Environmental monitoring pollution early warning system based on artificial intelligence

Abstract

The invention discloses an environmental monitoring pollution early warning system based on artificial intelligence. The system comprises a data acquisition module, a data preprocessing module, an environmental monitoring pollution evaluation model establishment module and an environmental monitoring pollution early warning module. The invention belongs to the field of data processing, and particularly relates to an environmental monitoring pollution early warning system based on artificial intelligence, which captures changeable and complex environmental monitoring pollution changes by introducing a rapid change long-term trend and dynamic disturbance compensation; pollutant interaction strength is introduced to construct a gain design unit, and the accuracy of environmental monitoring pollution early warning is improved; a dynamic adjustment fuzzy basis function mechanism is introduced, the pollutant concentration range is dynamically adjusted, and the overall monitoring and early warning efficiency is improved based on multi-stage recursive control; a nonlinear dynamic surface controller filter is used for smoothing a control signal, and interference of monitoring noise on the system is reduced; pollution assessment is carried out based on the dynamic gain design and the time upper bound; and thus, the environmental monitoring pollution early warning effect is improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to an artificial intelligence-based environmental monitoring pollution early warning system. Background Art

[0002] The environmental monitoring pollution early warning system is an integrated system based on environmental monitoring data analysis and dynamic control technology. Its main goal is to effectively monitor, evaluate and predict environmental pollution through real-time collection, processing and analysis of environmental data, timely detect abnormal conditions, and issue early warning signals, thereby helping decision makers take appropriate pollution control and emergency management measures to reduce the harm of pollution to human health and the environment. However, general environmental monitoring pollution early warning systems have poor adaptability to dynamically changing environmental monitoring data, are sensitive to high-frequency environmental noise data, and are difficult to coordinate the inconsistent control directions of multiple pollution sources, which leads to poor accuracy of environmental monitoring pollution early warnings; general environmental monitoring pollution early warning systems are unable to make real-time adjustments to the dynamic changes of pollution sources in different regions, and are easily affected by monitoring noise and external disturbances, which leads to poor environmental monitoring pollution early warning effects. Summary of the invention

[0003] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides an artificial intelligence-based environmental monitoring pollution warning system. In view of the fact that general environmental monitoring pollution warning systems have poor adaptability to dynamically changing environmental monitoring data, are sensitive to high-frequency environmental noise data, and have difficulty in coordinating inconsistent control directions of multiple pollution sources, which leads to poor accuracy of environmental monitoring pollution warnings, this scheme introduces rapid changes in traffic flow fluctuations and long-term trends in seasonal changes and dynamic disturbance compensation to construct a multi-time scale dynamic model of pollutant concentration to capture the changeable and complex changes in environmental monitoring pollution; introduces pollutant interaction intensity to construct a gain design unit to achieve coordinated control of multiple pollution sources; thereby improving the accuracy of environmental monitoring pollution warnings; in view of the general environmental monitoring pollution warning system ... The environmental monitoring pollution warning system cannot make real-time adjustments to the dynamic changes of pollution sources in different regions and is easily affected by monitoring noise and external disturbances, which leads to poor environmental monitoring pollution warning effects. This scheme introduces a dynamic adjustment fuzzy basis function mechanism to dynamically adjust the pollutant concentration range and improve control accuracy. Based on multi-level recursive control, an independent recursive control input is designed for each pollutant indicator, so that the recursive control inputs at different levels can work together to improve the overall monitoring and early warning efficiency; a nonlinear dynamic surface controller filter is used to smooth the control signal to reduce the interference of monitoring noise on the system; and pollution assessment is performed based on dynamic gain design and the time upper limit of the pollutant concentration returning to the safe range is calculated to improve the environmental monitoring pollution early warning effect.

[0004] The technical solution adopted by the present invention is as follows: the artificial intelligence-based environmental monitoring pollution early warning system provided by the present invention includes a data acquisition module, a data preprocessing module, an environmental monitoring pollution assessment model establishment module and an environmental monitoring pollution early warning module; The data acquisition module collects historical environmental monitoring data; The data preprocessing module performs data cleaning, data conversion and standardization on the collected data; The environmental monitoring pollution assessment model establishment module realizes precise control of pollutant concentrations by dynamically adjusting fuzzy basis functions and recursively designing multi-level control inputs, and performs pollution assessment based on the time upper bound, thereby realizing the establishment of an environmental monitoring pollution assessment model; The environmental monitoring pollution warning module monitors pollution warning for environmental monitoring data collected in real time.

[0005] Furthermore, in the data acquisition module, the historical environmental monitoring data includes pollutant concentration data, meteorological data, geographic data, sampling time and pollution assessment status; the pollution assessment status is used as a data label; the pollution assessment status includes a normal state and an abnormal state.

[0006] Furthermore, in the data preprocessing module, the data cleaning is to process missing values ​​and duplicate values; the data conversion is to convert the data into a vector form; and the standardization processing is based on the maximum and minimum normalization method for standardization.

[0007] Furthermore, the environmental monitoring pollution assessment model establishment module specifically includes the following contents: Pollutant concentration multi-time scale dynamic model construction unit: establish a pollutant concentration multi-time scale dynamic model based on historical environmental monitoring data; Gain design unit; introduce the pollutant interaction intensity and design multiple gain functions for multiple indicators of pollutants; Fixed-time stability is introduced into the unit; Lyapunov function is designed based on the fixed-time stability theory; Adaptive fuzzy control combined unit; use fuzzy logic system to approximate unknown functions; design adaptive law to estimate weights; Nonlinear dynamic surface controller filter building unit; Introducing nonlinear dynamic surface controller filter; Final controller design unit; introduce the mechanism of dynamically adjusting fuzzy basis functions, recursively design the control input of pollutants; obtain the final control input of pollutants; Pollution assessment unit; calculate the upper time limit for the pollutant concentration to return to the safe range; set a convergence threshold in advance, and when the upper time limit is higher than the convergence threshold, it is determined to be an abnormal state; use the binary cross entropy loss function to update the parameters of the environmental monitoring pollution assessment model based on the gradient descent algorithm; divide the collected data into a test set and a training set, train the parameters of the environmental monitoring pollution assessment model based on the training set, and verify the performance of the environmental monitoring pollution assessment model based on the test set.

[0008] Furthermore, the environmental monitoring pollution early warning module collects environmental monitoring data in real time, and inputs it into the environmental monitoring pollution assessment model after preprocessing. If it is determined to be an abnormal state by the environmental monitoring pollution assessment model, the management personnel will be warned.

[0009] The beneficial effects achieved by the present invention using the above scheme are as follows: (1) In view of the fact that general environmental monitoring pollution warning systems have poor adaptability to dynamically changing environmental monitoring data, are sensitive to high-frequency environmental noise data, and have difficulty coordinating inconsistent control directions of multiple pollution sources, which in turn leads to poor accuracy of environmental monitoring pollution warnings, this scheme introduces the rapid changes in traffic flow fluctuations and the long-term trend of seasonal changes and dynamic disturbance compensation to construct a multi-time scale dynamic model of pollutant concentration to capture the changeable and complex changes in environmental monitoring pollution; introduces the pollutant interaction intensity to construct a gain design unit to achieve coordinated control of multiple pollution sources; and thus improves the accuracy of environmental monitoring pollution warnings.

[0010] (2) In view of the problem that general environmental monitoring pollution warning systems cannot make real-time adjustments to the dynamic changes of pollution sources in different regions and are easily affected by monitoring noise and external disturbances, which leads to poor environmental monitoring pollution warning effects, this scheme introduces a dynamic adjustment fuzzy basis function mechanism to dynamically adjust the pollutant concentration range and improve control accuracy. Based on multi-level recursive control, independent recursive control inputs are designed for each pollutant indicator, so that the recursive control inputs at different levels can work together to improve the overall monitoring and early warning efficiency; a nonlinear dynamic surface controller filter is used to smooth the control signal to reduce the interference of monitoring noise on the system; and pollution assessment is performed based on dynamic gain design and calculation of the time upper limit of the pollutant concentration returning to the safe range; thereby improving the environmental monitoring pollution early warning effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A schematic diagram of the process flow of the artificial intelligence-based environmental monitoring pollution early warning system provided by the present invention; Figure 2 Schematic diagram of the process for building a module for the pollution assessment model for environmental monitoring.

[0012] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0013] 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.

[0014] In the description of the present invention, it should be understood that terms such as “upper”, “lower”, “front”, “back”, “left”, “right”, “top”, “bottom”, “inside” and “outside” indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as limiting the present invention.

[0015] Example 1, see Figure 1 The artificial intelligence-based environmental monitoring pollution early warning system provided by the present invention includes a data acquisition module, a data preprocessing module, an environmental monitoring pollution assessment model establishment module and an environmental monitoring pollution early warning module; The data acquisition module collects historical environmental monitoring data; and sends the data to the data preprocessing module; The data preprocessing module performs data cleaning, data conversion and standardization on the collected data; and sends the data to the environmental monitoring pollution assessment model establishment module; The environmental monitoring pollution assessment model establishment module realizes precise control of pollutant concentration by dynamically adjusting fuzzy basis functions and recursively designing multi-level control inputs, and performs pollution assessment based on the time upper bound, thereby realizing the establishment of an environmental monitoring pollution assessment model; and sends the data to the environmental monitoring pollution early warning module; The environmental monitoring pollution warning module monitors pollution warning for environmental monitoring data collected in real time.

[0016] Example 2, see Figure 1 This embodiment is based on the above embodiment. In the data acquisition module, the historical environmental monitoring data includes pollutant concentration data, meteorological data, geographic data, sampling time and pollution assessment status; the pollution assessment status is used as a data label; the pollution assessment status includes normal state and abnormal state; the pollutant concentration data includes PM2.5, PM10, SO 2 、NO 2, O 3 and CO concentration data; the meteorological data include temperature, humidity, wind speed, wind direction, atmospheric pressure, rainfall and radiation intensity; the geographical data include terrain features, land use type, road network data, green space distribution and pollution source distribution.

[0017] Example 3, see Figure 1 This embodiment is based on the above embodiment. In the data preprocessing module, data cleaning is to process missing values ​​and duplicate values; the data conversion is to convert the data into a vector form; and the standardization processing is based on the maximum and minimum normalization method for standardization.

[0018] Example 4, see Figure 1 and Figure 2 ,The module for establishing the environmental monitoring pollution assessment model includes the following: Contaminant concentration multi-time scale dynamic model construction unit; Based on pollution diffusion and external random interference, a pollutant concentration multi-time scale dynamic model is constructed to improve adaptability to complex dynamic environments; A pollutant concentration multi-time scale dynamic model is established based on historical environmental monitoring data, expressed as: ; ; ; where x is the pollutant concentration vector; f(·) is the multi-time scale natural diffusion dynamic function of the pollutant; h(·) is the unknown pollutant control direction, which is used to reflect the impact of intervention measures; g(·) is the external random disturbance; u is the control input of the pollution emission reduction; is Brownian motion; t is the sampling time; is the scale parameter; and They are the short-time-scale and long-time-scale pollution diffusion dynamic functions, which are used to capture the rapid changes of traffic flow fluctuations and the long-term trend of seasonal changes, respectively; is the dynamic mean of the disturbance, indicating the direction of the disturbance; is the dynamic variance of the disturbance, indicating the uncertainty of the disturbance intensity; N(·) is a normal distribution; Gain design unit; used to design independent gain for each pollutant index, improve the control accuracy of multi-source pollutants, and avoid the gain offset problem between multi-index control directions; introduce pollutant interaction intensity and design multiple gain functions for multiple pollutant indexes, expressed as: ;in, is the gain function of the pollutant index; is an adaptive variable used to adjust the gain dynamics; i is the pollutant type index; is the pollutant interaction intensity; Fixed-time stability is introduced into the unit; the environmental system is susceptible to external interference from weather changes, which slows down the convergence of pollutant concentration indicators; the fixed-time stability theory is introduced to ensure that the pollutant indicators converge to a safe range within a limited time; the Lyapunov function is designed based on the fixed-time stability theory, which is expressed as: ;in, is the generator of the Lyapunov function, which is used to analyze the system stability; V(·) is the Lyapunov function, which is used to measure the magnitude of the pollutant concentration error; a and b are controller gain parameters; p and q are nonlinear attenuation exponents; and is the compensation constant; is an adaptive variable The dynamic rate of change; is the unknown pollutant control direction; m is the total number of pollutant types.

[0019] By performing the above operations, the general environmental monitoring pollution warning system has poor adaptability to dynamically changing environmental monitoring data, is sensitive to high-frequency environmental noise data, and has difficulty in coordinating inconsistent control directions of multiple pollution sources, which leads to poor accuracy of environmental monitoring pollution warning. This scheme introduces the rapid changes in traffic flow fluctuations and the long-term trend of seasonal changes and dynamic disturbance compensation to construct a multi-time scale dynamic model of pollutant concentration to capture the changeable and complex changes in environmental monitoring pollution; introduces the pollutant interaction intensity to construct a gain design unit to achieve coordinated control of multiple pollution sources; and thereby improves the accuracy of environmental monitoring pollution warning.

[0020] Example 5, see Figure 1 and Figure 2 Based on the above embodiment, this embodiment further includes the following contents: Adaptive fuzzy control combination unit; used to dynamically update fuzzy system parameters, improve controller adaptability, solve the problem that pollutant diffusion model and interference terms are complex nonlinear functions and difficult to accurately model; use fuzzy logic system to approximate unknown functions, expressed as: ; Design the adaptive law estimation weight, expressed as: ; ; Where W is the fuzzy system weight, trained by historical data; Where, is the unknown function approximated by the fuzzy logic system ; is the fuzzy basis function; is the approximation error; is the weight parameter of the fuzzy system; is the dynamic rate of change of the weight parameter; is the gain matrix of the adaptive law; e is the pollutant concentration tracking error; is the target concentration value; and It is the inhibitory factor in the adaptive law; The nonlinear dynamic surface controller filter construction unit is used to filter out high-frequency noise in the change of pollutant concentration and accelerate the convergence of tracking error. The nonlinear dynamic surface controller filter is introduced and expressed as: ;in, is the filter gain; is the filtered control input; is the dynamic response of the filter; is the unfiltered control input; The final controller design unit realizes multi-level control of pollutant concentration, gradually reduces concentration error, and finally controls pollutant emissions; introduces a mechanism for dynamically adjusting fuzzy basis functions, and recursively designs the control input of pollutants, which is expressed as: ; ; ; ; The final control input of the pollutant is obtained, expressed as: Optimization goal It is expressed as: ;in, It is a trade-off factor that adjusts the balance between pollutant concentration control and cost; is the sampling time length; is the square of the control input; is the center of the fuzzy basis function; is the width of the fuzzy basis function; and is the dynamic rate of change; and is the gain parameter that adjusts the rate; is the control gain parameter, is the gain parameter of the final controller; and are the current and final gain dynamic variables, respectively; and are the current gain coefficients of the controller, used for linear and nonlinear error feedback respectively, and is the final gain coefficient of the controller; and are the tracking errors of current and final pollutant concentrations, respectively; is the current estimate of the fuzzy system weights, is the final estimate; and are the current and final strengths used to adjust the fuzzy system feedback, respectively; and are the derivative signals of the current and final previous filter respectively; u is the final control input, which is used to adjust the pollution emission and realize concentration control; is the gain parameter of the final controller; is the fuzzy basis function of the final layer; Pollution assessment unit; calculates the time limit for pollutant concentration to return to the safe range , expressed as: ;in, is a stability parameter; a convergence threshold is set in advance. When the upper limit of time is higher than the convergence threshold, it is judged as an abnormal state; the binary cross entropy loss function is used to update the parameters of the environmental monitoring pollution assessment model based on the gradient descent algorithm; the collected data are divided into a test set and a training set, the parameters of the environmental monitoring pollution assessment model are trained based on the training set, and the performance of the environmental monitoring pollution assessment model is verified based on the test set.

[0021] By performing the above operations, the general environmental monitoring pollution warning system cannot make real-time adjustments to the dynamic changes of pollution sources in different regions, and is easily affected by monitoring noise and external disturbances, which leads to poor environmental monitoring pollution warning effects. This scheme introduces a dynamic adjustment fuzzy basis function mechanism to dynamically adjust the pollutant concentration range and improve control accuracy. Based on multi-level recursive control, an independent recursive control input is designed for each pollutant indicator, so that the recursive control inputs at different levels can work together to improve the overall monitoring and early warning efficiency; a nonlinear dynamic surface controller filter is used to smooth the control signal to reduce the interference of monitoring noise on the system; and pollution assessment is performed based on dynamic gain design and calculation of the time upper limit of the pollutant concentration returning to the safe range; thereby improving the environmental monitoring pollution early warning effect.

[0022] Example 6, see Figure 1 This embodiment is based on the above embodiment. The environmental monitoring pollution warning module collects environmental monitoring data in real time and inputs it into the environmental monitoring pollution assessment model after preprocessing. If it is determined to be an abnormal state by the environmental monitoring pollution assessment model, the management personnel will be warned.

[0023] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0024] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

[0025] The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.

Claims

1. The environmental monitoring and pollution early warning system based on artificial intelligence is characterized by: The system includes a data acquisition module, a data preprocessing module, an environmental monitoring pollution assessment model building module and an environmental monitoring pollution early warning module; The data acquisition module collects historical environmental monitoring data; The data preprocessing module performs data cleaning, data conversion and standardization on the collected data; The environmental monitoring pollution assessment model establishment module realizes precise control of pollutant concentrations by dynamically adjusting fuzzy basis functions and recursively designing multi-level control inputs, and performs pollution assessment based on the time upper bound, thereby realizing the establishment of an environmental monitoring pollution assessment model; The environmental monitoring pollution warning module monitors pollution warning for environmental monitoring data collected in real time.

2. The artificial intelligence-based environmental monitoring pollution early warning system according to claim 1 is characterized by: The environmental monitoring pollution assessment model establishment module specifically includes the following contents: Pollutant concentration multi-time scale dynamic model construction unit: establish a pollutant concentration multi-time scale dynamic model based on historical environmental monitoring data; Gain design unit; Introduce the pollutant interaction intensity and design multiple gain functions for multiple indicators of pollutants; Fixed time stability introduced into the unit; Design of Lyapunov function based on fixed-time stability theory; Adaptive fuzzy control combined unit; use fuzzy logic system to approximate unknown functions; design adaptive law to estimate weights; Nonlinear dynamic surface controller filter building unit; Introducing nonlinear dynamic surface controller filter; Final controller design unit; introduce the mechanism of dynamically adjusting fuzzy basis functions, recursively design the control input of pollutants; obtain the final control input of pollutants; Pollution assessment unit; calculate the upper time limit for the pollutant concentration to return to the safe range; set a convergence threshold in advance, and when the upper time limit is higher than the convergence threshold, it is determined to be an abnormal state; use the binary cross entropy loss function to update the parameters of the environmental monitoring pollution assessment model based on the gradient descent algorithm; divide the collected data into a test set and a training set, train the parameters of the environmental monitoring pollution assessment model based on the training set, and verify the performance of the environmental monitoring pollution assessment model based on the test set.

3. The artificial intelligence-based environmental monitoring pollution early warning system according to claim 2 is characterized by: In the data acquisition module, the historical environmental monitoring data includes pollutant concentration data, meteorological data, geographic data, sampling time and pollution assessment status; the pollution assessment status is used as a data label; the pollution assessment status includes a normal state and an abnormal state.

4. The artificial intelligence-based environmental monitoring pollution early warning system according to claim 3 is characterized by: The environmental monitoring pollution early warning module collects environmental monitoring data in real time, and inputs it into the environmental monitoring pollution assessment model after pre-processing. If it is determined to be an abnormal state by the environmental monitoring pollution assessment model, an early warning will be issued to the management personnel.

5. The artificial intelligence-based environmental monitoring pollution early warning system according to claim 4 is characterized by: In the data preprocessing module, the data cleaning is to process missing values ​​and duplicate values; the data conversion is to convert the data into vector form; and the standardization processing is based on the maximum and minimum normalization method for standardization.

Images