Technical Field
[0001] The embodiments herein generally relate to an artificial intelligence based air pollution prediction and monitoring systems.
Description of the Related Art
[0002] With the continuous promotion of the urbanization process and the steady improvement of the economic development level in China, urban environmental problems such as air, water, and soil pollution are increasingly prominent, people pay more and more attention to the environmental problems, the requirements on the environmental quality are higher and more, and the environmental problems cannot be met by simple manpower monitoring, management and control, and management. With the development and the rise of artificial intelligence technology, the exploration research and the innovative application of the exploration research artificial intelligence technology in the field of environmental management become a new development trend in the field of environmental protection based on the application of information technologies such as the internet of things and big data, and the method has important significance for monitoring and evaluation of regional pollution conditions, large-area joint defense joint control, disposal of environmental pollution events and the like. mainly carry out environmental pollution detection and management through modes such as digital environmental protection and wisdom environmental protection, but the aging and intelligence level of the above-mentioned two kinds of modes remain to be promoted, also can't be the reason that causes environmental pollution carrying out the analysis, and this patent is consequently come.
[0003] Industrial facilities are often built with large open areas in which both workers and sensitive materials are present. In some cases, the processes performed in an industrial facility may negatively influence the climate and air quality of the facility, making it hazardous or inhospitable to the environment inside or outside the facility, or may lead the air quality to exceed or contravene regulatory or environmental health and safety requirements. To stop or mitigate negative effects on air quality, industrial facilities use air handling systems responsible for providing fresh, conditioned outside air and/or removing air from within the facility. Air handlers such as heating, ventilation, and air conditioning units and make-up air units may be individually controlled via a thermostat or basic on/off switches. The facilities may also be cleaned through some sort of stack or baghouse system or exhaust units. The step of modeling the indoor air pollution state based on the measurement data in real-time to predict the pollution of the indoor air quality and calculating the pollution forecasting index may include calculating a pollution prediction index based on the indoor air pollution, Modeling the indoor air pollution condition by classifying it as an exposure model and a risk model for analyzing the model, the IAQ model, the occupant exposure to the pollutant and the individual pollutant reactivity; And an indoor air quality modeling unit that calculates an observation value by using a correlation between measurement data observed over time in indoor environment conditions, identify the indoor air quality model using the observation value, And a prediction step of estimating a contamination prediction index by predicting contamination of the indoor air quality.

SUMMARY
[0004] In view of the foregoing, an embodiment herein provides an artificial intelligence based air pollution prediction and monitoring system. The particulate matter analysis early warning method and device based on artificial intelligence, can realize full coverage of pollution monitoring management based on effectively monitoring the atmospheric environmental pollution condition by a solution formed by combining the Internet, artificial intelligence technology, and environmental informatization, and promote the high-efficiency treatment and decision-making scientification of work such as environmental quality supervision, pollution prevention and control, ecological environment protection and the like. a multivariable input abnormity detection model by using a gate control circulation unit neural network of an attention mechanism provides the deviation degree data of the real-time air particle pollutant concentration data relative to the estimated value, and judges whether the alarm is needed or not by combining the fluctuation rule of historical time-sharing data. And classifying the pollution reasons by using the data triggering the alarm through a full-connection neural network to obtain the speculative values of the pollution to respond at the first time, improve the disposal efficiency, and provide a management mode of reducing personnel and improving efficiency for the optimization of the atmospheric environment.
[0005] The sensing unit collects sensing information including temperature and humidity information and air volume information of the air conditioner and is connected to the air conditioner to receive operation information and sensing information from the air conditioner to control and control the air conditioner A control controller for performing a monitoring function, and an output control unit for controlling an air conditioner based on a control signal of the control controller, wherein the control controller is an artificial intelligence algorithm using temperature and humidity information and air volume information included in the sensing information. It is characterized in that the control is performed by performing machine learning based on the prediction of temperature and humidity information and air volume information by calculating optimized operating conditions and sensing errors. The control controller comprises an input unit connected to the air conditioner and receiving operation information of the air conditioner and sensing information of the sensing unit; a data unit for storing and managing the driving information and the sensing information; a control unit provided to receive the sensing information, determine an air conditioner operation condition, and perform various control functions for the air conditioner; an output unit for outputting an output signal to the output control unit to receive an instruction from the control unit to optimize the operation of the air conditioner; It further includes; a communication unit that transmits information to analyze the information in detail.
[0006] The contribution rate of refined air pollution prediction is based on the emission inventory data and the air pollution prediction data; the refined pollution contribution rate of air pollution is the multiple components of the target pollutants contributed by each emission source recorded in the emission inventory data The predicted contribution rate of each component in the composition to the target pollutant causing air pollution. The refined prediction module is configured to calculate the contribution rate of the refined prediction of air pollution based on the emission inventory data and the air pollution prediction data; the contribution rate of the refined prediction of air pollution is the contribution of each emission source recorded in the emission inventory data The predicted contribution rate of each of the multiple components of the target pollutants to the target pollutants causing air pollution.
[0007] The mesoscale weather forecast data and the emission inventory data of the destination to be predicted can be obtained. The emission inventory data records the emissions and the emission sources corresponding to the emissions. The emission sources are combined to obtain reference emission data, and then mesoscale weather forecast data and reference emission data are input into the air quality numerical model to obtain air pollution forecast data, and the air is calculated based on the emission inventory data and air pollution forecast data Contribution rate of refined pollution prediction. In this application, the emission sources input into the air quality numerical model are combined and used as input to obtain air pollution prediction data in units of the industry type, and then refined based on the emission inventory data. The problem of large calculation amounts in the air quality numerical model is avoided, and the calculation rate is improved.
[0008] The air exchange system according to the present invention has an air regenerating device, individual measuring appliances, multiple decentralized measure devices, and a control Device. The air regenerating device is configured to carry out the ventilation of the building. Individual measuring appliances are configured to measure the building's Air quality and the building's outside air quality. The multiple decentralized measure device is configured to measure respectively to be built including described Build the air quality of multiple observation places in the monitoring region of the object. The control device has a control unit, if the building The air quality beyond the region of objective existence is better than the air quality in the building, then the control unit, which executes, makes the air regenerating device work Usually action. Also there is the control device prediction section, the prediction section to be based on being measured respectively by the multiple decentralized measure device Air quality come predicts whether to occur the air quality outside the building presents the exceptional value caused by polluting air It is abnormal. The control unit is configured to When the prediction section is predicted to occur the exception, terminate the usual action to make The air regenerating device stops.
[0009] The monitoring data are objective and effective. Compared with other types of pollution, environmental pollution, especially atmospheric environmental pollution, has the characteristics of great changes with time and space. Monitoring based on these characteristics is of great significance for obtaining monitoring results that accurately reflect the actual state of atmospheric pollution. The spatial-temporal distribution and concentration of air pollutants are closely related to the distribution, emission volume, topography, geomorphology, and meteorology of pollutant emission sources. Different types of pollutants, emission laws, and the nature of pollutants have different spatial and temporal distribution characteristics. Atmospheric pollutant levels at the same location fluctuate rapidly. There is a concept of time resolution in air pollution monitoring, which requires changes in pollutant concentration to be reflected within a specified time. some acutely hazardous pollutants require a resolution of 3 minutes; some chemical aerosols, such as ozone, require a resolution of 10 minutes for the stimulation of the respiratory tract.
[0010] These and other aspects of the embodiments herein will be better appreciated and understood when considered in conjunction with the following description and the accompanying drawings. It should be understood, however, that the following descriptions, while indicating preferred embodiments and numerous specific details thereof, are given by way of illustration and not of limitation. Many changes and modifications may be made within the scope of the embodiments herein without departing from the spirit thereof, and the embodiments herein include all such modifications.
BRIEF DESCRIPTION OF THE DRAWINGS
[0011] The embodiments herein will be better understood from the following detailed description with reference to the drawings, in which:
[0012] Fig. 1 illustrates an artificial intelligence based air pollution prediction and monitoring system according to certain embodiments herein; and
[0013] FIG. 2 illustrates a flowchart of an air particulate analysis early warning based on artificial intelligence according to certain embodiments herein.
DETAILED DESCRIPTION OF PREFERRED EMBODIMENTS
[0014] The embodiments herein and the various features and advantageous details thereof are explained more fully with reference to the non-limiting embodiments that are illustrated in the accompanying drawings and detailed in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein may be practiced and to further enable those of skill in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.
[0015] Fig. 1 illustrates an artificial intelligence based air pollution prediction and monitoring system according to certain embodiments herein. The indoor air quality control system may be implemented to control a plurality of air handling and distribution units within an industrial facility in a concerted effort to affect an overall air quality goal. An implementation of the air quality control system may include any air handling units, air distribution units, baghouses, exhaust systems, sensor devices, site management devices, and/or supporting computing resources, and other physical and logical components relevant to implement air handling equipment in/for a single facility. In an exemplary embodiment, a plurality of sensors is positioned to operate at different physical locations throughout an enclosed facility such as a building or similar manufacturing location in which the air can be controlled. The sensors variously measure environmental values relevant to air quality, such as humidity, temperature, air pressure, level of contaminants, and the like. In some embodiments, the system may leverage existing nodes and/or networked lighting systems to add additional sensing capability or to add additional communication flexibility to the mesh network. The sensors, together with one or more other devices, may act as a wireless mesh network to transfer and receive data across the facility. The sensors operate periodically to sense their respective environmental conditions, and the sensor data is sent, through the mesh network, to a gateway device. The gateway device may store the sensor data in a database, either local or remote to the gateway.
[0016] The sensor data, historical data, and other environments in a dataset, and use one or more machine-learning algorithms to model the air quality within the facility. In the exemplary embodiment, the sensor data is considered holistically that is, the sensed air quality data is considered in a pervasive analysis of the overall condition of the facility, rather than individual, independent analyses of data for the position of each sensor. As the sensors continue to provide additional data, machine learning techniques may be applied to progressively generate modified, improved models and algorithms for decision-making. The models predict the behavior of the air in the facility given a variety of parameters indicating a correlation between collected data and air quality and are used to identify actions to take to meet desired air handling goals. Error minimization functions may be applied over the predictive models to adhere the outputs of the models to a desired optimization target such as energy usage, particulate concentration, temperature, humidity, and/or pressure. The decisions regarding the limitations and/or goals of the model are done by various appropriate environmental health and safety considerations, as defined by a site administrator, industry standard, and the like.
[0017] The control controller has a real-time operation status display function, a variable air volume or constant air volume control function to provide operation information such as a fan performance chart, check the vibration status of the fan rotating body and the presence of abnormality in the belt coupled to the fan housing, fluctuations in system static pressure. It is possible to provide various control functions for the air conditioner and the internal configuration, including an analysis of operating cost using a fan and coil heat quantity, and a warning and action method according to various operating conditions. the support vector machine algorithm as described above is applied to the data obtained from the sensors, the number of training times of machine learning increases as the data transmitted from the sensors accumulated more and more, and as a result, the modeling obtained through training the accuracy gradually increases. This characteristic is that the prediction error rate can be improved more and more as the number of training increases compared to the analysis technique using a specific mathematical or statistical modeling always has a certain degree of prediction error rate, which is a major factor in modeling through machine learning techniques. advantage.
[0018] FIG. 2 illustrates a flowchart of an air particulate analysis early warning based on artificial intelligence according to certain embodiments herein. The minimum-maximum normalization method is used for performing data normalization processing on the air particulate matter data, and the normalization principle of the method is that a linear mapping operation is performed on sample data by using a conversion function so that a result after the linear mapping falls within the interval, and subsequent processing is facilitated. When the standardized sample data is used for modeling and predicting by using the neural network, the convergence rate of the model can be greatly improved, and meanwhile, the prediction precision and the learning efficiency of the model are improved. an air particulate matter data set is established based on the data after the preprocessing. In this embodiment, the whole data set is selected as the training set for training the model parameters, and the other is selected as the test set for evaluating the generalization ability of the model. Considering the limited amount of data available, the K-Fold cross-validation method is used in the present embodiment to evaluate the predictive performance of the model, and the validation set is not divided separately.
[0019] At a certain distance from the target station, the attention-based gated loop unit neural network respectively establishes an abnormality detection model for the target station and the other stations, and the target station and the other stations are respectively trained according to the air particulate matter data sets corresponding to the target station and the other stations, to obtain an abnormality detection model corresponding to the trained target station and an abnormality detection model corresponding to the other stations. The air particulate matter analysis early warning method based on artificial intelligence can effectively utilize monitoring data, automatically identify the reason for the air pollution event and give an alarm based on the existing air monitoring station, so that government departments can deal with the air particulate matter in the first time, the disposal efficiency is improved, and a treatment mode of reducing manpower and increasing efficiency is provided for the optimization of the atmospheric environment. The embodiment of the invention also provides an air particulate matter analysis and early warning device based on artificial intelligence, which comprises.
[0020] The abnormity early warning module is used for determining a difference value between the predicted value and the actual value of each air particulate matter through the trained abnormity detection model, judging whether each air particulate matter is abnormal according to the difference value, and if so, giving an early warning prompt. The device also comprises an analysis module, a data processing module, and a data processing module, wherein the analysis module is used for extracting corresponding characteristic quantities from the air particles and meteorological data. The air particulate matter analysis and early warning device based on artificial intelligence provided by the embodiment of the invention can execute the air particulate matter analysis and early warning method based on artificial intelligence provided by any embodiment of the invention and has corresponding functional modules and beneficial effects of the execution method.

We Claims:

A method of an artificial intelligence based air pollution prediction and monitoring systems, wherein the method comprises:
an anomaly detection model based on a gated cycle unit neural network of an attention mechanism, and training the anomaly detection model according to the air particulate matter data set to obtain a trained anomaly detection model;
air quality or a state of an air handling unit of a plurality of air handling units, and to transmit the sensed environmental measurement or the state to the air handling control unit, the frequency of periodic transmission being based on a predetermined interval of time;
a public information unit that collects public information of external organizations necessary for the operation of the air conditioner;
the pollution degree, the air purification capability value, or the air purification prediction information of the indoor air quality through at least one or more display devices installed in the large building. Way;
a prediction module configured to input the mesoscale weather prediction data and the reference emission data into an air quality numerical model to obtain air pollution prediction data;
individual measuring appliances measure the air quality in the building and the air quality outside the building.