CN115931041A - Novel regional environment-friendly monitoring and early warning method - Google Patents
Novel regional environment-friendly monitoring and early warning method Download PDFInfo
- Publication number
- CN115931041A CN115931041A CN202211249760.7A CN202211249760A CN115931041A CN 115931041 A CN115931041 A CN 115931041A CN 202211249760 A CN202211249760 A CN 202211249760A CN 115931041 A CN115931041 A CN 115931041A
- Authority
- CN
- China
- Prior art keywords
- data
- enterprise
- monitoring
- power
- environmental protection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a novel regional environment-friendly monitoring and early-warning method, and relates to the field of environment-friendly detection. The regional environment-friendly monitoring and early warning method comprises the following steps: step one, enterprise electric power data acquisition: the method comprises the steps of collecting various data of an enterprise, wherein the collected data comprise enterprise power data, environment monitoring data and equipment power data; step two, data analysis: after the enterprise electric power data acquisition is finished, various acquired data are transmitted to the cloud through the internet of things gateway, the cloud can integrate various data, and an electric power environmental protection index model, a pollution source online monitoring model and a production state estimation model are constructed, so that pollution behaviors are found. Waste gas, waste water discharge in with enterprise's amount of taxation, enterprise's power consumption total amount, industrial production, external environment data and thing networking collection equipment's operating condition data integrated analysis carry out accurate portrait to the pollutant discharge activity in the industrial production process of enterprise, reach the effect of high-efficient environmental protection monitoring and early warning in advance.
Description
Technical Field
The invention relates to the technical field of environmental protection detection, in particular to a novel regional environmental protection monitoring and early warning method.
Background
The existing environmental pollution monitoring and early warning technology is based on internet of things collection equipment and video collection equipment, a plurality of pollution source monitoring equipment are installed at pollution source production positions, an environmental quality monitoring and management system comprises a plurality of environment detection equipment and is used for detecting environmental indexes, the environmental indexes comprise wind direction, wind power, temperature and humidity, comprehensive environmental protection monitoring can be carried out on all environmental protection data of a large-scale factory or a certain area, and the effect of environmental protection monitoring is improved.
The external environmental protection data mainly comprise three types of data, namely pollution source data, environment monitoring data and meteorological data. Wherein the pollution source data comprises data such as pollution source names, administrative areas, industry types, production addresses and the like; the environment monitoring data comprises water pollution emission data, atmospheric pollution emission data and other data; the meteorological data comprises data such as atmospheric quality information and daily temperature information.
The prior art has the defects that only the data dimension of pollutant emission is concerned, and effective correlation analysis is lacked for the relation between the pollutant emission and the production scale and the production intensity, so that reasonable early warning for the pollutant emission according to industrial production activities is difficult to carry out.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a novel regional environment-friendly monitoring and early warning method, which comprehensively analyzes the tax amount of an enterprise, the total power consumption of the enterprise, the waste gas and waste water discharge in industrial production, external environment data and the working state data of the Internet of things acquisition equipment, accurately figures the pollutant discharge activity in the industrial production process of the enterprise and achieves the effects of efficient environment-friendly monitoring and early warning.
In order to realize the purpose, the invention is realized by the following technical scheme: a novel regional environment-friendly monitoring and early-warning method comprises the following steps:
step one, enterprise electric power data acquisition: the method comprises the steps of collecting various data of an enterprise, wherein the collected data comprise enterprise power data, environment monitoring data and equipment power data;
step two, data analysis: after the enterprise electric power data acquisition is finished, various acquired data are transmitted to the cloud through the internet of things gateway, the cloud can integrate various data, and an electric power environmental protection index model, a pollution source online monitoring model and a production state estimation model are constructed, so that pollution behaviors are found.
Preferably, the enterprise power data is mainly used for collecting total power consumption data of an enterprise power consumption collection system butted with an industrial enterprise, and the collected data comprises current, voltage, power, electric quantity and power consumption load data;
the environment monitoring data mainly comprises pollution source data, pollutant emission data and meteorological hydrological data of enterprises;
the equipment power data mainly comprises current, voltage, power and electric quantity data collected by the environmental protection facility power consumption monitoring equipment.
Preferably, the power environmental protection index model takes air quality indexes AQI, PM2.5, air temperature, rainfall, humidity and air pollution control enterprise load as input data, integrates power and environmental protection data based on Hadoop cluster big data, establishes an analysis model of a BP neural network through normalizing a unified data source format, achieves better prediction precision through iterative tuning of the model, and finally outputs load prediction and air quality index prediction results.
Preferably, the pollution source online monitoring model comprises pollution source monitoring positioning, and the pollution source monitoring positioning is mainly used for establishing a typical pollution-related enterprise load model library to form an industry curve and characteristic parameters. And selecting a designated enterprise, reading power utilization data, and calculating characteristic parameters. And comparing the parameters one by one to generate a list of suspicions found.
Preferably, the production state estimation model is mainly used for constructing an enterprise production state estimation model based on electric power data, enterprise production state estimation under the condition that enterprise historical yield is unknown is considered, clustering analysis is carried out based on a K-means algorithm, dynamic measurement and calculation of enterprise production activities are achieved, enterprises with production mode transfer during control period are researched and found by identifying main production period characteristic points of a typical power consumption curve for normal production of the enterprises and a power consumption curve during control period, and reference is provided for accurate law enforcement.
The invention provides a novel regional environment-friendly monitoring and early warning method. The method has the following beneficial effects:
1. the invention adopts various basic data to comprehensively analyze the pollutant emission condition, so that the pollutant emission state identification and the compliance identification in the enterprise production process are more accurate, the characteristics of each type and each enterprise can be independently identified, the problem of one-step operation in the environmental protection monitoring process is avoided, and a scientific and objective pollutant emission report is provided.
2. The system and the method have the advantages that the high penetrability of the electric power data is utilized, the auxiliary analysis of the power consumption and the energy consumption of enterprises on the environmental protection is objectively reflected, the environmental protection department is assisted to carry out effective supervision, effective pollution discharge monitoring and pollution control guidance are carried out on the polluted enterprises, the environmental protection treatment level of the whole area is improved, and comprehensive control and joint defense joint control treatment are realized.
3. Under the heavy pollution environment, environmental protection management and control are upgraded, and the ecological environment bureau can be helped to quickly lock illegal discharge enterprises based on scientific judgment and accurate analysis of electric power big data; and providing an abnormal power utilization list of an enterprise, and assisting the enterprise to stop production and limit production decision analysis.
4. The power data and the environmental protection data are analyzed, and the pollution condition possibly generated in a short term is predicted by researching and judging from the power utilization angle of enterprises through quantitative diagnosis, so that early warning is provided for the ecological environment bureau, and a treatment strategy is researched in advance.
Drawings
FIG. 1 is a schematic view of the present invention;
FIG. 2 is a block diagram of a power environmental protection index algorithm of the present invention;
fig. 3 is a block diagram of the pollution source monitoring and positioning algorithm of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example (b):
as shown in fig. 1 to 3, an embodiment of the present invention provides a new method for monitoring and warning environmental protection in a region, including the following steps:
step one, enterprise electric power data acquisition: collecting various data of an enterprise, wherein the collected data comprises enterprise power data, environment monitoring data and equipment power data;
step two, data analysis: after the enterprise electric power data acquisition is finished, various acquired data are transmitted to the cloud through the gateway of the Internet of things, the cloud can integrate various data, and an electric power environmental protection index model, a pollution source online monitoring model and a production state estimation model are constructed, so that pollution behaviors are found, the behaviors of stealing, draining and omitting are eliminated, and advance early warning is realized;
the data analysis comprises several system architectures, which are divided into an acquisition layer, a data layer, a platform layer, a service layer and an application layer;
an acquisition layer: the data sources are mainly as follows: internal power data, power data acquired by environmental protection facility power utilization monitoring equipment and external environmental protection data;
and (3) a data layer: the data layer includes real-time data and business application data. The service data of the project is divided into a pollution source database, an automatic environment quality monitoring database, an environment metadata database, a GIS database, an equipment power database and a power database according to functions;
a platform layer: the platform layer mainly comprises data synchronization, data statistics, data exchange, data analysis and a data interface;
and (3) a service layer: the service layer comprises independent sub-modules of unified user management, GIS service, real-time data service, application data service and the like, each sub-module provides an accessible service interface to the outside, and the inside of each sub-module forms an integrated basic service layer through a corresponding mechanism to provide various universal functions for each application system constructed to run on the service layer;
an application layer: the application layer is composed of a plurality of business application subsystems and is jointly based on a unified service support environment.
The enterprise power data mainly comprises the steps that total power utilization data of an enterprise power utilization acquisition system and an industrial enterprise are acquired, the acquired data comprise current, voltage, power, electric quantity and power consumption load data, monitoring equipment comprises an enterprise ammeter, an equipment ammeter and an environment sensor, the data are acquired from a data source respectively and are transmitted to a data center for data analysis;
the environment monitoring data mainly comprises pollution source data, pollutant emission data and meteorological hydrological data of enterprises, wherein the pollution source data comprises data such as pollution source names, administrative areas, industry categories and production addresses; the pollutant emission data comprises water pollution emission data, atmospheric pollution emission data and other data; the meteorological hydrological data comprise data such as atmospheric quality information and daily temperature information;
the equipment power data mainly comprises current, voltage, power and electric quantity data collected by the environmental protection facility power consumption monitoring equipment.
As shown in fig. 2, the electric power environmental protection index is based on the power consumption data of the pollution-related enterprises, is dynamically associated with the environmental protection air quality index AQI value to perform environmental protection data expression, is used for quantitatively evaluating the execution situation of pollution prevention measures of enterprises in various areas and industries, and reflects the emission reduction effect of the enterprises, the electric power environmental protection index model takes the air quality index AQI, PM2.5, air temperature, rainfall, humidity and the load of the pollution-related pollution control enterprises as input data, integrates electric power and environmental protection data based on the big data of the Hadoop cluster, establishes an analysis model of the BP neural network by normalizing a unified data source format, and iteratively adjusts the model to achieve better prediction precision, so that the model outputs the load prediction and air quality index prediction results.
And monitoring and positioning the pollution source, establishing a load model library of a typical pollution-related enterprise, and forming an industry curve and characteristic parameters. And selecting a designated enterprise, reading power utilization data, and calculating characteristic parameters. And comparing the parameters one by one to generate a list of suspected pollutants, wherein the pollution source online monitoring model comprises pollution source monitoring and positioning, and the pollution source monitoring and positioning are mainly used for establishing a load model library of a typical pollutant-related enterprise to form an industry curve and characteristic parameters. And selecting a designated enterprise, reading power utilization data, and calculating characteristic parameters. Comparing the parameters one by one to generate a list of suspicions found;
the method has two core concepts: the power consumption fluctuation rate of the pollution source and the day and night load ratio of the pollution source;
one is the fluctuation rate for pollution sources: as shown in fig. 3, the power fluctuation rate of the pollution source mainly describes the power fluctuation situation of an enterprise or an area, and is reflected by comparing the standard deviation of the power consumption in the current month with the standard deviation of the power consumption in the current month of the industry, which is specifically as follows:
wherein i ∈ [1, 31 ]]，X i Representing the daily power consumption of the pollution source in the month.
When the standard deviation of the monthly power consumption of the pollution source is less than or equal to 10% of the standard deviation of the monthly power consumption of the industry, or the standard deviation of the monthly power consumption of the pollution source is more than or equal to 90% of the standard deviation of the monthly power consumption of the industry, judging that the power consumption fluctuation of the enterprise of the pollution source is large;
the second is pollution source day and night load ratio: the pollution source day-night load ratio mainly describes the day-night electricity utilization difference condition of an enterprise or an area and is mainly represented by the ratio of day-night electricity utilization of the enterprise in a plurality of days.
Wherein D is j Is the daily power consumption of the enterprise, N j Is the night electricity consumption of the enterprise, (6 am to 8 pm in the daytime, 9 pm to 5 pm in the evening)
And collecting 96 points of data every day, comparing the data with the daily and night electricity load ratio of enterprises of the same type, and identifying abnormal states.
The production state estimation model is mainly used for constructing an enterprise production state estimation model based on electric power data, considering enterprise production state estimation under the condition that the historical yield of an enterprise is unknown, carrying out cluster analysis based on a K-means algorithm, realizing dynamic measurement and calculation of enterprise production activities, and researching and judging the enterprise with the production mode transferred during the management and control period by identifying the characteristic points of the main production period of a typical power utilization curve produced normally by the enterprise and a power utilization curve during the management and control period, so as to provide reference for accurate law enforcement;
the method comprises the steps that firstly, the historical daily integral point power consumption data of an enterprise can be clustered, and daily power consumption curve centroids corresponding to a peak power consumption state and a valley power consumption state are found and are respectively used for representing power consumption corresponding to PH and PL of full production of the enterprise;
the second mode is normal production when the power consumption of an enterprise is between PL and PH;
thirdly, when the power consumption of the enterprise is lower than PL, the enterprise production is stopped or a production limit state is executed;
the production state recognition effect analysis of enterprises can be realized: the simulation identifies the production state of 300 enterprises, makes up the nonlinear regression of input data abnormity and partial missing data, processes 52 enterprises with abnormal data, and correctly identifies 296 enterprises with the accuracy rate of 98%;
as shown in fig. 1, according to the above, the present specification makes the following detailed description: the application provides an environmental protection monitoring method for calculating an electric power environmental protection index, which comprises the following steps:
1) Taking air quality index AQI, PM2.5, air temperature, rainfall, humidity and air pollution to control enterprise load;
2) Reading daily power consumption of all enterprises in the area;
3) Calculating the N-day rolling average value of daily electricity consumption of a certain enterprise;
4) Calculating the electric power environmental protection index of a certain enterprise according to the pollution discharge pressure reduction standard of the enterprise;
5) Carrying out weighted average on enterprise power environmental protection indexes in the region;
6) And (5) obtaining the environmental protection index of the electric power in the region.
As shown in fig. 1, it is a correlation between the environmental index of electric power and the power consumption of the enterprise.
The environmental protection monitoring method is used for positioning a pollution source and comprises the following steps:
1) Selecting an area needing to be calculated;
2) Selecting the daily electricity consumption of a certain enterprise;
3) Calculating a certain enterprise characteristic parameter X according to the power consumption fluctuation rate of the pollution source and the day-night load ratio of the pollution source i ；
4) Matching the enterprise industry type K;
5) Obtaining an industry characteristic parameter T k ；
6)X i And T k The degree of confidence N is determined
7) If X is i And T k If the two are consistent, ignoring, and continuing to the step 2), if the two are not consistent, considering that the pollutant theft and exclusion exist in the enterprise
And adding the enterprise i into the pollutant stealing suspicion list.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (5)
1. A new regional environmental protection monitoring and early warning method is characterized in that: the method comprises the following steps:
step one, enterprise electric power data acquisition: the method comprises the steps of collecting various data of an enterprise, wherein the collected data comprise enterprise power data, environment monitoring data and equipment power data;
step two, data analysis: after the enterprise electric power data acquisition is finished, various acquired data are transmitted to the cloud through the internet of things gateway, the cloud can integrate various data, and an electric power environmental protection index model, a pollution source online monitoring model and a production state estimation model are constructed, so that pollution behaviors are found.
2. The new regional environmental protection monitoring and early warning method according to claim 1, characterized in that:
the enterprise power data mainly comprises total power consumption data of an industrial enterprise, which are acquired by an enterprise power consumption acquisition system, wherein the acquired data comprise current, voltage, power, electric quantity and power consumption load data;
the environment monitoring data mainly comprises pollution source data, pollutant emission data and meteorological hydrological data of enterprises;
the equipment power data mainly comprises current, voltage, power and electric quantity data collected by the environmental protection facility power consumption monitoring equipment.
3. The new regional environmental protection monitoring and early warning method according to claim 1, characterized in that: the electric power environmental protection index model is characterized in that an air quality index AQI, a PM2.5, air temperature, rainfall, humidity and air pollution control enterprise load are taken as input data, the electric power and environmental protection data are integrated based on Hadoop cluster big data, an analysis model of a BP neural network is established through normalization and unification of a data source format, the model achieves better prediction precision through iterative optimization, and finally the model outputs a load prediction result and an air quality index prediction result.
4. The new regional environmental protection monitoring and early warning method according to claim 1, characterized in that: the pollution source online monitoring model comprises pollution source monitoring and positioning, and the pollution source monitoring and positioning are mainly used for establishing a typical pollution-related enterprise load model library to form an industry curve and characteristic parameters. And selecting a designated enterprise, reading power utilization data, and calculating characteristic parameters. And comparing the parameters one by one to generate a list of suspicions found.
5. The new regional environmental protection monitoring and early warning method of claim 1, which is characterized in that: the production state estimation model is mainly used for constructing an enterprise production state estimation model based on power data, enterprise production state estimation under the condition that the historical yield of an enterprise is unknown is considered, clustering analysis is carried out based on a K-means algorithm, dynamic measurement and calculation of enterprise production activities are achieved, enterprises with production mode transfer during control period are researched and found by identifying main production period characteristic points of a typical power utilization curve and a power utilization curve during control period in normal production of the enterprises, and reference is provided for accurate law enforcement.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211249760.7A CN115931041A (en) | 2022-10-12 | 2022-10-12 | Novel regional environment-friendly monitoring and early warning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211249760.7A CN115931041A (en) | 2022-10-12 | 2022-10-12 | Novel regional environment-friendly monitoring and early warning method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115931041A true CN115931041A (en) | 2023-04-07 |
Family
ID=86551313
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211249760.7A Pending CN115931041A (en) | 2022-10-12 | 2022-10-12 | Novel regional environment-friendly monitoring and early warning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115931041A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117455124A (en) * | 2023-12-25 | 2024-01-26 | 杭州烛微智能科技有限责任公司 | Environment-friendly equipment monitoring method, system, medium and electronic equipment for enterprises |
-
2022
- 2022-10-12 CN CN202211249760.7A patent/CN115931041A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117455124A (en) * | 2023-12-25 | 2024-01-26 | 杭州烛微智能科技有限责任公司 | Environment-friendly equipment monitoring method, system, medium and electronic equipment for enterprises |
| CN117455124B (en) * | 2023-12-25 | 2024-03-08 | 杭州烛微智能科技有限责任公司 | Environment-friendly equipment monitoring method, system, medium and electronic equipment for enterprises |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110097297B (en) | Multi-dimensional electricity stealing situation intelligent sensing method, system, equipment and medium | |
| CN110889088B (en) | Enterprise pollution discharge supervision method assisted by electric power model | |
| CN115759488B (en) | Carbon emission monitoring early warning analysis system and method based on edge calculation | |
| CN109376906B (en) | Travel time prediction method and system based on multi-dimensional trajectory and electronic equipment | |
| CN114580291B (en) | LSTM-VAE-based dynamic equipment health condition assessment method | |
| CN112465256A (en) | Building power consumption prediction method and system based on Stacking model fusion | |
| CN114518143A (en) | Intelligent environment sensing system | |
| CN115931041A (en) | Novel regional environment-friendly monitoring and early warning method | |
| CN112183625A (en) | PM based on deep learning2.5High-precision time-space prediction method | |
| CN115905319B (en) | Automatic identification method and system for abnormal electricity fees of massive users | |
| CN114023399A (en) | Air particulate matter analysis early warning method and device based on artificial intelligence | |
| CN114997608A (en) | Production efficiency assessment method and system based on industrial chain data analysis | |
| CN115062851B (en) | Pollution discharge abnormality monitoring method and system based on multi-algorithm fusion | |
| CN118098442B (en) | Urban water environment small-scale tracing method based on multilayer perceptron model | |
| CN117935561B (en) | Intelligent traffic flow analysis method based on Beidou data | |
| CN116108445A (en) | Intelligent risk early warning management method and system for information system | |
| CN114235653A (en) | Atmospheric particulate pollutant space-time prediction cloud platform based on end cloud cooperation | |
| CN117634678A (en) | Low-carbon park carbon emission prediction method based on actual operation scene | |
| CN116205528A (en) | Illegal construction identification method and system based on construction site power data | |
| Ali et al. | Architecting a big data-driven software architecture for smart street lighting | |
| CN113822587B (en) | Factory capacity evaluation method based on bus current data | |
| Lin et al. | A novel long-term air quality forecasting algorithm based on kNN and NARX | |
| Hu et al. | The early warning model of dust concentration in smart construction sites based on long short term memory network | |
| CN111369062A (en) | Vehicle dynamics index extraction method and accident risk value prediction method | |
| CN117349777B (en) | Intelligent identification system and method for online monitoring data of water environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |