Monitoring method and system based on Internet of Things architecture

Abstract

The invention relates to the technical field of Internet of Things monitoring, and particularly discloses a monitoring method and system based on an Internet of Things architecture, and the method comprises the steps: collecting environment data in real time through deploying a plurality of temperature and humidity sensors in a monitoring region, and transmitting the data to a central processing unit or a cloud end through a wireless network for storage and preliminary processing; the system establishes a prediction model by fitting historical data, evaluates the accuracy of sensor data, and calibrates or replaces an abnormal sensor to ensure the reliability of the data; the system comprehensively analyzes the calibrated sensor data, calculates a temperature abnormal coefficient and a humidity abnormal coefficient, and evaluates the overall environment condition of the monitoring area; when an abnormal condition is detected, the system immediately starts an early warning mechanism, sends alarm information to a monitoring center or related personnel, and records the detailed condition of the abnormal event for subsequent analysis and processing.

Description

Technical Field

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

[0002] The monitoring method of the Internet of Things architecture has been widely used in various fields. Such systems are usually composed of multiple sensors distributed in the monitoring area, and the collected data is transmitted to the central processing unit or cloud server for analysis and processing through wireless communication technology; although such systems have achieved real-time monitoring of environmental parameters to a certain extent, there are still some shortcomings in practical applications.

[0003] The existing monitoring system lacks an effective quality control mechanism for data collection. Over time, sensors may cause data drift or errors due to environmental factors, equipment aging, etc., and the existing system often cannot detect and correct these problems in a timely manner, resulting in inaccurate data collection and affecting monitoring results. There is a lack of comprehensive analysis of calibrated sensor data to determine whether there are any abnormal conditions in the monitored area, and to conduct intelligent early warning processing on this basis to ensure that response measures are taken in the first place to reduce the impact of potential risks. Summary of the invention

[0004] The purpose of the present invention is to provide a monitoring method and system based on the Internet of Things architecture to solve the problems in the above background.

[0005] The purpose of the present invention can be achieved by the following technical solutions: A monitoring method based on the Internet of Things architecture comprises the following steps: S1: Deploy multiple temperature sensors and humidity sensors in the monitoring area. Collect temperature and humidity data of the monitoring area in real time through the temperature sensors and humidity sensors according to the time series and record them as actual values. S2: Obtain historical temperature data and humidity data of the monitored area, fit the historical temperature data and humidity data, establish a prediction model, and predict the current temperature data and humidity data, which are recorded as predicted values; S3: Compare and analyze the actual value with the predicted value, calculate the error coefficient, and evaluate the accuracy of the data collected by the temperature sensor and humidity sensor; S4: According to the evaluation results, the temperature sensor and the humidity sensor are divided into normal sensors and abnormal sensors, and the abnormal sensors are calibrated; S5: Based on the calibrated temperature sensor and humidity sensor, re-collect the temperature data and humidity data according to the time series, and conduct a comprehensive analysis of the temperature data and humidity data to determine whether there is any abnormality in the monitoring area; S6: According to the judgment result, if there is no abnormality in the monitoring area, the current monitoring state is continued; if there is an abnormality in the monitoring area, an early warning process is performed.

[0006] As a further solution of the present invention: the acquisition of historical temperature data and humidity data of the monitored area, fitting the historical temperature data and humidity data, establishing a prediction model, and predicting the current temperature data and humidity data, recorded as a predicted value, specifically includes: Get historical temperature and humidity data, all data are arranged in time series; Check the data for missing values ​​and outliers; Missing values ​​can be handled through interpolation, and outliers can be identified and adjusted through statistical methods; Unit root test was used to test the stationarity of the time series; Stabilization is performed by difference method; Use the autocorrelation and partial autocorrelation plots to determine the order of the autoregressive and moving average components and ; in, represents the number of autoregressive terms, represents the number of moving average terms; Establish the expression of ARMA model and calculate the predicted value; The calculation expression of the predicted value is: ; In the formula, Indicates time The predicted value of Indicates the number of time points corresponding to the time series, i=1, 2, ..., , represents the maximum number of autoregressive terms, j=1, 2, ..., , represents the number of moving average terms, represents the i-th autoregressive coefficient, represents the jth moving average coefficient, Indicates time Historical temperature data or humidity data, Indicates time The error term of The predicted value Used as input for the next moment to make step-by-step predictions.

[0007] As a further solution of the present invention: the comparison and analysis of the actual value and the predicted value and the calculation of the error coefficient specifically include: The temperature sensor and humidity sensor collect temperature data and humidity data in time series respectively as actual values, recorded as ; Get the predicted value at the corresponding time point , the actual value With the predicted value Conduct comparative analysis; By calculating the error between the actual value and the predicted value, the error coefficient is calculated; Wherein, the calculation expression of the error coefficient is: ; In the formula, a represents the number of real-time collection points, m represents the maximum value of the collection points, Represents the error coefficient.

[0008] As a further solution of the present invention: the step of evaluating the accuracy of data collected by the temperature sensor and the humidity sensor specifically includes: Judgment error coefficient Is it greater than or equal to the preset error coefficient threshold? If so, it is recorded as an abnormal sensor; if not, it is recorded as a normal sensor.

[0009] As a further solution of the present invention: the comprehensive analysis of temperature data and humidity data specifically includes: Process the temperature data collected in real time in the monitoring area and calculate the temperature anomaly coefficient; Process the humidity data collected in real time in the monitoring area and calculate the humidity anomaly coefficient; The temperature anomaly coefficient and humidity anomaly coefficient of the monitored area are normalized and the regional anomaly fluctuation index is calculated.

[0010] As a further solution of the present invention: the process of obtaining the temperature anomaly coefficient is: Re-collect the temperature and humidity data in the monitoring area according to the time series; A set of time series temperature data collected by each temperature sensor is recorded as a set of temperature data; Obtain the mean and standard deviation of each set of temperature data, and calculate the temperature anomaly coefficient based on the mean and standard deviation of each set of data; Wherein, the calculation expression of the temperature anomaly coefficient is: ; In the formula, Temperature anomaly coefficient, represents the average value of the temperature data of group a, represents the standard deviation of the ath group of data, a represents the number of sensors, a=1,2,...,n, n represents the maximum number of sensors.

[0011] As a further solution of the present invention: the process of obtaining the humidity anomaly coefficient is: A set of time series humidity data collected by each humidity sensor is recorded as a set of humidity data; Obtain the mean value of each group of humidity data, calculate the difference between the humidity data collected at each time point of each group of humidity data and the mean value of the corresponding group, and take the absolute value to obtain the humidity deviation value; Calculate the ratio of each humidity deviation value to the mean value of the corresponding group to obtain the humidity fluctuation ratio of the humidity data of each collection point; The humidity fluctuation ratio of each set of data is summed up and calculated to obtain the humidity anomaly ratio of each set of data; The humidity anomaly ratio of each set of humidity data is summed up and calculated to obtain the humidity anomaly coefficient of the monitored area.

[0012] As a further solution of the present invention: the determining whether there is an abnormal situation in the monitoring area specifically includes: Determine whether the regional abnormal fluctuation index is greater than or equal to the preset regional abnormal fluctuation index threshold. If so, it is recorded as the presence of an abnormal situation; if not, it is recorded as the absence of an abnormal situation.

[0013] As a further solution of the present invention: according to the judgment result, if there is no abnormality in the monitoring area, the current monitoring state is continued; if there is an abnormality in the monitoring area, an early warning process is performed, which specifically includes: If there is an abnormal situation in the monitoring area, the first-stage response procedure is immediately initiated, that is, a warning notification is sent, and an alarm signal is sent to the monitoring center through the IoT architecture; The system will activate the redundancy mechanism to ensure the continued normal operation of the monitoring area functions.

[0014] A monitoring system based on the Internet of Things architecture, comprising: A data acquisition module, wherein the data acquisition module is used to collect temperature data and humidity data of the monitoring area in real time according to a time series through a temperature sensor and a humidity sensor, and record them as actual values; A prediction model building module, which is used to obtain historical temperature data and humidity data of the monitoring area, fit the historical temperature data and humidity data, build a prediction model, and predict the current temperature data and humidity data, which are recorded as predicted values; A comparison and analysis module, which is used to compare and analyze the actual value with the predicted value, calculate the error coefficient, and evaluate the accuracy of the data collected by the temperature sensor and the humidity sensor; A sensor abnormality distinction and calibration module, wherein the sensor abnormality distinction and calibration module is used to divide the temperature sensor and the humidity sensor into normal sensors and abnormal sensors, and calibrate the abnormal sensors; A comprehensive analysis module, which is used for the calibrated temperature sensor and humidity sensor to re-collect temperature data and humidity data according to the time series, and to conduct a comprehensive analysis on the temperature data and humidity data to determine whether there is an abnormality in the monitoring area; The early warning module, according to the judgment result, continues the current monitoring state if there is no abnormal situation in the monitoring area, and performs early warning processing if there is an abnormal situation in the monitoring area.

[0015] Beneficial effects of the present invention: (1) By collecting temperature and humidity data in the monitoring area in real time and building a prediction model based on historical data, the system can effectively evaluate the working status of the sensor and promptly detect and handle abnormal conditions of the sensor. This sensor calibration or replacement mechanism based on the error coefficient not only ensures the accuracy of data collection, but also reduces the false alarm rate or missed alarm rate caused by sensor failure, thereby ensuring the stable operation of the monitoring system. Through comprehensive analysis of sensor data, the system can quickly identify the trend of environmental changes and warn of potential risks in advance, so that managers can take timely measures to prevent accidents, thereby ensuring the safety of production and life to a large extent. (2) By calculating the temperature anomaly coefficient and humidity anomaly coefficient, and further synthesizing the regional anomaly fluctuation index, the system can accurately determine whether there are any abnormal conditions in the monitored area. This comprehensive analysis method can not only identify the anomalies of a single sensor data, but also capture the overall trend of environmental changes in the entire area, thereby providing a more comprehensive risk assessment. In a production environment, if the temperature or humidity in a certain area suddenly rises, the system can promptly identify this change and determine through comprehensive analysis whether it exceeds the normal range, and then decide whether an early warning is needed. In this way, managers can take targeted preventive measures based on the system's comprehensive analysis results to prevent potential environmental problems from turning into serious safety accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The present invention will be further described below in conjunction with the accompanying drawings.

[0017] Figure 1 It is a flowchart of the specific steps of a monitoring method based on the Internet of Things architecture of the present invention; Figure 2 It is a flow chart of a monitoring system based on the Internet of Things architecture in the present invention. DETAILED DESCRIPTION

[0018] 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.

[0019] See also Figure 1 As shown, the present invention is a monitoring method based on the Internet of Things architecture, comprising the following steps: S1: Deploy multiple temperature sensors and humidity sensors in the monitoring area. Collect temperature and humidity data of the monitoring area in real time through the temperature sensors and humidity sensors according to the time series and record them as actual values. S2: Obtain historical temperature data and humidity data of the monitored area, fit the historical temperature data and humidity data, establish a prediction model, and predict the current temperature data and humidity data, which are recorded as predicted values; S3: Compare and analyze the actual value with the predicted value, calculate the error coefficient, and evaluate the accuracy of the data collected by the temperature sensor and humidity sensor; S4: According to the evaluation results, the temperature sensor and the humidity sensor are divided into normal sensors and abnormal sensors, and the abnormal sensors are calibrated; S5: Based on the calibrated temperature sensor and humidity sensor, re-collect the temperature data and humidity data according to the time series, and conduct a comprehensive analysis of the temperature data and humidity data to determine whether there is any abnormality in the monitoring area; S6: According to the judgment result, if there is no abnormality in the monitoring area, the current monitoring state is continued; if there is an abnormality in the monitoring area, an early warning process is performed.

[0020] In S1, multiple temperature sensors and humidity sensors are deployed in the monitoring area. The temperature and humidity data of the monitoring area are collected in real time through the temperature sensors and humidity sensors according to the time series. Specifically, the following are included: According to the monitoring objectives (such as climate monitoring, environmental safety, equipment operation), determine the specific areas that need to be monitored. Taking the environment of the production workshop as an example, the production workshop is used as the monitoring area; Deploy multiple temperature sensors and humidity sensors in the production workshop to collect temperature and humidity data in the workshop in real time, ensuring that the temperature sensors and humidity sensors cover the entire workshop; The location of the sensor should be chosen to avoid direct sunlight and air flow interference, and the sensors should be arranged at different heights and locations to obtain more comprehensive data. Use a bracket or other fixing device to firmly install the sensor in the selected location to ensure good contact between the sensor and the monitoring environment; Collect the temperature and humidity data of the environment in time series (e.g. every minute), and transmit the collected data to the central processing unit or cloud platform in real time through the wireless network for subsequent analysis and storage; Set up a data logging mechanism to ensure that all collected data is accurately recorded and stored for subsequent comparison and analysis.

[0021] In S2, historical temperature data and humidity data are obtained, and the historical temperature data and humidity data are fitted to establish a prediction model, and the current temperature data and humidity data are predicted and recorded as predicted values, which specifically include: Get historical temperature and humidity data, all data are arranged in time series; Check the data for missing values ​​and outliers; Missing values ​​can be handled by interpolation or forward filling, and outliers can be identified and adjusted using statistical methods (e.g., boxplots); Use unit root tests (such as ADF test) to test the stationarity of the time series; Stabilization is performed by difference method; Use the autocorrelation function (ACF) and partial autocorrelation function (PACF) plots to determine the order of the autoregressive (AR) and moving average (MA) components and ; in, represents the number of autoregressive terms, represents the number of moving average terms; Establish the expression of ARMA model and calculate the predicted value; The calculation expression of the predicted value is: ; In the formula, Indicates time The predicted value of Indicates the number of time points corresponding to the time series, i=1, 2, ..., , represents the maximum number of autoregressive terms, j=1, 2, ..., , represents the number of moving average terms, represents the i-th autoregressive coefficient, represents the jth moving average coefficient, Indicates time Historical temperature data or humidity data, Indicates time The error term of The predicted value Used as input for the next moment to make step-by-step predictions; Continue to use the model to predict multiple subsequent time points and evaluate the accuracy of the predictions to ensure the accuracy of the predictions; It should be noted that the data before time t represents historical temperature data or humidity data, and the data after time t+1 represents predicted temperature data or humidity data.

[0022] In S3, the actual value is compared with the predicted value, the error coefficient is calculated, and the accuracy of the data collected by the temperature sensor and humidity sensor is evaluated, including: The temperature sensor and humidity sensor collect temperature data and humidity data in time series respectively as actual values, recorded as ; Get the predicted value at the corresponding time point , the actual value With the predicted value Conduct comparative analysis; By calculating the error between the actual value and the predicted value, the error coefficient is calculated; Wherein, the calculation expression of the error coefficient is: ; Where a represents the number of real-time acquisition points, a=1, 2, ..., m, and m represents the maximum value of acquisition points. represents the error coefficient; It should be noted that the actual data collected by the sensor is compared with the predicted data, and the error coefficient is calculated. According to the size of the error coefficient, it is judged whether the data collection of the sensor is accurate.

[0023] In S4, according to the evaluation results, the temperature sensor and the humidity sensor are divided into normal sensors and abnormal sensors, and the abnormal sensors are calibrated, specifically including: The error coefficient comparing with a preset error coefficient threshold; If the error coefficient If the error coefficient is greater than or equal to the preset error coefficient threshold, it means that the corresponding temperature sensor or humidity sensor collects inaccurate data and is recorded as an abnormal sensor; If the error coefficient If the error is less than the preset error coefficient threshold, it means that the corresponding temperature sensor or humidity sensor collects data accurately and is recorded as a normal sensor; It should be noted that by comparing the predicted value with the actual value, the status of the sensor is monitored and evaluated in real time, and the sensor is screened to ensure the accuracy of the data collected by the sensor.

[0024] Based on abnormal sensors, adjust the sensitivity or sampling frequency of the sensor according to the data deviation of the abnormal sensor to avoid interference of noise and environmental factors on the measurement; If the sensor makes inaccurate measurements due to changes in ambient temperature, you can adjust the sensor's temperature compensation parameters to ensure data stability and reliability; If calibration and parameter adjustment still fail to effectively solve the problem, the sensor hardware may be damaged or aged; Replace the abnormal sensor and redeploy it in a suitable location to ensure that the new sensor can accurately collect data; After the replacement is complete, reinitialize the system to ensure that the new sensor operates normally and to avoid abnormal data from occurring again.

[0025] In S5, based on the calibrated temperature sensor and humidity sensor, the temperature data and humidity data are recollected in time series, and the temperature data and humidity data are comprehensively analyzed to determine whether there is any abnormality in the monitoring area, including: For calibrated temperature and humidity sensors, ensure the accuracy of data collection; Re-collect the temperature and humidity data in the monitoring area according to the time series; A set of time series temperature data collected by each temperature sensor is recorded as a set of temperature data; Obtain the mean and standard deviation of each set of temperature data, and calculate the temperature anomaly coefficient based on the mean and standard deviation of each set of data; Wherein, the calculation expression of the temperature anomaly coefficient is: ; In the formula, Temperature anomaly coefficient, represents the average value of the temperature data of group a, represents the standard deviation of the a-th group of data, a represents the number of sensors, a=1,2,...,n, n represents the maximum number of sensors; A set of time series humidity data collected by each humidity sensor is recorded as a set of humidity data; Obtain the mean value of each group of humidity data, calculate the difference between the humidity data collected at each time point of each group of humidity data and the mean value of the corresponding group, and take the absolute value to obtain the humidity deviation value; Calculate the ratio of each humidity deviation value to the mean value of the corresponding group to obtain the humidity fluctuation ratio of the humidity data of each collection point; The humidity fluctuation ratio of each set of data is summed up and calculated to obtain the humidity anomaly ratio of each set of data; The humidity anomaly ratio of each set of humidity data is summed up to obtain the humidity anomaly coefficient of the monitored area, which is recorded as ; Normalize the temperature anomaly coefficient and humidity anomaly coefficient of the monitored area, and calculate the regional anomaly fluctuation index; The calculation expression of the regional abnormal fluctuation index is: ; In the formula, is the regional abnormal fluctuation index, and is the preset scale factor, and and All are greater than 0; comparing the regional abnormal fluctuation index with a preset regional abnormal fluctuation index threshold; If the regional abnormal fluctuation index is greater than or equal to the preset regional abnormal fluctuation index threshold, it means that an abnormal situation occurs in the monitored area, which is recorded as an abnormal situation; If the regional abnormal fluctuation index is less than the preset regional abnormal fluctuation index threshold, it means that there is no environmental abnormality in the monitored area, and it is recorded as no abnormality; It should be noted that: Regional Abnormal Fluctuation Index , reflects the abnormal environment in the monitored area, and when the abnormal fluctuation index in the area The larger the value is, the higher the abnormality of the corresponding area is.

[0026] In S6, according to the judgment result, if there is no abnormality in the monitoring area, the current monitoring state is continued; if there is an abnormality in the monitoring area, an early warning process is performed.

[0027] If there is no abnormality in the monitoring area, the temperature and humidity data of the current monitoring area will continue to be monitored, and the monitoring frequency can be reduced to improve resource utilization; If there is an abnormal situation in the monitoring area, the first-stage response procedure will be immediately initiated, that is, sending an early warning notification. Through the IoT architecture, an alarm signal will be sent to the monitoring center, or an alarm message will be pushed to the mobile phones of relevant personnel. After receiving the early warning notification, relevant personnel need to take prompt action and handle it according to the preset emergency response plan; Emergency response may include dispatching staff to conduct on-site inspections, or remotely adjusting the parameters of monitoring equipment to observe abnormal conditions in more detail; At the same time, the system may also automatically record the time, location and details of the abnormality for subsequent investigation; Finally, implementation of preventive measures requires temporary closure or isolation of affected areas to protect personnel safety and reduce potential losses; The system may also activate redundancy mechanisms or switch to backup operating modes to ensure the continued operation of critical functions; The early warning handling process also includes follow-up tracking and analysis of the entire incident; After the initial response, someone needs to be responsible for collecting all relevant temperature and humidity data and conducting a comprehensive analysis to determine the cause of the anomaly and the effectiveness of its treatment.

[0028] See also Figure 2 As shown, a monitoring system based on the Internet of Things architecture includes: A data acquisition module, wherein the data acquisition module is used to collect temperature data and humidity data of the monitoring area in real time according to a time series through a temperature sensor and a humidity sensor, and record them as actual values; A prediction model building module, which is used to obtain historical temperature data and humidity data of the monitoring area, fit the historical temperature data and humidity data, build a prediction model, and predict the current temperature data and humidity data, which are recorded as predicted values; A comparison and analysis module, which is used to compare and analyze the actual value with the predicted value, calculate the error coefficient, and evaluate the accuracy of the data collected by the temperature sensor and the humidity sensor; A sensor abnormality distinction and calibration module, wherein the sensor abnormality distinction and calibration module is used to divide the temperature sensor and the humidity sensor into normal sensors and abnormal sensors, and calibrate the abnormal sensors; A comprehensive analysis module, which is used for the calibrated temperature sensor and humidity sensor to re-collect temperature data and humidity data according to the time series, and to conduct a comprehensive analysis on the temperature data and humidity data to determine whether there is an abnormality in the monitoring area; The early warning module, according to the judgment result, continues the current monitoring state if there is no abnormal situation in the monitoring area, and performs early warning processing if there is an abnormal situation in the monitoring area.

[0029] The working principle of the present invention is as follows: first, multiple temperature sensors and humidity sensors are deployed in the monitoring area to collect the temperature and humidity data of the environment in real time, and the data is transmitted to the central processing unit or cloud platform through a wireless network for storage and preliminary processing; through the time series method, the system can continuously obtain first-hand information on environmental changes, providing a basis for subsequent analysis and decision-making; In order to improve the accuracy of data prediction, the system will fit historical data and establish a prediction model; by analyzing the data collected in the past period of time, the system can predict future temperature and humidity trends; then, the system will compare the actual collected data with the predicted value and calculate the error coefficient to evaluate the working status of the sensor; if the data error of a sensor is found to be too large, it will be marked as an abnormal sensor and enter the calibration or replacement process to ensure the accuracy and reliability of the data; For sensors marked as abnormal, the system will try to calibrate them by adjusting their sensitivity or sampling frequency. If the calibration is invalid, the system will consider replacing the sensor and redeploying it to restore normal operation. After the calibration or replacement is completed, the system will restart data collection and conduct a comprehensive analysis of the new data. Through the calculated temperature anomaly coefficient and humidity anomaly coefficient, the system can evaluate the overall environmental conditions of the monitored area and determine whether there is an abnormality based on the set threshold. If the system determines that the environmental anomaly reaches the warning standard, it will immediately start the warning processing procedure and send alarm information to the monitoring center or relevant personnel through the Internet of Things architecture to remind them to take timely response measures.

[0030] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0031] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0032] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0033] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0034] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A monitoring method based on the Internet of Things architecture, characterized in that: The following steps are involved: S1: Deploy multiple temperature sensors and humidity sensors in the monitoring area. Collect temperature and humidity data of the monitoring area in real time through the temperature sensors and humidity sensors according to the time series and record them as actual values. S2: Obtain historical temperature data and humidity data of the monitored area, fit the historical temperature data and humidity data, establish a prediction model, and predict the current temperature data and humidity data, which are recorded as predicted values; S3: Compare and analyze the actual value with the predicted value, calculate the error coefficient, and evaluate the accuracy of the data collected by the temperature sensor and humidity sensor; S4: According to the evaluation results, the temperature sensor and the humidity sensor are divided into normal sensors and abnormal sensors, and the abnormal sensors are calibrated; S5: Based on the calibrated temperature sensor and humidity sensor, re-collect the temperature data and humidity data according to the time series, and conduct a comprehensive analysis of the temperature data and humidity data to determine whether there is any abnormality in the monitoring area; S6: According to the judgment result, if there is no abnormality in the monitoring area, the current monitoring state is continued; if there is an abnormality in the monitoring area, an early warning process is performed.

2. The monitoring method based on the Internet of Things architecture according to claim 1, characterized in that: The acquisition of historical temperature data and humidity data of the monitored area, fitting of the historical temperature data and humidity data, establishment of a prediction model, and prediction of the current temperature data and humidity data, recorded as a prediction value, specifically includes: Get historical temperature and humidity data, all data are arranged in time series; Check the data for missing values ​​and outliers; Missing values ​​can be handled through interpolation, and outliers can be identified and adjusted through statistical methods; Unit root test was used to test the stationarity of the time series; Stabilization is performed by difference method; Use the autocorrelation and partial autocorrelation plots to determine the order of the autoregressive and moving average components and ; in, represents the number of autoregressive terms, represents the number of moving average terms; Establish the expression of ARMA model and calculate the predicted value; The calculation expression of the predicted value is: ； In the formula, Indicates time The predicted value of Indicates the number of time points corresponding to the time series, i=1, 2, ..., , represents the maximum number of autoregressive terms, j=1, 2, ..., , represents the number of moving average terms, represents the i-th autoregressive coefficient, represents the jth moving average coefficient, Indicates time Historical temperature data or humidity data, Indicates time The error term of The predicted value Used as input for the next moment to make step-by-step predictions.

3. The monitoring method based on the Internet of Things architecture according to claim 1, characterized in that: The actual value is compared with the predicted value and analyzed to calculate the error coefficient, specifically including: The temperature sensor and humidity sensor collect temperature data and humidity data in time series respectively as actual values, recorded as ; Get the predicted value at the corresponding time point , the actual value With the predicted value Conduct comparative analysis; By calculating the error between the actual value and the predicted value, the error coefficient is calculated; Wherein, the calculation expression of the error coefficient is: ； In the formula, a represents the number of real-time collection points, m represents the maximum value of the collection points, Represents the error coefficient.

4. The monitoring method based on the Internet of Things architecture according to claim 1 is characterized in that: The step of evaluating the accuracy of data collected by the temperature sensor and the humidity sensor specifically includes: Judgment error coefficient Is it greater than or equal to the preset error coefficient threshold? If so, it is recorded as an abnormal sensor; if not, it is recorded as a normal sensor.

5. The monitoring method based on the Internet of Things architecture according to claim 1, characterized in that: The comprehensive analysis of temperature data and humidity data specifically includes: Process the temperature data collected in real time in the monitoring area and calculate the temperature anomaly coefficient; Process the humidity data collected in real time in the monitoring area and calculate the humidity anomaly coefficient; The temperature anomaly coefficient and humidity anomaly coefficient of the monitored area are normalized and the regional anomaly fluctuation index is calculated.

6. The monitoring method based on the Internet of Things architecture according to claim 5 is characterized in that: The process of obtaining the temperature anomaly coefficient is as follows: Re-collect the temperature and humidity data in the monitoring area according to the time series; A set of time series temperature data collected by each temperature sensor is recorded as a set of temperature data; Obtain the mean and standard deviation of each set of temperature data, and calculate the temperature anomaly coefficient based on the mean and standard deviation of each set of data; Wherein, the calculation expression of the temperature anomaly coefficient is: ； In the formula, Temperature anomaly coefficient, represents the average value of the temperature data of group a, represents the standard deviation of the ath group of data, a represents the number of sensors, a=1,2,...,n, n represents the maximum number of sensors.

7. The monitoring method based on the Internet of Things architecture according to claim 5 is characterized in that: The process of obtaining the humidity anomaly coefficient is as follows: A set of time series humidity data collected by each humidity sensor is recorded as a set of humidity data; Obtain the mean value of each group of humidity data, calculate the difference between the humidity data collected at each time point of each group of humidity data and the mean value of the corresponding group, and take the absolute value to obtain the humidity deviation value; Calculate the ratio of each humidity deviation value to the mean value of the corresponding group to obtain the humidity fluctuation ratio of the humidity data of each collection point; The humidity fluctuation ratio of each set of data is summed up and calculated to obtain the humidity anomaly ratio of each set of data; The humidity anomaly ratio of each set of humidity data is summed up and calculated to obtain the humidity anomaly coefficient of the monitored area.

8. The monitoring method based on the Internet of Things architecture according to claim 1, characterized in that: The determining whether there is an abnormal situation in the monitoring area specifically includes: Determine whether the regional abnormal fluctuation index is greater than or equal to the preset regional abnormal fluctuation index threshold. If so, it is recorded as the presence of an abnormal situation; if not, it is recorded as the absence of an abnormal situation.

9. The monitoring method based on the Internet of Things architecture according to claim 1, characterized in that: According to the judgment result, if there is no abnormality in the monitoring area, the current monitoring state is continued; if there is an abnormality in the monitoring area, an early warning process is performed, which specifically includes: If there is an abnormal situation in the monitoring area, the first-stage response procedure is immediately initiated, that is, a warning notification is sent, and an alarm signal is sent to the monitoring center through the IoT architecture; The system will activate the redundancy mechanism to ensure the continued normal operation of the monitoring area functions.

10. A monitoring system based on the Internet of Things architecture, characterized in that: A monitoring method based on an Internet of Things architecture as claimed in any one of claims 1 to 9, comprising: A data acquisition module, wherein the data acquisition module is used to collect temperature data and humidity data of the monitoring area in real time according to a time series through a temperature sensor and a humidity sensor, and record them as actual values; A prediction model building module, which is used to obtain historical temperature data and humidity data of the monitored area, fit the historical temperature data and humidity data, build a prediction model, and predict the current temperature data and humidity data, which are recorded as predicted values; A comparison and analysis module, which is used to compare and analyze the actual value with the predicted value, calculate the error coefficient, and evaluate the accuracy of the data collected by the temperature sensor and the humidity sensor; A sensor abnormality distinction and calibration module, wherein the sensor abnormality distinction and calibration module is used to divide the temperature sensor and the humidity sensor into normal sensors and abnormal sensors, and calibrate the abnormal sensors; A comprehensive analysis module, which is used for the calibrated temperature sensor and humidity sensor to re-collect temperature data and humidity data according to the time series, and to conduct a comprehensive analysis on the temperature data and humidity data to determine whether there is an abnormality in the monitoring area; The early warning module, according to the judgment result, continues the current monitoring state if there is no abnormal situation in the monitoring area, and performs early warning processing if there is an abnormal situation in the monitoring area.

Images