Smart city environment monitoring system based on Internet of Things

Abstract

The invention discloses a smart city environment monitoring system based on the Internet of Things, and relates to the technical field of the Internet of Things. When the system operates, the system can continuously acquire accurate hydrological data through fixed-period data acquisition of an intelligent water meter and a sensor, and the influence of noise and data missing is reduced through data cleaning and statistical analysis; and thus, reliable hydrological anomaly factors are generated. The water quality evaluation module further calculates a water quality evaluation index Ew, and performs quality judgment in combination with a water quality evaluation threshold value SZ to ensure that a water quality problem is found in time. And the water pollution risk calculation module calculates the influence degree of pollution diffusion according to the evaluation result, and quantifies the influence degree as a water pollution risk coefficient Rw to provide a basis for early warning decision. The early warning module generates an effective early warning strategy scheme and notifies related personnel through matching of an upper limit value Rmax and a lower limit value Rmin of water pipe network diffusion early warning, thereby ensuring that measures are taken in time before pollution diffusion, and avoiding event deterioration.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to a smart city environment monitoring system based on the Internet of Things. Background Art

[0002] Smart city refers to a modern urban development model that optimizes the management and real-time monitoring of urban resources through new-generation information technology, including the Internet of Things, big data, and artificial intelligence, aiming to improve urban operation efficiency and the quality of life of residents. The construction of smart cities covers multiple fields, such as smart transportation, smart energy, smart security, and smart environmental monitoring. Smart environmental monitoring is one of the key components of smart cities, mainly used to monitor the urban ecological environment, including air quality, water quality, and noise. In smart environmental monitoring, water quality monitoring, as an important sub-field, focuses on the water quality of water supply networks and natural water bodies.

[0003] Although the current pipe network water quality monitoring system can achieve water quality monitoring and data collection to a certain extent, it still has some shortcomings. First of all, traditional water quality monitoring systems often require the installation of additional water quality sensors or specialized equipment, which not only increases the cost of infrastructure construction, but may also bring technical difficulties in installation and maintenance. In addition, since the pipe network monitoring equipment often has limited points and the timeliness of monitoring is poor, when pollution occurs in some areas, the system fails to detect problems and issue warnings in time, which may lead to the spread of pollutants in the pipe network. The existing system's ability to analyze and warn of real-time data is also limited, making it difficult to identify water pollution incidents in a timely manner. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a smart city environment monitoring system based on the Internet of Things, which solves the problems mentioned in the background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a smart city environment monitoring system based on the Internet of Things, including a data acquisition module, a data analysis module, a water quality assessment module, a water pollution risk calculation module, an early warning module and a feedback and correction module;

[0006] The data acquisition module collects hydrological data D at a fixed period through the smart water meters installed in the urban water pipe network, and transmits the collected hydrological data D to the data analysis module for processing and analysis through the Internet of Things;

[0007] The data analysis module performs data cleaning preprocessing on the hydrological data D, including denoising preprocessing and missing value preprocessing, performs statistical analysis on the preprocessed hydrological data set Q, and obtains the hydrological anomaly factor vector Mp;

[0008] The water quality assessment module performs fitting calculation on the hydrological anomaly factor vector Mp to obtain a water quality assessment index Ew for the water quality, and matches it with a preset water quality assessment threshold SZ to obtain a water quality assessment result;

[0009] The water pollution risk calculation module triggers the water pipe network diffusion calculation according to the water quality assessment result to obtain the water pollution risk coefficient Rw;

[0010] The early warning module matches the preset upper limit value Rmax and lower limit value Rmin of the water pipe network diffusion early warning with the water pollution risk coefficient Rw, obtains the water pollution diffusion early warning assessment strategy plan, and notifies relevant personnel to handle and verify;

[0011] The feedback and correction module collects and records the execution of the water pollution diffusion warning assessment strategy program content, evaluates the deviation of the hydrological anomaly factor vector Mp, the water quality assessment index Ew and the water pollution risk coefficient Rw, and adaptively adjusts the upper limit Rmax and lower limit Rmin of the water pipe network diffusion warning.

[0012] Preferably, the data acquisition module includes a smart water meter acquisition unit, a water quality sensor unit and a data transmission unit;

[0013] The smart water meter collection unit records the water flow F, water pressure P and water temperature Tw at a fixed period through the smart water meters installed in the urban water pipe network;

[0014] The water quality sensor unit collects data synchronously and periodically by integrating a water quality sensor at the installed smart water meter, including pH value pH, turbidity Tz and conductivity Ce, and integrates the data with water flow F, water pressure P and water temperature Tw to form hydrological data D = {pH, Tz, Ce, F, P, Tw};

[0015] The data transmission unit adopts the Internet of Things technology and uses a wireless network to establish a communication channel to transmit the collected hydrological data D in real time to the data analysis module for processing and analysis.

[0016] Preferably, the data analysis module includes a data cleaning unit and a statistical analysis unit;

[0017] The data cleaning unit performs data cleaning preprocessing on the hydrological data D, including denoising preprocessing and missing value preprocessing, specifically, denoising preprocessing on pH value pH, turbidity Tz, conductivity Ce, water flow F, water pressure P and water temperature Tw by using moving average filtering; filling missing values ​​of pH value pH, turbidity Tz, conductivity Ce, water flow F, water pressure P and water temperature Tw by using linear interpolation; obtaining a hydrological data set Q={pHc, Tzc, Cec, Fc, Pc, Twc} after denoising preprocessing and missing value preprocessing, wherein pHc represents the pH value pH after processing, Tzc represents the turbidity Tz after processing, Cec represents the conductivity Ce after processing, Fc represents the water flow F after processing, Pc represents the water pressure P after processing, and Twc represents the water temperature Twc after processing;

[0018] The statistical analysis unit calculates the preprocessed hydrological data set Q to obtain the matrix mean μ and the matrix standard deviation σ of each parameter in the hydrological data set Q, and then performs statistical analysis to obtain the fluctuation information of the hydrological data set Q to form a hydrological anomaly factor vector Mp={pHbd, Tzbd, Cebd, Fbd, Pbd, Twbd}, where pHbd represents the pH value fluctuation value, Tzbd represents the turbidity fluctuation value, Cebd represents the conductivity fluctuation value, Fbd represents the water flow fluctuation value, Pbd represents the water pressure fluctuation value, and Twbd represents the water temperature fluctuation value.

[0019] Preferably, the matrix mean μ is obtained by the following calculation formula:

[0020]

[0021] Where n represents the total number of data in the hydrological dataset Q, specifically the length of the hydrological dataset Q, i represents the i-th parameter in the hydrological dataset Q, m represents the total number of samples of the hydrological dataset Q collected within a fixed period, j represents the hydrological dataset Q of the j-th sample, and Q,i,j represents the i-th parameter in the hydrological dataset Q of the j-th sample;

[0022] The matrix standard deviation σ is obtained by the following calculation formula:

[0023]

[0024] In the formula, Q,i represents the i-th parameter in the hydrological dataset Q;

[0025] The hydrological anomaly factor vector Mp is Obtain the calculation formula.

[0026] Preferably, the water quality assessment module includes a water quality calculation unit and a water quality matching unit;

[0027] The water quality calculation unit obtains a water quality assessment index Ew for water quality by fitting the hydrological anomaly factor vector Mp, including fitting the pH value fluctuation value pHbd, the turbidity fluctuation value Tzbd and the conductivity fluctuation value Cebd in the hydrological anomaly factor vector Mp;

[0028] The water quality matching unit obtains a water quality assessment result by matching the water quality assessment index Ew with a preset water quality assessment threshold SZ.

[0029] Preferably, the water quality evaluation index Ew is obtained by the following calculation formula:

[0030]

[0031] In the formula, α, β and γ represent fitting coefficients, which are specifically used to adjust the influence of pH fluctuation value pHbd, turbidity fluctuation value Tzbd and conductivity fluctuation value Cebd on water quality assessment index Ew; ε represents a positive constant, which is specifically used to avoid calculation errors caused by the denominator being zero;

[0032] The water quality assessment results are obtained through the following matching methods:

[0033] When the water quality assessment index Ew is less than the water quality assessment threshold SZ, the water quality assessment result is a qualified result;

[0034] When the water quality assessment index Ew ≥ the water quality assessment threshold SZ, the water quality assessment result is an unqualified result;

[0035] When the water quality assessment index Ew ≥ twice the water quality assessment threshold SZ, the water quality assessment result obtained is an abnormal warning result.

[0036] Preferably, the water pollution risk calculation module triggers the influence degree of water pipe network diffusion calculation according to the water quality assessment result, specifically, the influence degree of water pipe network diffusion calculation triggered when the water quality assessment result is an unqualified result and an abnormal warning result, and obtains the water pollution risk coefficient Rw;

[0037] The water pollution risk coefficient Rw is obtained by the following calculation formula:

[0038]

[0039] Wherein, log represents logarithmic function, sin represents sine function, and logarithmic function log and sine function sin are specifically used to deal with nonlinear situations of wave effects.

[0040] Preferably, the early warning module includes a risk matching unit and a response generating unit;

[0041] The risk matching unit matches the water pollution risk coefficient Rw with the preset upper limit value Rmax and lower limit value Rmin of the water pipe network diffusion warning to obtain a matching result signal L;

[0042] The matching result signal L is Matching method acquisition;

[0043] When the water pollution risk coefficient Rw is less than the lower limit Rmin, the matching result signal L=1;

[0044] When the lower limit value Rmin≤water pollution risk coefficient Rw≤upper limit value Rmax, the matching result signal L=2;

[0045] When the upper limit value Rmax<water pollution risk coefficient Rw, the matching result signal L=3.

[0046] Preferably, the response generation unit generates a water pollution diffusion early warning assessment strategy plan according to the matching result signal L, and notifies relevant personnel to handle and verify;

[0047] The water pollution diffusion early warning assessment strategy is obtained by the following generation method:

[0048] When the matching result signal L=1, a strategy scheme for continuing monitoring without processing the evaluation is generated;

[0049] When the matching result signal L=2, a task of continuing monitoring and inspection and maintenance is generated, and the inspection and maintenance task is simultaneously sent to the inspection personnel's pending task list to wait for disposal and verification;

[0050] When the matching result signal L=3, a continued monitoring and warning task is generated, and the warning task is simultaneously sent to the patrol personnel's pending task list, and is pinned and flashed for processing and verification, and a text message, email, and preset notification voice are sent to inform the relevant patrol personnel.

[0051] Preferably, the feedback and correction module includes a feedback recording unit and a correction execution unit;

[0052] The feedback recording unit records the execution of the water pollution diffusion early warning assessment strategy program content by collecting the inspection and maintenance personnel's processing flow, including the execution personnel's response time, operation record, processing type and water pollution diffusion early warning assessment strategy program matching degree FD;

[0053] The matching degree FD of the water pollution diffusion early warning assessment strategy is obtained by the following calculation formula:

[0054]

[0055] In the formula, Rwact represents the water pollution risk coefficient Rw obtained by on-site actual measurement by inspection and maintenance personnel;

[0056] The correction execution unit evaluates the deviation of the hydrological anomaly factor vector Mp, the water quality assessment index Ew and the water pollution risk coefficient Rw, and adaptively adjusts the upper limit Rmax and the lower limit Rmin of the water network diffusion warning, including proportionally regulating the upper limit Rmax and the lower limit Rmin of the water network diffusion warning according to the matching degree FD of the water pollution diffusion warning assessment strategy scheme.

[0057] The present invention provides a smart city environment monitoring system based on the Internet of Things, which has the following beneficial effects:

[0058] (1) When the system is running, through the fixed-period data collection of smart water meters and sensors, the system can continuously obtain accurate hydrological data, and reduce the impact of noise and data loss through data cleaning and statistical analysis, thereby generating reliable hydrological anomaly factors. The water quality assessment module further calculates the water quality assessment index Ew, and combines the water quality assessment threshold SZ to make quality judgments to ensure timely detection of water quality problems. The water pollution risk calculation module calculates the impact of pollution diffusion based on the assessment results and quantifies it as the water pollution risk coefficient Rw, providing a basis for early warning decisions. The early warning module matches the upper limit Rmax and lower limit Rmin of the water pipe network diffusion warning, generates an effective early warning strategy plan and notifies relevant personnel, thereby ensuring that timely measures are taken before the pollution spreads to avoid the deterioration of the situation. At the same time, the feedback and correction module further optimizes the sensitivity and response speed of the system by evaluating the execution of the early warning strategy and the actual deviation.

[0059] (2) Through the design of the water quality assessment module, the accuracy of refined assessment of water quality and pollution warning is improved. The water quality calculation unit combines the pH value fluctuation value pHbd, turbidity fluctuation value Tzbd and conductivity fluctuation value Cebd in the hydrological anomaly factor vector Mp for fitting calculation to generate the water quality assessment index Ew, which can more comprehensively reflect the comprehensive status of water quality. Compared with the traditional water quality assessment method, it can flexibly adjust the influence of each fluctuation parameter on the assessment result, optimize the weight of different water quality factors through the fitting coefficient, and avoid misjudgment due to abnormal fluctuation of a single parameter. The water quality matching unit matches the assessment index Ew with the water quality assessment threshold SZ, which can not only accurately distinguish the qualified, unqualified and abnormal warning status of water quality, but also provide an important basis for the subsequent calculation and warning of water pollution diffusion.

[0060] (3) The risk matching unit matches the water pollution risk coefficient Rw with the preset upper limit Rmax and lower limit Rmin of the water pipe network diffusion warning, and generates a matching result signal L to ensure that risks of different degrees can be accurately identified and handled. According to the matching result signal L, the response generation unit can automatically generate the corresponding warning evaluation strategy, from simple continued monitoring to higher-level inspection maintenance and warning tasks, to achieve flexible response of the warning plan. Especially in high-risk situations, the system can not only send flashing and top notifications to the inspection personnel, but also inform them in real time through multiple channels to ensure that urgent problems are handled in a timely manner. Through the feedback and correction module, the system can record and evaluate the task response in real time based on the execution feedback of the inspection personnel, and calculate the matching degree FD of the warning evaluation strategy. According to the matching result, the system can proportionally adjust the upper limit Rmax and lower limit Rmin of the warning to optimize its sensitivity so that it can better adapt to the actual water quality conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 The present invention is a block diagram of a smart city environment monitoring system based on the Internet of Things. DETAILED DESCRIPTION

[0062] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0063] Example 1

[0064] The present invention provides a smart city environment monitoring system based on the Internet of Things. Figure 1 , including data acquisition module, data analysis module, water quality assessment module, water pollution risk calculation module, early warning module and feedback and correction module;

[0065] The data acquisition module collects hydrological data D at a fixed period through the smart water meters installed in the urban water pipe network, and transmits the collected hydrological data D to the data analysis module for processing and analysis through the Internet of Things;

[0066] The data analysis module performs data cleaning preprocessing on the hydrological data D, including denoising preprocessing and missing value preprocessing, performs statistical analysis on the preprocessed hydrological data set Q, and obtains the hydrological anomaly factor vector Mp;

[0067] The water quality assessment module performs fitting calculation on the hydrological anomaly factor vector Mp to obtain a water quality assessment index Ew for the water quality, and matches it with a preset water quality assessment threshold SZ to obtain a water quality assessment result;

[0068] The water pollution risk calculation module triggers the water pipe network diffusion calculation according to the water quality assessment result to obtain the water pollution risk coefficient Rw;

[0069] The early warning module matches the preset upper limit value Rmax and lower limit value Rmin of the water pipe network diffusion early warning with the water pollution risk coefficient Rw, obtains the water pollution diffusion early warning assessment strategy plan, and notifies relevant personnel to handle and verify;

[0070] The feedback and correction module collects and records the execution of the water pollution diffusion warning assessment strategy program content, evaluates the deviation of the hydrological anomaly factor vector Mp, the water quality assessment index Ew and the water pollution risk coefficient Rw, and adaptively adjusts the upper limit Rmax and lower limit Rmin of the water pipe network diffusion warning.

[0071] In this embodiment, through the collaboration of the data acquisition module, the data analysis module, the water quality assessment module, the water pollution risk calculation module, the early warning module and the feedback and correction module, a complete closed-loop process is formed from data acquisition to early warning and feedback, which can effectively overcome the problems of poor timeliness, limited monitoring points and untimely early warning response in traditional water quality monitoring. Through the fixed-period data acquisition of smart water meters and sensors, the system can continuously obtain accurate hydrological data, and reduce the influence of noise and data loss through data cleaning and statistical analysis, thereby generating reliable hydrological anomaly factors. The water quality assessment module further calculates the water quality assessment index Ew, and combines the water quality assessment threshold SZ for quality judgment to ensure timely discovery of water quality problems. The water pollution risk calculation module calculates the impact of pollution diffusion based on the assessment results, quantifies it into the water pollution risk coefficient Rw, and provides a basis for early warning decision-making. The early warning module matches the upper limit Rmax and lower limit Rmin of the water pipe network diffusion early warning, generates an effective early warning strategy and notifies relevant personnel, thereby ensuring that timely measures are taken before the pollution spreads to avoid the deterioration of the situation. At the same time, the feedback and correction module further optimizes the system's sensitivity and response speed by evaluating the implementation of the early warning strategy and the actual deviation. It improves the accuracy and efficiency of water quality monitoring, and effectively shortens the time from discovering water quality problems to taking action, making up for the limitations of traditional water quality monitoring systems and greatly improving the city's water quality management capabilities.

[0072] Example 2

[0073] This embodiment is explained in Example 1, please refer to Figure 1,Specifically: the data acquisition module includes a smart water meter acquisition unit, a water quality sensor unit and a data transmission unit;

[0074] The smart water meter collection unit records the water flow F, water pressure P and water temperature Tw at a fixed period through the smart water meters installed in the urban water pipe network;

[0075] The water quality sensor unit collects data synchronously and periodically by integrating a water quality sensor at the installed smart water meter, including pH value pH, turbidity Tz and conductivity Ce, and integrates the data with water flow F, water pressure P and water temperature Tw to form hydrological data D = {pH, Tz, Ce, F, P, Tw};

[0076] The data transmission unit adopts the Internet of Things technology and uses a wireless network to establish a communication channel to transmit the collected hydrological data D in real time to the data analysis module for processing and analysis.

[0077] The data analysis module includes a data cleaning unit and a statistical analysis unit;

[0078] The data cleaning unit performs data cleaning preprocessing on the hydrological data D, including denoising preprocessing and missing value preprocessing, specifically, denoising preprocessing on pH value pH, turbidity Tz, conductivity Ce, water flow F, water pressure P and water temperature Tw by using moving average filtering; filling missing values ​​of pH value pH, turbidity Tz, conductivity Ce, water flow F, water pressure P and water temperature Tw by using linear interpolation; obtaining a hydrological data set Q={pHc, Tzc, Cec, Fc, Pc, Twc} after denoising preprocessing and missing value preprocessing, wherein pHc represents the pH value pH after processing, Tzc represents the turbidity Tz after processing, Cec represents the conductivity Ce after processing, Fc represents the water flow F after processing, Pc represents the water pressure P after processing, and Twc represents the water temperature Twc after processing;

[0079] The statistical analysis unit calculates the preprocessed hydrological data set Q to obtain the matrix mean μ and the matrix standard deviation σ of each parameter in the hydrological data set Q, and then performs statistical analysis to obtain the fluctuation information of the hydrological data set Q to form a hydrological anomaly factor vector Mp={pHbd, Tzbd, Cebd, Fbd, Pbd, Twbd}, where pHbd represents the pH value fluctuation value, Tzbd represents the turbidity fluctuation value, Cebd represents the conductivity fluctuation value, Fbd represents the water flow fluctuation value, Pbd represents the water pressure fluctuation value, and Twbd represents the water temperature fluctuation value.

[0080] The matrix mean μ is obtained by the following calculation formula:

[0081]

[0082] Where n represents the total number of data in the hydrological dataset Q, specifically the length of the hydrological dataset Q, i represents the i-th parameter in the hydrological dataset Q, m represents the total number of samples of the hydrological dataset Q collected within a fixed period, j represents the hydrological dataset Q of the j-th sample, and Q,i,j represents the i-th parameter in the hydrological dataset Q of the j-th sample;

[0083] The matrix standard deviation σ is obtained by the following calculation formula:

[0084]

[0085] In the formula, Q,i represents the i-th parameter in the hydrological dataset Q;

[0086] The hydrological anomaly factor vector Mp is Obtain the calculation formula.

[0087] In this embodiment, the accuracy of water quality monitoring and the integrity of data processing are greatly improved through a multi-level data collection and analysis mechanism. First, the data acquisition module regularly collects and integrates pH value pH, turbidity Tz, conductivity Ce, water flow F, water pressure P and water temperature Tw through smart water meters and water quality sensors to form a hydrological data set D, and transmits it in real time through the Internet of Things technology. This integrated collection not only reduces the installation and maintenance costs of the equipment, but also improves the efficiency of data synchronization. Secondly, the data cleaning unit in the data analysis module performs denoising and missing value filling processing on the data to ensure the reliability and integrity of the data. Through moving average filtering and linear interpolation, the system effectively eliminates the impact of abnormal data and data missing, and obtains a high-quality hydrological data set Q. Subsequently, the statistical analysis unit conducts a deep analysis of water quality fluctuations based on the data matrix mean μ and the matrix standard deviation σ, and generates a hydrological anomaly factor vector Mp, so that abnormal water quality changes in the pipe network can be accurately captured. This multiple mechanism of data processing and analysis ensures that the system can not only detect small water quality fluctuations, but also identify potential pollution risks more quickly, greatly improving the sensitivity and response capabilities of monitoring. Compared with traditional monitoring systems, this system can achieve more intelligent and refined water quality management by processing complex multi-dimensional data.

[0088] Example 3

[0089] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the water quality assessment module includes a water quality calculation unit and a water quality matching unit;

[0090] The water quality calculation unit obtains a water quality assessment index Ew for water quality by fitting the hydrological anomaly factor vector Mp, including fitting the pH value fluctuation value pHbd, the turbidity fluctuation value Tzbd and the conductivity fluctuation value Cebd in the hydrological anomaly factor vector Mp;

[0091] The water quality matching unit obtains a water quality assessment result by matching the water quality assessment index Ew with a preset water quality assessment threshold SZ.

[0092] The water quality evaluation index Ew is obtained by the following calculation formula:

[0093]

[0094] In the formula, α, β and γ represent fitting coefficients, which are specifically used to adjust the influence of pH fluctuation value pHbd, turbidity fluctuation value Tzbd and conductivity fluctuation value Cebd on water quality assessment index Ew; ε represents a positive constant, which is specifically used to avoid calculation errors caused by the denominator being zero;

[0095] The water quality assessment results are obtained through the following matching methods:

[0096] When the water quality assessment index Ew is less than the water quality assessment threshold SZ, the water quality assessment result is a qualified result;

[0097] When the water quality assessment index Ew ≥ the water quality assessment threshold SZ, the water quality assessment result is an unqualified result;

[0098] When the water quality assessment index Ew ≥ twice the water quality assessment threshold SZ, the water quality assessment result obtained is an abnormal warning result.

[0099] The water pollution risk calculation module triggers the water pipe network diffusion calculation according to the water quality assessment result, specifically, the influence degree of triggering the water pipe network diffusion calculation when the water quality assessment result is an unqualified result and an abnormal warning result, and obtains the water pollution risk coefficient Rw;

[0100] The water pollution risk coefficient Rw is obtained by the following calculation formula:

[0101]

[0102] Wherein, log represents logarithmic function, sin represents sine function, and logarithmic function log and sine function sin are specifically used to deal with nonlinear situations of wave effects.

[0103] In this embodiment, the design of the water quality assessment module improves the accuracy of the refined assessment of water quality and pollution warning. The water quality calculation unit combines the pH value fluctuation value pHbd, the turbidity fluctuation value Tzbd and the conductivity fluctuation value Cebd in the hydrological anomaly factor vector Mp for fitting calculation to generate the water quality assessment index Ew, so as to more comprehensively reflect the comprehensive state of water quality. Compared with the traditional water quality assessment method, it can flexibly adjust the influence of each fluctuation parameter on the assessment result, optimize the weights of different water quality factors through the fitting coefficient, and avoid misjudgment caused by abnormal fluctuations of a single parameter. The water quality matching unit matches the assessment index Ew with the water quality assessment threshold SZ, which can not only accurately distinguish the qualified, unqualified and abnormal warning states of water quality, but also provide an important basis for the calculation and warning of subsequent water pollution diffusion. By introducing nonlinear functions into the water pollution risk calculation module, the system effectively captures the complex effects of water parameter fluctuations, making the risk assessment of pollution diffusion more accurate and sensitive. This multi-level assessment and matching mechanism enables the system to quickly identify potential water quality problems, trigger risk warnings in a timely manner, and take corresponding prevention and control measures, effectively improving the safety and stability of the urban water supply network.

[0104] Example 4

[0105] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the early warning module includes a risk matching unit and a response generating unit;

[0106] The risk matching unit matches the water pollution risk coefficient Rw with the preset upper limit value Rmax and lower limit value Rmin of the water pipe network diffusion warning to obtain a matching result signal L;

[0107] The matching result signal L is Matching method acquisition;

[0108] When the water pollution risk coefficient Rw is less than the lower limit Rmin, the matching result signal L=1;

[0109] When the lower limit value Rmin≤water pollution risk coefficient Rw≤upper limit value Rmax, the matching result signal L=2;

[0110] When the upper limit value Rmax<water pollution risk coefficient Rw, the matching result signal L=3.

[0111] The response generation unit generates a water pollution diffusion early warning assessment strategy plan according to the matching result signal L, and notifies relevant personnel to handle and verify;

[0112] The water pollution diffusion early warning assessment strategy is obtained by the following generation method:

[0113] When the matching result signal L=1, a strategy scheme for continuing monitoring without processing the evaluation is generated;

[0114] When the matching result signal L=2, a task of continuing monitoring and inspection and maintenance is generated, and the inspection and maintenance task is simultaneously sent to the inspection personnel's pending task list to wait for disposal and verification;

[0115] When the matching result signal L=3, a continued monitoring and warning task is generated, and the warning task is simultaneously sent to the patrol personnel's pending task list, and is pinned and flashed for processing and verification, and a text message, email, and preset notification voice are sent to inform the relevant patrol personnel.

[0116] The feedback and correction module includes a feedback recording unit and a correction execution unit;

[0117] The feedback recording unit records the execution of the water pollution diffusion early warning assessment strategy program content by collecting the inspection and maintenance personnel's processing flow, including the execution personnel's response time, operation record, processing type and water pollution diffusion early warning assessment strategy program matching degree FD;

[0118] The matching degree FD of the water pollution diffusion early warning assessment strategy is obtained by the following calculation formula:

[0119]

[0120] In the formula, Rwact represents the water pollution risk coefficient Rw obtained by on-site actual measurement by inspection and maintenance personnel;

[0121] The correction execution unit evaluates the deviation of the hydrological anomaly factor vector Mp, the water quality assessment index Ew and the water pollution risk coefficient Rw, and adaptively adjusts the upper limit Rmax and the lower limit Rmin of the water network diffusion warning, including proportionally regulating the upper limit Rmax and the lower limit Rmin of the water network diffusion warning according to the matching degree FD of the water pollution diffusion warning assessment strategy scheme.

[0122] In this embodiment, the risk matching unit matches the water pollution risk coefficient Rw with the preset upper limit Rmax and lower limit Rmin of the water pipe network diffusion warning, and generates a matching result signal L to ensure that risks of different degrees can be accurately identified and processed. According to the matching result signal L, the response generation unit can automatically generate the corresponding early warning assessment strategy, from simple continued monitoring to higher-level inspection maintenance and early warning tasks, to achieve flexible response of the early warning scheme. Especially in high-risk situations, the system can not only send flashing and top notifications to the inspection personnel, but also inform them in real time through multiple channels to ensure that emergency problems are handled in a timely manner. Through the feedback and correction module, the system can record and evaluate the task response in real time based on the execution feedback of the inspection personnel, and calculate the matching degree FD of the early warning assessment strategy. According to the matching result, the system can proportionally adjust the upper limit Rmax and lower limit Rmin of the early warning, optimize its sensitivity, and make it better adapt to the actual water quality conditions. This closed-loop mechanism of feedback and adjustment not only enhances the dynamic adaptability of the system, but also ensures that water pollution problems can be handled quickly and accurately, further improving the emergency response level of urban water quality management.

[0123] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A smart city environment monitoring system based on the Internet of Things, characterized by: It includes data collection module, data analysis module, water quality assessment module, water pollution risk calculation module, early warning module and feedback and correction module; The data acquisition module collects hydrological data D at a fixed period through the smart water meters installed in the urban water pipe network, and transmits the collected hydrological data D to the data analysis module for processing and analysis through the Internet of Things; The data analysis module performs data cleaning preprocessing on the hydrological data D, including denoising preprocessing and missing value preprocessing, performs statistical analysis on the preprocessed hydrological data set Q, and obtains the hydrological anomaly factor vector Mp; The water quality assessment module performs fitting calculation on the hydrological anomaly factor vector Mp to obtain a water quality assessment index Ew for the water quality, and matches it with a preset water quality assessment threshold SZ to obtain a water quality assessment result; The water pollution risk calculation module triggers the water pipe network diffusion calculation according to the water quality assessment result to obtain the water pollution risk coefficient Rw; The early warning module matches the preset upper limit value Rmax and lower limit value Rmin of the water pipe network diffusion early warning with the water pollution risk coefficient Rw, obtains the water pollution diffusion early warning assessment strategy plan, and notifies relevant personnel to handle and verify; The feedback and correction module collects and records the execution of the water pollution diffusion warning assessment strategy program content, evaluates the deviation of the hydrological anomaly factor vector Mp, the water quality assessment index Ew and the water pollution risk coefficient Rw, and adaptively adjusts the upper limit Rmax and lower limit Rmin of the water pipe network diffusion warning.

2. The smart city environment monitoring system based on the Internet of Things according to claim 1 is characterized in that: The data acquisition module includes a smart water meter acquisition unit, a water quality sensor unit and a data transmission unit; The smart water meter collection unit records the water flow F, water pressure P and water temperature Tw at a fixed period through the smart water meters installed in the urban water pipe network; The water quality sensor unit collects data synchronously and periodically by integrating a water quality sensor at the installed smart water meter, including pH value pH, turbidity Tz and conductivity Ce, and integrates the data with water flow F, water pressure P and water temperature Tw to form hydrological data D = {pH, Tz, Ce, F, P, Tw}; The data transmission unit adopts the Internet of Things technology and uses a wireless network to establish a communication channel to transmit the collected hydrological data D in real time to the data analysis module for processing and analysis.

3. The smart city environment monitoring system based on the Internet of Things according to claim 2 is characterized in that: The data analysis module includes a data cleaning unit and a statistical analysis unit; The data cleaning unit performs data cleaning preprocessing on the hydrological data D, including denoising preprocessing and missing value preprocessing, specifically, denoising preprocessing on pH value pH, turbidity Tz, conductivity Ce, water flow F, water pressure P and water temperature Tw by using moving average filtering; filling missing values ​​of pH value pH, turbidity Tz, conductivity Ce, water flow F, water pressure P and water temperature Tw by using linear interpolation; obtaining a hydrological data set Q={pHc, Tzc, Cec, Fc, Pc, Twc} after denoising preprocessing and missing value preprocessing, wherein pHc represents the pH value pH after processing, Tzc represents the turbidity Tz after processing, Cec represents the conductivity Ce after processing, Fc represents the water flow F after processing, Pc represents the water pressure P after processing, and Twc represents the water temperature Twc after processing; The statistical analysis unit calculates the preprocessed hydrological data set Q to obtain the matrix mean μ and the matrix standard deviation σ of each parameter in the hydrological data set Q, and then performs statistical analysis to obtain the fluctuation information of the hydrological data set Q to form a hydrological anomaly factor vector Mp={pHbd, Tzbd, Cebd, Fbd, Pbd, Twbd}, where pHbd represents the pH value fluctuation value, Tzbd represents the turbidity fluctuation value, Cebd represents the conductivity fluctuation value, Fbd represents the water flow fluctuation value, Pbd represents the water pressure fluctuation value, and Twbd represents the water temperature fluctuation value.

4. The smart city environment monitoring system based on the Internet of Things according to claim 3 is characterized in that: The matrix mean μ is obtained by the following calculation formula: Where n represents the total number of data in the hydrological dataset Q, specifically the length of the hydrological dataset Q, i represents the i-th parameter in the hydrological dataset Q, m represents the total number of samples of the hydrological dataset Q collected within a fixed period, j represents the hydrological dataset Q of the j-th sample, and Q,i,j represents the i-th parameter in the hydrological dataset Q of the j-th sample; The matrix standard deviation σ is obtained by the following calculation formula: In the formula, Q,i represents the i-th parameter in the hydrological dataset Q; The hydrological anomaly factor vector Mp is Obtain the calculation formula.

5. The smart city environment monitoring system based on the Internet of Things according to claim 4 is characterized in that: The water quality assessment module includes a water quality calculation unit and a water quality matching unit; The water quality calculation unit obtains a water quality assessment index Ew for water quality by fitting the hydrological anomaly factor vector Mp, including fitting the pH value fluctuation value pHbd, the turbidity fluctuation value Tzbd and the conductivity fluctuation value Cebd in the hydrological anomaly factor vector Mp; The water quality matching unit obtains a water quality assessment result by matching the water quality assessment index Ew with a preset water quality assessment threshold SZ.

6. The smart city environment monitoring system based on the Internet of Things according to claim 5 is characterized in that: The water quality evaluation index Ew is obtained by the following calculation formula: In the formula, α, β and γ represent fitting coefficients, which are specifically used to adjust the influence of pH fluctuation value pHbd, turbidity fluctuation value Tzbd and conductivity fluctuation value Cebd on water quality assessment index Ew; ε represents a positive constant, which is specifically used to avoid calculation errors caused by the denominator being zero; The water quality assessment results are obtained through the following matching methods: When the water quality assessment index Ew is less than the water quality assessment threshold SZ, the water quality assessment result is a qualified result; When the water quality assessment index Ew ≥ the water quality assessment threshold SZ, the water quality assessment result is an unqualified result; When the water quality assessment index Ew ≥ twice the water quality assessment threshold SZ, the water quality assessment result obtained is an abnormal warning result.

7. The smart city environment monitoring system based on the Internet of Things according to claim 6 is characterized in that: The water pollution risk calculation module triggers the water pipe network diffusion calculation according to the water quality assessment result, specifically, the influence degree of triggering the water pipe network diffusion calculation when the water quality assessment result is an unqualified result and an abnormal warning result, and obtains the water pollution risk coefficient Rw; The water pollution risk coefficient Rw is obtained by the following calculation formula: Wherein, log represents logarithmic function, sin represents sine function, and logarithmic function log and sine function sin are specifically used to deal with nonlinear situations of wave effects.

8. The smart city environment monitoring system based on the Internet of Things according to claim 7 is characterized in that: The early warning module includes a risk matching unit and a response generation unit; The risk matching unit matches the water pollution risk coefficient Rw with the preset upper limit value Rmax and lower limit value Rmin of the water pipe network diffusion warning to obtain a matching result signal L; The matching result signal L is Matching method acquisition; When the water pollution risk coefficient Rw is less than the lower limit Rmin, the matching result signal L=1; When the lower limit value Rmin≤water pollution risk coefficient Rw≤upper limit value Rmax, the matching result signal L=2; When the upper limit value Rmax<water pollution risk coefficient Rw, the matching result signal L=3.

9. The smart city environment monitoring system based on the Internet of Things according to claim 8 is characterized in that: The response generation unit generates a water pollution diffusion early warning assessment strategy plan according to the matching result signal L, and notifies relevant personnel to handle and verify; The water pollution diffusion early warning assessment strategy is obtained by the following generation method: When the matching result signal L=1, a strategy scheme for continuing monitoring without processing the evaluation is generated; When the matching result signal L=2, a task of continuing monitoring and inspection and maintenance is generated, and the inspection and maintenance task is simultaneously sent to the inspection personnel's pending task list to wait for disposal and verification; When the matching result signal L=3, a continued monitoring and warning task is generated, and the warning task is simultaneously sent to the patrol personnel's pending task list, and is pinned and flashed for processing and verification, and a text message, email, and preset notification voice are sent to inform the relevant patrol personnel.

10. The smart city environment monitoring system based on the Internet of Things according to claim 9, characterized in that: The feedback and correction module includes a feedback recording unit and a correction execution unit; The feedback recording unit records the execution of the water pollution diffusion early warning assessment strategy program content by collecting the inspection and maintenance personnel's processing flow, including the execution personnel's response time, operation record, processing type and water pollution diffusion early warning assessment strategy program matching degree FD; The matching degree FD of the water pollution diffusion early warning assessment strategy is obtained by the following calculation formula: In the formula, Rwact represents the water pollution risk coefficient Rw obtained by on-site actual measurement by inspection and maintenance personnel; The correction execution unit evaluates the deviation of the hydrological anomaly factor vector Mp, the water quality assessment index Ew and the water pollution risk coefficient Rw, and adaptively adjusts the upper limit Rmax and the lower limit Rmin of the water network diffusion warning, including proportionally regulating the upper limit Rmax and the lower limit Rmin of the water network diffusion warning according to the matching degree FD of the water pollution diffusion warning assessment strategy scheme.

Images