Environment monitoring method based on Internet of Things

Abstract

The invention discloses an environment monitoring method based on the Internet of Things, and belongs to the technical field of environment monitoring. Comprising the steps of collecting data in a garbage transfer station, and when a judgment result is that the proportion of abnormal data points is not greater than a proportion threshold value of a time period, obtaining an abnormal coefficient of each abnormal data point; performing primary judgment on the data exception risk of the time period by utilizing a quantitative relationship between the exception coefficient and a preset exception coefficient threshold value, and performing secondary judgment on the data exception risk of the time period according to a judgment result; and the management personnel remotely controls the start and stop of the equipment of the garbage transfer station and adjusts the operation parameters of the equipment according to the early warning information. Intelligent monitoring and data sharing of the environment of the garbage transfer station are achieved, energy consumption is reduced, comprehensive intelligent monitoring of the environment of the garbage transfer station is achieved, potential safety hazards can be found in advance, corresponding prevention measures are taken, and safe operation of the garbage transfer station is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental monitoring, and in particular to an environmental monitoring method based on the Internet of Things. Background Art

[0002] Garbage stations are transfer stations for domestic waste in residential areas, factory areas, and housing construction. They are mainly used to temporarily store garbage, and then regularly transfer it to large-scale garbage treatment stations or landfills through garbage trucks such as garbage transfer trucks. However, in this fast-paced society, it is not easy for people to sort and dispose of garbage at any time in their daily lives, and garbage transfer stations are often piled with various garbage. For example, in the hot summer weather, some chemicals piled together will react chemically, causing explosions, fires and other dangerous situations. Therefore, some measures need to be taken to avoid disasters such as fires, so it is necessary to monitor the environment of garbage transfer stations.

[0003] A Chinese patent with publication number CN114323150A discloses a comprehensive environmental monitoring and adjustment system for a garbage transfer station, including: an environmental monitoring platform, an integrated processing unit, a ventilation processing mechanism and a directional fire-fighting mechanism; the output end of the environmental monitoring platform is wirelessly connected to the integrated processing unit, and the output end of the integrated processing unit is also wirelessly connected to the input end of the ventilation analysis unit and the input end of the directional fire-fighting mechanism, respectively, to realize automatic gas detection of the garbage station, and automatically analyze and calculate the ventilation volume according to the gas concentration and the size of the garbage station space, and then cooperate with the integrated processing unit to carry out linkage control of the ventilation component to automatically perform ventilation treatment on the garbage station, realize rational and refined ventilation adjustment of the garbage station, and at the same time detect the smoke and open flames inside the garbage station and perform scene analysis to realize directional fire-fighting treatment, improve fire prevention effect, and enhance safety of use.

[0004] The above patent can only monitor the gas during actual use. Since changes in ambient temperature and humidity will directly affect the activity of microorganisms and the fermentation process of garbage, if these parameters are not monitored and controlled, it is easy to cause excessive fermentation of garbage, produce odor and harmful gases, and pollute the environment. Therefore, it does not meet the existing needs. We propose an environmental monitoring method based on the Internet of Things. Summary of the invention

[0005] The purpose of the present invention is to provide an environmental monitoring method based on the Internet of Things, to realize intelligent monitoring of the environment of a garbage transfer station, to achieve data sharing, to reduce energy consumption, and to realize all-round intelligent monitoring of the environment of a garbage transfer station. Management personnel can more accurately grasp the changes in environmental conditions in the garbage transfer station, can discover potential safety hazards in advance, and take corresponding preventive measures to ensure the safe operation of the garbage transfer station, thereby solving the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solution: an environment monitoring method based on the Internet of Things, the environment monitoring method comprising: Sensors installed in garbage transfer stations are used to collect temperature, humidity and air quality data in real time, and the pre-processed data is integrated and uploaded to the cloud server for storage; The quality of the stored data is judged, and when the judgment result is that the proportion of abnormal data points is not greater than the proportion threshold of the time period, the abnormal coefficient of each abnormal data point is obtained; The data anomaly risk of the time period is initially determined by using the quantitative relationship between the anomaly coefficient and the preset anomaly coefficient threshold, and the data anomaly risk of the time period is secondarily determined based on the determination result; After the processing is completed, feature data is extracted, the extracted feature data is analyzed and predicted, warning information is generated based on the results of the analysis and prediction, and the real-time location of the management personnel is obtained; The early warning information is automatically sent to the terminal of the manager closest to the garbage transfer station. The manager remotely controls the start and stop of the equipment in the garbage transfer station and adjusts the operating parameters of the equipment based on the early warning information.

[0007] Preferably, the judging of the quality of the stored data specifically includes: According to the time series, the thresholds of the collected results at different times are set to determine whether the collected data is discontinuous in the time series; When the collected data do not show discontinuities in the time series, the collected data are divided into multiple time periods; Determine whether the data points in each time period are within the range of the lower abnormal threshold and the upper abnormal threshold; When the data point is not within the range, it is judged as an abnormal data point, and when the data point is within the range, it is judged as a normal data point; Analyze the proportion of abnormal data points to the total data points. When the proportion of abnormal data points is greater than the proportion threshold of the time period, the data at that time is determined to be an abnormal value. When the result of the corresponding time period is determined to be an abnormal value, the data quality of the corresponding time period is determined to be substandard, and the substandard data is processed.

[0008] Preferably, when the proportion of abnormal data points is not greater than the proportion threshold of the time period, obtaining the abnormal coefficient of each abnormal data point specifically includes: When the proportion of abnormal data points is not greater than the proportion threshold of the time period, extract the data value corresponding to each abnormal data point and the data value corresponding to the normal data point in the time period; Generate a data point distribution graph with the time axis corresponding to the data collection moment as the horizontal axis and the data value corresponding to the abnormal data point as the vertical axis; Extract the normal data point closest to the collection time before and after the collection time corresponding to each abnormal data point, and use the normal data point closest to the collection time before and after the collection time corresponding to each abnormal data point as the reference data point; Extract the data value of the reference data point corresponding to each abnormal data point; Obtaining a connection angle between the abnormal data point and the reference data point on a data point distribution diagram using the data value of the abnormal data point and the data value of the corresponding reference data point; Obtaining an abnormal coefficient of each abnormal data point using the data value of each abnormal data point, the connection angle and the data value of the corresponding reference data point; The abnormal coefficient is obtained by the following formula: ; Among them, Y represents the abnormal coefficient; X b Indicates the numerical standard deviation of all normal data points contained in the time period; X yb represents the numerical standard deviation of all abnormal data points contained in the time period; N represents the number of abnormal data points contained in the time period; X yi represents the data value corresponding to the i-th abnormal data point contained in the time period; X 01i Indicates the data value of the normal data point closest to the previous collection time corresponding to the abnormal data point; X 02i Indicates the data value of the normal data point whose collection time is closest to the abnormal data point; D yi represents the data collection time corresponding to the i-th abnormal data point contained in the time period; D 01i The data collection time corresponding to the abnormal data point is the data collection time corresponding to the nearest normal data point before the previous collection time; D 02i It indicates that the collection time corresponding to the abnormal data point is the data collection time corresponding to the nearest normal data point after the collection time.

[0009] Preferably, the method of using the quantitative relationship between the abnormal coefficient and the preset abnormal coefficient threshold to make a primary determination on the data abnormality risk of the time period, and making a secondary determination on the data abnormality risk of the time period according to the determination result, specifically includes: Comparing the abnormal coefficient with a preset abnormal coefficient threshold; When the abnormal coefficient is lower than the preset abnormal coefficient threshold, the data abnormality risk of the time period corresponding to the abnormal coefficient being lower than the preset abnormal coefficient threshold is determined to be low risk; When the abnormal coefficient is not lower than the preset abnormal coefficient threshold, the data abnormality risk of the time period corresponding to the abnormal coefficient being not lower than the preset abnormal coefficient threshold is determined; When the abnormal coefficient is not lower than the preset abnormal coefficient threshold, the distribution density of the abnormal data points in the time period is retrieved.

[0010] Preferably, the distribution density of abnormal data points in the time period is obtained by the following formula: ; Where P represents the distribution density of abnormal data points in a time period; N represents the number of abnormal data points in the time period; R t Indicates the length of time corresponding to the time period; D i represents the data collection time corresponding to the ith abnormal data point; D i+1 Indicates the data collection time corresponding to the i+1th abnormal data point; The data anomaly risk of the time period is determined by using the distribution density of the abnormal data points in the time period and the abnormal coefficient corresponding to the time period.

[0011] Preferably, the data anomaly risk of the time period is determined by using the distribution density of the abnormal data points in the time period and the abnormal coefficient corresponding to the time period, specifically including: Comparing the distribution density of the abnormal data points in the time period with a preset distribution density threshold; When the distribution density of abnormal data points in the time period exceeds a preset distribution density threshold, the data abnormality risk of the time period corresponding to the distribution density exceeding the preset distribution density threshold is determined to be high risk; The data quality in high-risk time periods is considered substandard and the substandard data is processed; When the distribution density of the abnormal data points in the time period does not exceed the preset distribution density threshold, the abnormal coefficient and distribution density corresponding to the time period are retrieved; Using a preset abnormal coefficient reference value and a preset distribution density reference value to perform standardization processing on the abnormal coefficient and the distribution density, respectively, to obtain the abnormal coefficient and the distribution density after the standardization processing; The abnormal comprehensive evaluation coefficient corresponding to the time period is obtained by using the abnormal coefficient and distribution density after the standardization process.

[0012] Preferably, the abnormal comprehensive evaluation coefficient is obtained by the following formula: ; Among them, Z represents the abnormal comprehensive evaluation coefficient; Y trepresents the abnormal coefficient after standardized processing; Y y Indicates the preset abnormal coefficient threshold; P t represents the distribution density after standardization; P y Indicates the preset distribution density threshold; Comparing the abnormal comprehensive evaluation coefficient with a preset comprehensive evaluation coefficient threshold; When the abnormal comprehensive evaluation coefficient does not exceed the preset comprehensive evaluation coefficient threshold, the data abnormality risk of the time period in which the abnormal comprehensive evaluation coefficient does not exceed the preset comprehensive evaluation coefficient threshold is determined to be low risk; When the abnormal comprehensive evaluation coefficient exceeds the preset comprehensive evaluation coefficient threshold, the data abnormality risk of the time period in which the abnormal comprehensive evaluation coefficient exceeds the preset comprehensive evaluation coefficient threshold is determined to be medium risk; The data sources corresponding to the medium-risk time period are marked with data anomaly risk.

[0013] Preferably, the analyzing and predicting the extracted characteristic data and generating warning information according to the results of the analysis and prediction specifically include: Establish an analysis and prediction model and preset warning values ​​for temperature, humidity and air quality at garbage transfer stations; Input the extracted feature data into the analysis and prediction model; Use the analysis and prediction model to analyze and predict the temperature, humidity and air quality of the garbage transfer station, and output the analysis and prediction results; Compare the analysis and prediction results with the preset warning values ​​of temperature, humidity and air quality at the garbage transfer station; When the analysis and prediction results exceed or approach the preset warning values ​​of temperature, humidity and air quality of the garbage transfer station, a warning message is generated.

[0014] Preferably, the manager remotely controls the start and stop of the equipment of the garbage transfer station and adjusts the operating parameters of the equipment according to the early warning information, specifically including: When the warning information is the ambient temperature, the temperature change rate is calculated based on all the collected temperature data, and the operating parameters of the temperature control equipment are adjusted based on the temperature change rate and the predicted trend; When the warning information is the ambient humidity, the humidity change rate is calculated based on all the collected humidity data, and the operating parameters of the humidity control equipment are adjusted based on the humidity change rate and the predicted trend; When the warning information is air quality, all pollutant concentration parameters in the air of the garbage transfer station are integrated, including the parameters of hydrogen sulfide, ammonia, sulfur dioxide, nitrogen dioxide, trimethylamine, methyl mercaptan and methyl sulfide, to calculate the air quality index. According to the air quality index and predicted trends, the operating parameters of the air purification equipment are adjusted.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The present invention realizes intelligent monitoring of the environment of the garbage transfer station by analyzing and processing the collected data, adopts the Internet of Things technology to connect the management terminal with the sensor in the garbage transfer station, realizes data sharing, and reduces energy consumption, and realizes all-round intelligent monitoring of the environment of the garbage transfer station by real-time location tracking of the user terminal combined with intelligent algorithm analysis. By predicting and analyzing the temperature, humidity and air quality in the garbage transfer station, it can help managers understand the changing trends of environmental conditions in the garbage transfer station in advance, so as to reasonably arrange the time and frequency of garbage collection, transportation and treatment, keep the environment in the transfer station stable, and improve the quality of life of surrounding residents. Through predictive analysis, managers can more accurately grasp the changes in environmental conditions in the garbage transfer station, discover potential safety hazards in advance, and take corresponding preventive measures to ensure the safe operation of the garbage transfer station. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of an environmental monitoring method based on the Internet of Things of the present invention; Figure 2 This is a specific process of step S3 of an environmental monitoring method based on the Internet of Things of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] In order to solve the problem that the existing technology can only monitor the gas during actual use, the changes in ambient temperature and humidity will directly affect the activity of microorganisms and the fermentation process of garbage. If these parameters are not monitored and controlled, it is easy to cause excessive fermentation of garbage, produce odor and harmful gases, and pollute the environment. Please refer to Figure 1-Figure 2 , this embodiment provides the following technical solutions: An environmental monitoring method based on the Internet of Things, the environmental monitoring method comprising: Sensors installed in garbage transfer stations are used to collect temperature, humidity and air quality data in real time and perform pre-processing; The pre-processed data is integrated and uploaded to the cloud server. The cloud server stores the received data and processes the stored data to determine whether the data quality meets the standards, including: According to the time series, the thresholds of the collection results at different times are set. When a data point is not within the range of the lower abnormal threshold and the upper abnormal threshold, it is judged as an abnormal data point. When the proportion of abnormal data points is greater than the proportion threshold of the time period, the data at that time is judged to be an abnormal value, and the data quality of the corresponding time period does not meet the standard; When the proportion of abnormal data points is not greater than the proportion threshold of the time period, the normal data point closest to the collection time before and after the collection time corresponding to each abnormal data point is used as the reference data point; Calculate the angle of the line connecting the abnormal data point and the reference data point on the data point distribution diagram, and obtain the abnormal coefficient using the data value of the abnormal data point, the line angle and the data value of the corresponding reference data point; The quantitative relationship between the abnormal coefficient and the preset abnormal coefficient threshold is used to make a preliminary judgment on the data abnormality risk of the time period; After the processing is completed, feature data is extracted, the extracted feature data is analyzed and predicted, warning information is generated based on the results of the analysis and prediction, and the real-time location of the management personnel is obtained; The early warning information is automatically sent to the terminal of the manager closest to the garbage transfer station. The manager remotely controls the start and stop of the equipment in the garbage transfer station and adjusts the operating parameters of the equipment based on the early warning information.

[0019] By deploying sensors in the garbage transfer station, the temperature, humidity, and air quality data in the garbage transfer station are collected and uploaded to the cloud server in real time. By analyzing and processing these data, the intelligent monitoring of the garbage transfer station environment is realized. By connecting various sensors to the Internet, various environmental parameter data are collected and processed in real time. By using the Internet of Things technology, the management personnel terminal is connected to the sensors in the garbage transfer station to achieve data sharing and reduce energy consumption. By tracking the real-time location of the user terminal and combining intelligent algorithm analysis, all-round intelligent monitoring of the garbage transfer station environment is realized.

[0020] The preprocessed data is integrated, including: The error covariance matrix of the model is set, and a Kalman filter model suitable for the fusion of temperature, humidity and air quality data is constructed based on the real-time collected temperature, humidity and air quality data of the garbage transfer station; The pre-processed temperature, humidity and air quality data are input into the Kalman filter model; The Kalman filter model predicts and corrects data through a recursive algorithm to obtain accurate estimates; During the data fusion process, the Kalman filter assigns corresponding weights according to the uncertainty of each sensor data to obtain the optimal fusion data result.

[0021] The fusion transmission of temperature, humidity and air quality data of garbage transfer stations can realize comprehensive monitoring of the transfer station environment and improve the environmental protection and efficiency of garbage treatment. First of all, temperature, humidity and air quality are key indicators for evaluating the environmental conditions of garbage transfer stations. By real-time monitoring of these data, we can timely understand the environmental conditions in the transfer station, so as to take corresponding measures to improve and optimize the environment. Secondly, the fusion transmission of data helps to realize the intelligent management of transfer stations. By integrating temperature, humidity and air quality data into cloud servers, comprehensive monitoring and early warning of the transfer station environment can be realized. Once the data exceeds the preset range, it can automatically trigger an alarm to remind management personnel to take timely measures to avoid adverse effects of environmental deterioration on surrounding residents and staff. The fusion transmission of temperature, humidity and air quality data of garbage transfer stations can not only realize comprehensive monitoring and early warning of the transfer station environment, but also provide data support for the optimization design and transformation of transfer stations, thereby promoting the environmental protection transformation of garbage treatment and improving transfer efficiency.

[0022] Step S3 specifically includes: The temperature, humidity and air quality data in the garbage transfer station that have been integrated are stored in the order of collection time; Process the stored data, remove invalid data, and determine whether the data quality meets the standards; During the data processing process, the original data and processed data are backed up to prevent data loss or damage; Analyze the processed data, calculate the basic standard deviation to obtain the overall characteristics of the data, analyze the correlation and trend between the data based on the overall characteristics of the data, and extract feature data based on the correlation and trend between the data.

[0023] By analyzing temperature and humidity data, the schedule of garbage collection and removal can be optimized. For example, in high temperature and high humidity weather, the frequency of garbage collection and removal can be appropriately increased to prevent garbage corruption and odor. Air quality data can be used to monitor the environmental conditions around the garbage transfer station, promptly discover and deal with possible environmental pollution problems, and ensure the smooth progress of the garbage disposal process. Real-time temperature and humidity data can help managers monitor the environmental conditions in the garbage transfer station and take timely measures to improve the environment, such as starting the ventilation system or deodorization equipment to reduce the impact on surrounding residents. Air quality data can be used as an important indicator to evaluate the management effect of the garbage transfer station, help management formulate and adjust management strategies, and improve the overall management level. By analyzing temperature and humidity data, the trend of garbage corruption and odor generation can be predicted, and measures can be taken in advance to intervene and prevent the occurrence of environmental pollution. Real-time monitoring of air quality data helps to promptly discover and deal with air pollution problems around the garbage transfer station and protect the health and living environment of surrounding residents.

[0024] Determine whether the data quality meets the standards, including: According to the time series, the thresholds of the collected results at different times are set to determine whether the collected data is discontinuous in the time series; when the collected data is not discontinuous in the time series, the collected data is divided into multiple time periods; Determine whether the data points in each time period are within the range of the lower abnormal threshold and the upper abnormal threshold; When the data point is not within the range, it is judged as an abnormal data point, and when the data point is within the range, it is judged as a normal data point; Analyze the proportion of abnormal data points to the total data points. When the proportion of abnormal data points is greater than the proportion threshold of the time period, the data at that time is determined to be an abnormal value. When the result of the corresponding time period is determined to be an abnormal value, the data quality of the corresponding time period is determined to be substandard, and the substandard data is processed.

[0025] Specifically, the determination of whether the quality of the data meets the standards further includes: When the proportion of abnormal data points is not greater than the proportion threshold of the time period, extract the data value corresponding to each abnormal data point and the data value corresponding to the normal data point in the time period; Generate a data point distribution graph with the time axis corresponding to the data collection moment as the horizontal axis and the data value corresponding to the abnormal data point as the vertical axis; Extract the normal data point closest to the collection time before and after the collection time corresponding to each abnormal data point, and use the normal data point closest to the collection time before and after the collection time corresponding to each abnormal data point as the reference data point; Extract the data value of the reference data point corresponding to each abnormal data point; Obtaining a connection angle between the abnormal data point and the reference data point on a data point distribution diagram using the data value of the abnormal data point and the data value of the corresponding reference data point; Obtaining an abnormal coefficient of each abnormal data point using the data value of each abnormal data point, the connection angle and the data value of the corresponding reference data point; The abnormal coefficient is obtained by the following formula: ; Among them, Y represents the abnormal coefficient; X b Indicates the numerical standard deviation of all normal data points contained in the time period; X yb represents the numerical standard deviation of all abnormal data points contained in the time period; N represents the number of abnormal data points contained in the time period; X yi represents the data value corresponding to the i-th abnormal data point contained in the time period; X 01i Indicates the data value of the normal data point closest to the previous collection time corresponding to the abnormal data point; X 02i Indicates the data value of the normal data point whose collection time is closest to the abnormal data point; D yi represents the data collection time corresponding to the i-th abnormal data point contained in the time period; D 01i The data collection time corresponding to the abnormal data point is the data collection time corresponding to the nearest normal data point before the previous collection time; D 02i Indicates that the collection time corresponding to the abnormal data point is the data collection time corresponding to the nearest normal data point after the collection time; A primary determination is made on the data anomaly risk of a time period using a quantitative relationship between the anomaly coefficient and a preset anomaly coefficient threshold, and a secondary determination is made on the data anomaly risk of the time period when the data anomaly risk of the time period does not meet the primary determination requirement.

[0026] The technical effect of the above technical solution is: by setting the comparison between the ratio of abnormal data points and the time period ratio threshold, the abnormal data points that need to be analyzed can be accurately screened out, avoiding inefficient analysis or misjudgment caused by too many data points. Extracting abnormal data points and their corresponding reference data points (i.e., the nearest normal data points with a collection time before and a collection time after) provides an accurate data basis for subsequent calculation of abnormal coefficients. Generating a data point distribution graph with the data collection time as the horizontal axis and the abnormal data point data value as the vertical axis can intuitively display the distribution of abnormal data points in the time series, which helps to quickly identify patterns or trends of data anomalies.

[0027] By calculating the angle of the line connecting the abnormal data point and the reference data point on the data point distribution diagram, and using the data value of the abnormal data point, the angle of the line and the data value of the corresponding reference data point to obtain the abnormal coefficient, a quantitative evaluation of the abnormal degree of the abnormal data point is achieved. The calculation formula of the abnormal coefficient comprehensively considers the numerical standard deviation of the normal data point and the abnormal data point, the number of abnormal data points and the relationship between the abnormal data point and the reference data point, making the calculation of the abnormal coefficient more comprehensive and accurate. It effectively improves the accuracy and response sensitivity of the abnormal coefficient in evaluating the abnormal degree of the abnormal data point.

[0028] At the same time, the quantitative relationship between the anomaly coefficient and the preset anomaly coefficient threshold is used to make a primary judgment on the data anomaly risk of the time period, which can quickly screen out the time period that may have anomaly risks, thereby improving the efficiency and accuracy of data anomaly detection. When the primary judgment does not meet the requirements, a secondary judgment is made to further ensure the reliability and accuracy of the data anomaly risk judgment. This technical solution is not only applicable to anomaly detection of a single data source or a single time period, but can also be expanded to anomaly detection of multiple data sources or multiple time periods according to actual needs, and has strong adaptability and flexibility.

[0029] In summary, the technical effects of this technical solution in terms of performance indicators are mainly reflected in the accurate identification of abnormal data points, intuitive display of data distribution, quantitative assessment of the degree of abnormality, efficient determination of data anomaly risks and strong adaptability, etc., providing an effective and reliable method for data anomaly detection.

[0030] Specifically, the data anomaly risk of the time period is initially determined by using the quantitative relationship between the anomaly coefficient and the preset anomaly coefficient threshold, and when the data anomaly risk of the time period does not meet the primary determination requirements, the data anomaly risk of the time period is secondary determined, specifically including: Comparing the abnormal coefficient with a preset abnormal coefficient threshold; When the abnormal coefficient is lower than the preset abnormal coefficient threshold, the data abnormality risk of the time period corresponding to the abnormal coefficient being lower than the preset abnormal coefficient threshold is determined to be low risk; When the abnormal coefficient is not lower than the preset abnormal coefficient threshold, the data abnormality risk of the time period corresponding to the abnormal coefficient being not lower than the preset abnormal coefficient threshold is determined.

[0031] When the abnormal coefficient is not lower than the preset abnormal coefficient threshold, the distribution density of the abnormal data points in the time period is retrieved; The distribution density of abnormal data points in the time period is obtained by the following formula: ; Where P represents the distribution density of abnormal data points in a time period; N represents the number of abnormal data points in the time period; R t Indicates the length of time corresponding to the time period; D i represents the data collection time corresponding to the ith abnormal data point; D i+1 Indicates the data collection time corresponding to the i+1th abnormal data point; The data anomaly risk of the time period is determined by using the distribution density of the abnormal data points in the time period and the abnormal coefficient corresponding to the time period.

[0032] The technical effect of the above technical solution is: by comparing the abnormal coefficient with the preset abnormal coefficient threshold, the data abnormal risk level of the time period can be preliminarily determined. This method combines statistical analysis and threshold judgment to improve the accuracy of risk judgment. When the abnormal coefficient is not lower than the preset threshold, the distribution density of abnormal data points in the time period is further retrieved for secondary judgment. This multi-level and multi-angle judgment method further enhances the accuracy of risk identification. The preset abnormal coefficient threshold can be adjusted according to different application scenarios and requirements, so that the technical solution can flexibly adapt to different data anomaly detection requirements. When the primary judgment does not meet the requirements, the secondary judgment is made by introducing the distribution density of abnormal data points, which provides an additional judgment dimension and increases the flexibility and comprehensiveness of the judgment process. By calculating the distribution density of abnormal data points in the time period, the degree of aggregation of abnormal data points in the time series can be quantified, which helps to identify the distribution pattern and trend of abnormal data. This distribution density calculation method combines the number of abnormal data points and the collection time, provides a basis for the visualization of data abnormality risk, and makes the risk judgment result more intuitive and easy to understand. The primary judgment can quickly obtain the risk level through a simple threshold comparison, which improves the judgment efficiency. This technical solution is not only applicable to data anomaly detection in a single time period, but can also be extended to data anomaly detection in multiple time periods or from different data sources, and has strong adaptability. By introducing the distribution density of abnormal data points for secondary judgment, the robustness of the technical solution for complex data sets is enhanced, enabling it to better cope with various data anomalies.

[0033] To sum up, the technical effects of this technical solution in terms of performance indicators are mainly reflected in the improvement of risk judgment accuracy, the enhancement of risk judgment flexibility, the visualization of the distribution of abnormal data points, the improvement of judgment efficiency, and the enhancement of adaptability and robustness, etc., providing an efficient, accurate and flexible method for data anomaly detection.

[0034] Specifically, the data anomaly risk of the time period is determined by using the distribution density of the abnormal data points in the time period and the abnormal coefficient corresponding to the time period, which specifically includes: Comparing the distribution density of the abnormal data points in the time period with a preset distribution density threshold; When the distribution density of abnormal data points in the time period exceeds a preset distribution density threshold, the data abnormality risk of the time period corresponding to the distribution density exceeding the preset distribution density threshold is determined to be high risk; The data quality in high-risk time periods is considered substandard and the substandard data is processed; When the distribution density of the abnormal data points in the time period does not exceed the preset distribution density threshold, the abnormal coefficient and distribution density corresponding to the time period are retrieved; Using a preset abnormal coefficient reference value and a preset distribution density reference value to perform standardization processing on the abnormal coefficient and the distribution density, respectively, to obtain the abnormal coefficient and the distribution density after the standardization processing; Obtaining the abnormal comprehensive evaluation coefficient corresponding to the time period using the abnormal coefficient and distribution density after the normalization process; The abnormal comprehensive evaluation coefficient is obtained by the following formula: ; Among them, Z represents the abnormal comprehensive evaluation coefficient; Y t represents the abnormal coefficient after standardized processing; Y y Indicates the preset abnormal coefficient threshold; P t represents the distribution density after standardization; P y Indicates the preset distribution density threshold; Comparing the abnormal comprehensive evaluation coefficient with a preset comprehensive evaluation coefficient threshold; When the abnormal comprehensive evaluation coefficient does not exceed the preset comprehensive evaluation coefficient threshold, the data abnormality risk of the time period in which the abnormal comprehensive evaluation coefficient does not exceed the preset comprehensive evaluation coefficient threshold is determined to be low risk; When the abnormal comprehensive evaluation coefficient exceeds the preset comprehensive evaluation coefficient threshold, the data abnormality risk of the time period in which the abnormal comprehensive evaluation coefficient exceeds the preset comprehensive evaluation coefficient threshold is determined to be medium risk; The data sources corresponding to the medium-risk time period are marked with data anomaly risk.

[0035] The technical effect of the above technical solution is: by combining the distribution density and abnormal coefficient of abnormal data points, a refined judgment of the abnormal risk of data in a time period is achieved. This method not only considers the number of abnormal data points, but also considers their distribution in the time series, thereby improving the accuracy and comprehensiveness of risk judgment. Three levels of high risk, medium risk and low risk are set, making the judgment results of data abnormality risk clearer and easier to understand. At the same time, different treatment measures are taken for different risk levels, such as treating the data quality of the high-risk time period as substandard and processing it, and marking the data source of the medium-risk time period as abnormal risk, which is helpful for subsequent data management and risk control. The abnormal coefficient and distribution density are standardized to eliminate the dimensional differences that may exist between different time periods or different data sources, making the judgment results more objective and accurate. The introduction of the abnormal comprehensive evaluation coefficient comprehensively considers the two factors of abnormal coefficient and distribution density, and realizes a comprehensive assessment of data abnormality risk. This comprehensive evaluation method helps to more accurately identify potential data problems and improve data quality. The thresholds in this technical solution (such as distribution density threshold, anomaly coefficient threshold, and comprehensive evaluation coefficient threshold) can be adjusted according to actual application scenarios and requirements, making the technical solution highly flexible and scalable. At the same time, this technical solution can also be applied to data anomaly detection in different data sources and different time periods, and has good versatility. For time periods determined to be high-risk, their data quality is immediately considered substandard and processed, which helps to promptly eliminate the impact of data anomalies on subsequent analysis or decision-making. At the same time, marking the data source in the medium-risk time period with abnormal risks also facilitates subsequent data monitoring and management.

[0036] In summary, this technical solution combines the distribution density and anomaly coefficient of abnormal data points to achieve refined judgment and comprehensive assessment of data anomaly risks, improving the accuracy and comprehensiveness of risk judgment. At the same time, this technical solution is also flexible and scalable, suitable for data anomaly detection in different data sources and different time periods, and provides strong support for data quality management.

[0037] Processing of data that does not meet the standards includes: Correct the data source of substandard data to ensure the accuracy of subsequent data, and clean, transform and supplement the data to restore its quality; After the correction of the substandard data is completed, the processed data is verified to ensure that its quality has met the standards and to determine whether the errors, anomalies or incomplete information identified during the data correction process have been correctly corrected; When errors, anomalies or incomplete information in the judgment data are correctly corrected, it means that the data quality has met the standards.

[0038] Analyze and predict the extracted feature data, and generate warning information based on the results of the analysis and prediction, including: Establish an analysis and prediction model and preset warning values ​​for temperature, humidity and air quality at garbage transfer stations; Input the extracted feature data into the analysis and prediction model; Use the analysis and prediction model to analyze and predict the temperature, humidity and air quality of the garbage transfer station, and output the analysis and prediction results; Compare the analysis and prediction results with the preset warning values ​​of temperature, humidity and air quality at the garbage transfer station; When the analysis and prediction results exceed or approach the preset warning values ​​of temperature, humidity and air quality of the garbage transfer station, a warning message is generated.

[0039] By predicting and analyzing the temperature, humidity, and air quality in the garbage transfer station, managers can understand the changing trends of environmental conditions in the garbage transfer station in advance, so as to reasonably arrange the time and frequency of garbage collection, transportation, and treatment. For example, under high temperature and high humidity conditions, garbage may rot faster and produce odor. Through predictive analysis, the number of garbage collection and treatment can be increased in a timely manner to reduce the risk of environmental pollution. Appropriate temperature and humidity conditions can prevent garbage from rotting too quickly and reduce the emission of harmful gases, thereby improving the air quality of the garbage transfer station and its surrounding areas. Predictive analysis can guide managers to take necessary regulatory measures, such as ventilation, humidification or dehumidification, to maintain the environment in the transfer station. Stability, improve the quality of life of surrounding residents. Through predictive analysis, managers can more accurately grasp the changes in environmental conditions in the garbage transfer station, so as to reasonably allocate human, material and financial resources. For example, when extreme weather conditions are predicted, the frequency of cleaning and maintenance of equipment can be increased in advance to ensure the normal operation of the equipment, or the garbage transfer route can be adjusted according to the air quality prediction results to avoid secondary pollution to the environment. Unsuitable temperature and humidity conditions may cause safety accidents, such as mold growth and circuit short circuit caused by excessive humidity. Through predictive analysis, managers can discover potential safety hazards in advance and take corresponding preventive measures to ensure the safe operation of the garbage transfer station.

[0040] Establish an analytical prediction model, including: Use feature selection algorithms to extract feature data that affect temperature, humidity, and air quality at garbage transfer stations; Select a time series model and train the time series model using the extracted feature data; After the training is completed, the performance of the trained model is evaluated through the cross-validation method, and the model is optimized according to the evaluation results to obtain the analytical prediction model.

[0041] Based on the early warning information, the management personnel remotely control the start and stop of the equipment at the garbage transfer station and adjust the operating parameters of the equipment, including: When the warning information is the ambient temperature, the temperature change rate is calculated based on all the collected temperature data, and the operating parameters of the temperature control equipment are adjusted based on the temperature change rate and the predicted trend; When the warning information is the ambient humidity, the humidity change rate is calculated based on all the collected humidity data, and the operating parameters of the humidity control equipment are adjusted based on the humidity change rate and the predicted trend; When the warning information is air quality, all pollutant concentration parameters in the air of the garbage transfer station are integrated, including the parameters of hydrogen sulfide, ammonia, sulfur dioxide, nitrogen dioxide, trimethylamine, methyl mercaptan and methyl sulfide, to calculate the air quality index. According to the air quality index and predicted trends, the operating parameters of the air purification equipment are adjusted.

[0042] In summary, the present invention is an environmental monitoring method based on the Internet of Things. By deploying sensors in the garbage transfer station, the temperature, humidity, and air quality data in the garbage transfer station are collected and uploaded to the cloud server in real time, and the collected data are analyzed and processed to realize intelligent monitoring of the garbage transfer station environment. By connecting various sensors to the Internet, various environmental parameter data are collected and processed in real time. The Internet of Things technology is used to connect the management terminal with the sensor in the garbage transfer station to realize data sharing and reduce energy consumption. By tracking the real-time position of the user terminal and combining it with intelligent algorithm analysis, all-round intelligent monitoring of the environment of the garbage transfer station is realized. By predicting and analyzing the temperature, humidity, and air quality in the garbage transfer station, it can help managers understand the changing trends of environmental conditions in the garbage transfer station in advance, thereby reasonably arranging the time and frequency of garbage collection, transportation, and treatment, maintaining the stability of the environment in the transfer station, and improving the quality of life of surrounding residents. Through predictive analysis, managers can more accurately grasp the changes in environmental conditions in the garbage transfer station, can discover potential safety hazards in advance, and take corresponding preventive measures to ensure the safe operation of the garbage transfer station.

[0043] 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.

[0044] 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.

Claims

1. An environmental monitoring method based on the Internet of Things, characterized in that: The environmental monitoring method comprises: Sensors installed in garbage transfer stations are used to collect temperature, humidity and air quality data in real time, and the pre-processed data is integrated and uploaded to the cloud server for storage; The quality of the stored data is judged, and when the judgment result is that the proportion of abnormal data points is not greater than the proportion threshold of the time period, the abnormal coefficient of each abnormal data point is obtained; The data anomaly risk of the time period is initially determined by using the quantitative relationship between the anomaly coefficient and the preset anomaly coefficient threshold, and the data anomaly risk of the time period is secondarily determined based on the determination result; After the processing is completed, feature data is extracted, the extracted feature data is analyzed and predicted, warning information is generated based on the results of the analysis and prediction, and the real-time location of the management personnel is obtained; The early warning information is automatically sent to the terminal of the manager closest to the garbage transfer station. The manager remotely controls the start and stop of the equipment in the garbage transfer station and adjusts the operating parameters of the equipment based on the early warning information.

2. The method for environmental monitoring based on the Internet of Things according to claim 1, characterized in that: The judging of the quality of the stored data specifically includes: According to the time series, the thresholds of the collected results at different times are set to determine whether the collected data is discontinuous in the time series; When the collected data do not show discontinuities in the time series, the collected data are divided into multiple time periods; Determine whether the data points in each time period are within the range of the lower abnormal threshold and the upper abnormal threshold; When the data point is not within the range, it is judged as an abnormal data point, and when the data point is within the range, it is judged as a normal data point; Analyze the proportion of abnormal data points to the total data points. When the proportion of abnormal data points is greater than the proportion threshold of the time period, the data at that time is determined to be an abnormal value. When the result of the corresponding time period is determined to be an abnormal value, the data quality of the corresponding time period is determined to be substandard, and the substandard data is processed.

3. The method for environmental monitoring based on the Internet of Things according to claim 1, characterized in that: When the proportion of abnormal data points is not greater than the proportion threshold of the time period, obtaining the abnormal coefficient of each abnormal data point specifically includes: When the proportion of abnormal data points is not greater than the proportion threshold of the time period, extract the data value corresponding to each abnormal data point and the data value corresponding to the normal data point in the time period; Generate a data point distribution graph with the time axis corresponding to the data collection moment as the horizontal axis and the data value corresponding to the abnormal data point as the vertical axis; Extract the normal data point closest to the collection time before and after the collection time corresponding to each abnormal data point, and use the normal data point closest to the collection time before and after the collection time corresponding to each abnormal data point as the reference data point; Extract the data value of the reference data point corresponding to each abnormal data point; Obtaining a connection angle between the abnormal data point and the reference data point on a data point distribution diagram using the data value of the abnormal data point and the data value of the corresponding reference data point; Obtaining an abnormal coefficient of each abnormal data point using the data value of each abnormal data point, the connection angle and the data value of the corresponding reference data point; The abnormal coefficient is obtained by the following formula: ； Among them, Y represents the abnormal coefficient; X b Indicates the numerical standard deviation of all normal data points contained in the time period; X yb represents the numerical standard deviation of all abnormal data points contained in the time period; N represents the number of abnormal data points contained in the time period; X yi represents the data value corresponding to the i-th abnormal data point contained in the time period; X 01i Indicates the data value of the normal data point closest to the previous collection time corresponding to the abnormal data point; X 02i Indicates the data value of the normal data point whose collection time is closest to the abnormal data point; D yi represents the data collection time corresponding to the i-th abnormal data point contained in the time period; D 01i The data collection time corresponding to the abnormal data point is the data collection time corresponding to the nearest normal data point before the previous collection time; D 02i It indicates that the collection time corresponding to the abnormal data point is the data collection time corresponding to the nearest normal data point after the collection time.

4. The method for environmental monitoring based on the Internet of Things according to claim 1, characterized in that: The method of performing a primary determination on the data abnormality risk of a time period by using the quantitative relationship between the abnormal coefficient and a preset abnormal coefficient threshold, and performing a secondary determination on the data abnormality risk of the time period according to the determination result, specifically includes: Comparing the abnormal coefficient with a preset abnormal coefficient threshold; When the abnormal coefficient is lower than the preset abnormal coefficient threshold, the data abnormality risk of the time period corresponding to the abnormal coefficient being lower than the preset abnormal coefficient threshold is determined to be low risk; When the abnormal coefficient is not lower than the preset abnormal coefficient threshold, the data abnormality risk of the time period corresponding to the abnormal coefficient being not lower than the preset abnormal coefficient threshold is determined; When the abnormal coefficient is not lower than the preset abnormal coefficient threshold, the distribution density of the abnormal data points in the time period is retrieved.

5. The method for environmental monitoring based on the Internet of Things according to claim 4, characterized in that: The distribution density of abnormal data points in the time period is obtained by the following formula: ； Where P represents the distribution density of abnormal data points in a time period; N represents the number of abnormal data points in the time period; R t Indicates the length of time corresponding to the time period; D i represents the data collection time corresponding to the i-th abnormal data point; D i+1 Indicates the data collection time corresponding to the i+1th abnormal data point; The data anomaly risk of the time period is determined by using the distribution density of the abnormal data points in the time period and the abnormal coefficient corresponding to the time period.

6. The method for environmental monitoring based on the Internet of Things according to claim 5, characterized in that: The data anomaly risk of the time period is determined by using the distribution density of the abnormal data points in the time period and the abnormal coefficient corresponding to the time period, specifically including: Comparing the distribution density of the abnormal data points in the time period with a preset distribution density threshold; When the distribution density of abnormal data points in the time period exceeds a preset distribution density threshold, the data abnormality risk of the time period corresponding to the distribution density exceeding the preset distribution density threshold is determined to be high risk; The data quality in high-risk time periods is considered substandard and the substandard data is processed; When the distribution density of the abnormal data points in the time period does not exceed the preset distribution density threshold, the abnormal coefficient and distribution density corresponding to the time period are retrieved; Using a preset abnormal coefficient reference value and a preset distribution density reference value to perform standardization processing on the abnormal coefficient and the distribution density, respectively, to obtain the abnormal coefficient and the distribution density after the standardization processing; The abnormal comprehensive evaluation coefficient corresponding to the time period is obtained by using the abnormal coefficient and distribution density after the standardization process.

7. The method for environmental monitoring based on the Internet of Things according to claim 6, characterized in that: The abnormal comprehensive evaluation coefficient is obtained by the following formula: ； Among them, Z represents the abnormal comprehensive evaluation coefficient; Y t represents the abnormal coefficient after standardization; Y y Indicates the preset abnormal coefficient threshold; P t represents the distribution density after standardization; P y Indicates the preset distribution density threshold; Comparing the abnormal comprehensive evaluation coefficient with a preset comprehensive evaluation coefficient threshold; When the abnormal comprehensive evaluation coefficient does not exceed the preset comprehensive evaluation coefficient threshold, the data abnormality risk of the time period in which the abnormal comprehensive evaluation coefficient does not exceed the preset comprehensive evaluation coefficient threshold is determined to be low risk; When the abnormal comprehensive evaluation coefficient exceeds the preset comprehensive evaluation coefficient threshold, the data abnormality risk of the time period in which the abnormal comprehensive evaluation coefficient exceeds the preset comprehensive evaluation coefficient threshold is determined to be medium risk; The data sources corresponding to the medium-risk time period are marked with data anomaly risk.

8. The method for environmental monitoring based on the Internet of Things according to claim 1, characterized in that: The analysis and prediction of the extracted characteristic data and the generation of warning information according to the results of the analysis and prediction specifically include: Establish an analysis and prediction model and preset warning values ​​for temperature, humidity and air quality at garbage transfer stations; Input the extracted feature data into the analysis and prediction model; Use the analysis and prediction model to analyze and predict the temperature, humidity and air quality of the garbage transfer station, and output the analysis and prediction results; Compare the analysis and prediction results with the preset warning values ​​of temperature, humidity and air quality at the garbage transfer station; When the analysis and prediction results exceed or approach the preset warning values ​​of temperature, humidity and air quality of the garbage transfer station, a warning message is generated.

9. The method for environmental monitoring based on the Internet of Things according to claim 1, characterized in that: The manager remotely controls the start and stop of the equipment at the garbage transfer station and adjusts the operating parameters of the equipment according to the early warning information, including: When the warning information is the ambient temperature, the temperature change rate is calculated based on all the collected temperature data, and the operating parameters of the temperature control equipment are adjusted based on the temperature change rate and the predicted trend; When the warning information is the ambient humidity, the humidity change rate is calculated based on all the collected humidity data, and the operating parameters of the humidity control equipment are adjusted based on the humidity change rate and the predicted trend; When the warning information is air quality, all pollutant concentration parameters in the air of the garbage transfer station are integrated, including the parameters of hydrogen sulfide, ammonia, sulfur dioxide, nitrogen dioxide, trimethylamine, methyl mercaptan and methyl sulfide, to calculate the air quality index. According to the air quality index and predicted trends, the operating parameters of the air purification equipment are adjusted.

Images