101) and an edge computing module (102); The water quality sensing module (101) uses a water quality sensor to read the pH value of the groundwater in real time, and converts the collected original signal into a digital signal through an analog-to-digital converter; The edge computing module (102) is used to pre-process the digital signal, compensate for data loss, and perform feature extraction to generate a structured water quality data subset.

3. The remote monitoring system for smart water purification equipment according to claim 1, characterized in that: The data routing unit (200) transmits the water quality data collected and preliminarily processed by the sensing execution unit (100) to the intelligent central unit (300) through wireless communication technology according to a predetermined communication protocol and optimal path planning.

4. The remote monitoring system for smart water purification equipment according to claim 1, characterized in that: The data lake warehouse (301) is used to hierarchically store the water quality data collected by the sensing execution unit (100) over the years, including the following steps: Data storage layer: Archiving structured water quality data through a time series database and building data cubes for multi-dimensional analysis; Threshold calculation layer: Based on the sliding window algorithm, the dynamic mean and standard deviation of the water quality parameters of each monitoring point are calculated each month. After removing outliers using the box plot rule, an adaptive threshold interval with "monthly mean ± 2 times the standard deviation" as the boundary is generated, which is recorded as the regular threshold; Output layer: The final output regularity threshold will be synchronized to the rule engine of the analysis and decision module (302) as the basis for judging water quality anomalies, while retaining the threshold iteration interface for manual calibration.

5. The remote monitoring system for smart water purification equipment according to claim 2, characterized in that: The judgment module (310) is used to compare the real-time monitoring water quality data generated by the edge computing module (102) with the regularity threshold retrieved from the data lake (301). The judgment module (310) adopts a hierarchical judgment technology. If: 。 6. The remote monitoring system for smart water purification equipment according to claim 5, characterized in that: The analysis module (320) receives real-time weather data and determines whether the current weather factors have an impact on the water quality monitoring values through a dynamic structural equation model. If the weather factors affect the water quality values, the expected water quality baseline value under the weather conditions is generated through correlation analysis and recorded as an adaptive threshold. The adaptive threshold is compared and analyzed with the real-time monitoring water quality data reported by the edge computing module (102). If the real-time monitoring data is within the range of the adaptive threshold, the data is synchronized to the real-time monitoring dashboard of the interactive service unit (400). If the real-time monitoring data exceeds the range of the adaptive threshold, a water quality abnormality warning signal is generated through the dynamic threshold method formula.

7. The remote monitoring system for smart water purification equipment according to claim 6, characterized in that: When the real-time monitoring data is within the range of the adaptive threshold, the real-time monitoring dashboard of the interactive service unit (400) displays a green prompt mark, and when the real-time monitoring data is outside the range of the adaptive threshold, the abnormal water quality warning signal displays a red warning prompt, and the green prompt mark and the red warning prompt adopt SVG dynamic rendering technology.

8. A method for using a remote monitoring system comprising the smart water purification device according to any one of claims 1 to 7, characterized in that: The method comprises the following steps: S1, the sensing execution unit (100) obtains the pH value of water quality, cleans and calibrates abnormal values, and uploads the processed data to the intelligent central unit (300) through the data routing unit (200); S2. Retrieve the data of the same period in previous years for the monitoring point and calculate the benchmark reference value; S3. Based on the rainfall and temperature fluctuation range in real-time meteorological station data, a dynamic adjustment model is established to automatically correct the reasonable fluctuation range threshold of the pH value; S4. Compare and analyze the real-time pH value of the water quality with the dynamically adjusted threshold value. If the pH value exceeds the threshold range, combine it with the current meteorological data to determine whether the anomaly is caused by natural factors. If natural factors are ruled out, the situation is marked as a potential pollution event; S5. Perform graded responses according to the degree of abnormality, and highlight abnormal monitoring points in the interactive service unit (400).

Images