Smoke sensing system and method capable of realizing remote control management

Abstract

The invention relates to the technical field of environment monitoring, in particular to a flue gas sensing system and method capable of achieving remote control management, and the system comprises a sensor calibration module, a flue gas type classification module, a time data analysis module, a flue gas anomaly detection module and an emission source remote control module. According to the invention, by considering the influence of environmental temperature and humidity, calibrating a flue gas detection sensor, ensuring the accuracy of data acquisition and enhancing the reliability of monitoring data, the flue gas type is identified and an emission source is tracked by accurately classifying the flue gas type and predicting the source position, and the change trend of the flue gas concentration is predicted based on real-time data; a dynamic monitoring means is provided, real-time adjustment and coping strategies are helped to be carried out, the response speed and the event handling capacity are remarkably improved, the flue gas emission is managed through remote adjustment of emission control equipment, the environment safety guarantee and the capacity of conforming to laws and regulations are improved, and environment pollution and public health risks are reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of environmental monitoring, and in particular to a flue gas sensing system and method capable of remote control management. BACKGROUND

[0002] The field of environmental monitoring technology focuses on monitoring and analyzing natural or man-made environments using various sensors and data collection devices, covering air quality monitoring, water quality testing, noise level measurement, and real-time tracking of various environmental parameters. Through real-time data collection and processing, it provides key information and supports environmental protection, health and safety management, and policy making. Combined with modern information technology and communication technology, including cloud computing and the Internet of Things, it optimizes the collection, transmission and analysis of data, and implements effective environmental management and emergency response strategies.

[0003] Among them, the flue gas sensing system involves the use of sensing technology, data transmission and remote operation functions, aiming to monitor and control the flue gas emissions of industries and various emission sources. By providing real-time flue gas detection capabilities and allowing users to manage emissions through remote interfaces, it ensures environmental safety and compliance with regulatory requirements. Remote monitoring of air quality indicators and rapid response measures, including adjusting and stopping related emissions, can reduce environmental pollution and ensure air quality meets regulatory standards, protecting public health and environmental safety.

[0004] Traditional flue gas sensing technology lacks real-time adjustment capabilities for environmental changes such as temperature and humidity, resulting in poor accuracy of data monitoring. Misreading due to changes in environmental temperature and humidity affects the judgment and decision-making of the monitoring system. In terms of rapid identification of flue gas types and source tracking, it is often not accurate enough, limiting the ability to respond quickly to specific pollution events. In terms of flue gas concentration trend prediction, static models are used, lacking dynamic adaptability, which may cause delayed response in rapidly changing industrial environments. For remote adjustment functions of emission control equipment, existing technologies cannot be fully integrated, resulting in the inability to adjust control measures in time in emergency situations, causing environmental and health risks. SUMMARY

[0005] The purpose of the present application is to solve the shortcomings in the prior art and propose a flue gas sensing system and method capable of remote control management.

[0006] In order to achieve the above-mentioned purpose, the present application adopts the following technical solutions, a flue gas sensing system capable of remote control management comprises: The sensor calibration module is based on the flue gas detection sensor, analyzes the influence of environmental temperature and humidity changes on sensor readings, and calibrates the sensor. Real-time collection of flue gas detection data obtains environmental flue gas monitoring records; The flue gas type classification module identifies the flue gas composition by analyzing the flue gas data and compares the flue gas composition with known flue gas types to identify the flue gas emission type and predict the emission source location based on the environmental flue gas monitoring record, thereby obtaining type and source identification information; The time data analysis module calculates the time variation of the flue gas concentration based on the type and source identification information, compares the data variation at consecutive time points to predict the variation trend of the flue gas concentration, and obtains a concentration trend prediction result. The flue gas anomaly detection module identifies abnormal data by calculating the deviation of real-time flue gas concentration data and the predicted trend based on the concentration trend prediction result, analyzes the cause of the anomaly according to the data characteristics of the abnormal point, sends warning information to the management personnel, and obtains an anomaly event detection result. The emission source remote control module remotely adjusts the parameters of the emission control equipment based on the anomaly event detection result and the predicted trend of the flue gas concentration, monitors the effect of the adjustment, and obtains a flue gas response management result.

[0007] As a further scheme of the present application, the environmental flue gas monitoring record includes sensor calibration records, environmental temperature and humidity monitoring records, and real-time flue gas concentration data, the type and source identification information includes flue gas composition analysis results, flue gas type information, and predicted emission source type and location information, the concentration trend prediction result includes flue gas concentration prediction change graphs, predicted flue gas concentration peaks, and predicted concentration change rates, the anomaly event detection result includes abnormal data point detection records, abnormal emission cause identification results, and abnormal detection threshold parameters, and the flue gas response management result includes adjusted emission valve states, adjusted fan operating speeds, and monitored flue gas concentration change response effects.

[0008] As a further scheme of the present application, the sensor calibration module includes: The environmental influence analysis submodule calculates calibration parameters under various environmental conditions by analyzing the influence of environmental temperature and humidity changes on flue gas sensor readings based on flue gas detection sensors, and generates a calibration parameter analysis record. The sensor dynamic adjustment submodule adjusts the calibration parameters of the sensors according to real-time environmental conditions based on the calibration parameter analysis record, optimizes the influence of environmental changes on flue gas detection, and generates calibrated sensor settings. The data acquisition and recording submodule uses the calibrated sensor settings to collect flue gas detection data in real time and records the corresponding sensor positions and time stamps, and generates an environmental flue gas monitoring record.

[0009] As a further scheme of the present application, the flue gas type classification module includes: The smoke data analysis submodule analyzes the environmental smoke monitoring records, analyzes the smoke detection data, identifies the smoke concentration, and records the various components in the smoke to generate smoke characteristic data; The smoke component identification submodule compares the smoke components with known smoke types based on the smoke characteristic data, calculates the similarity of the data characteristics, identifies the type of target smoke, such as wood burning and chemical leakage, and generates a smoke component classification result; The smoke source location submodule uses the smoke component classification results to predict the location of the smoke emission source according to the smoke type and concentration, identifies abnormal emission sources, and generates type and source identification information.

[0010] As a further solution of the present invention, the specific formula for calculating the similarity of data features is: ; in, represents the cosine similarity, Represents the index value, which refers to the dimension position of the current calculation. The first feature vector representing the target smoke ingredients, Represents the first characteristic components, Represents the total dimension of characteristic data. This calculation method can effectively improve the accuracy and response speed of smoke type judgment.

[0011] As a further solution of the present invention, the time data analysis module includes: The smoke concentration analysis submodule calculates the change rate of the smoke concentration in real time based on the type and source identification information and utilizes the smoke concentration information at multiple time points to generate a change rate calculation result; The change trend assessment submodule assesses the increase and decrease trend and periodic changes of the smoke concentration based on the change rate calculation result through time series analysis to generate trend analysis data; The predicted value calculation submodule uses the trend analysis data to calculate the predicted values ​​of the smoke concentration at multiple time points and generate a concentration trend prediction result.

[0012] As a further solution of the present invention, the specific formula for calculating the predicted values ​​of the flue gas concentration at multiple time points is: ; in, Represents at a point in time The predicted concentration value is obtained by using the weighted moving average algorithm. Representative time point The actual concentration value at time the flue gas concentration record at the second most recent measurement time point before time representative time point the actual concentration value at time the flue gas concentration record at the third most recent measurement time point before time representative time point the actual concentration value at time the flue gas concentration record at the third most recent measurement time point before time is a weight coefficient of the concentration value at time point is a weight coefficient of the concentration value at time point is a weight coefficient of the concentration value at time point is a weight coefficient of the concentration value at time point is a weight coefficient of the concentration value at time point is a weight coefficient of the concentration value at time point is a weight coefficient of the concentration value at time point is a weight coefficient of the concentration value at time point is a weight coefficient of the concentration value at time point is the current time point, used to indicate the specific time based on which the predicted value is calculated.

[0013] As a further scheme of the present application, the flue gas anomaly detection module comprises: The real-time data detection submodule identifies abnormal data points by comparing the deviation of actual concentration from predicted concentration, generates real-time anomaly monitoring data, based on the concentration trend prediction result combined with real-time flue gas concentration data; The data feature recording submodule analyzes the real-time anomaly monitoring data, records the occurrence time, location, duration and intensity of the target abnormal data point, generates anomaly event feature information; The anomaly cause analysis submodule identifies the cause of abnormal emission, including equipment failure and operation error, and sends warning information to the management personnel, generates anomaly event detection results, based on the anomaly event feature information by analyzing the data features of the abnormal point.

[0014] As a further scheme of the present application, the emission source remote control module comprises: The adjustment parameter identification submodule identifies the equipment that needs to be adjusted and calculates the required adjustment amplitude, generates a list of control parameters, based on the anomaly event detection results combined with the real-time flue gas concentration prediction trend, analyzes the flue gas emission anomaly and concentration change trend; The device remote adjustment submodule generates control device adjustment records by remotely adjusting the emission control equipment in real time, including the opening degree of the emission valve and the fan speed of the exhaust system, based on the list of control parameters; The adjustment effect monitoring submodule monitors the real-time change of the flue gas concentration after adjustment based on the control device adjustment record, evaluates the real-time effect of the adjustment and the response state of the emission source, and generates a flue gas sensing management result.

[0015] A flue gas sensing method capable of remote control management is executed based on the above-mentioned flue gas sensing system capable of remote control management, comprising the following steps: S1: Based on the flue gas detection sensor, analyze the influence of temperature and humidity change on the sensor reading, and calibrate the sensor according to the real-time environmental conditions to generate sensor calibration parameters; S2: Using the sensor calibration parameters, real-time collection of flue gas data in the environment, including the concentration of flue gas, flue gas composition, generating environmental flue gas monitoring records; S3: Based on the environmental flue gas monitoring record, by comparing the flue gas composition with the known flue gas type, identifying the flue gas emission type, and predicting the emission source location, generating type and source identification information; S4: Using the type and source identification information, analyze the time change of flue gas concentration data, by comparing the data change of continuous time points, predict the change trend of flue gas concentration, generate concentration trend prediction results; S5: Using the concentration trend prediction results, real-time monitoring of flue gas concentration and comparison with predicted values, identifying and recording the occurrence time, location, duration and intensity of abnormal data, and performing cause analysis, generating abnormal event detection results; S6: According to the abnormal event detection result, combined with the concentration trend prediction result, remotely adjust the parameters of the emission control device, including adjusting the opening degree of the emission valve and the speed of the fan, and monitoring the adjustment effect, generating flue gas sensing management results.

[0016] Compared with the prior art, the advantages and positive effects of the present application are: In the present application, by considering the influence of environmental temperature and humidity, calibrating the flue gas detection sensor, ensuring the accuracy of data collection, enhancing the reliability of monitoring data, through accurate classification of flue gas type and prediction of source location, identifying flue gas type and tracking emission source, predicting the change trend of flue gas concentration based on real-time data, providing dynamic monitoring means, helping to make real-time adjustment and coping strategy, significantly improving response speed and event handling ability, by remotely adjusting the emission control device, managing flue gas emission, improving environmental safety and compliance with regulations, reducing environmental pollution and public health risks. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 The system flowchart of the present application; Figure 2A schematic diagram of a system framework of the present application; Figure 3 A flow chart of a sensor calibration module of the present application; Figure 4 A flow chart of a flue gas type classification module of the present application; Figure 5 A flow chart of a time data analysis module of the present application; Figure 6 A flow chart of a flue gas anomaly detection module of the present application; Figure 7 A flow chart of a remote control of an emission source module of the present application; Figure 8 A schematic diagram of a method step of the present application. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solutions and advantages of the present application more clear, the present application is further described in detail below in combination with the drawings and examples. It should be understood that the specific examples described herein are only used to explain the present application and do not limit the present application.

[0019] In the description of the present application, it should be understood that the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and therefore cannot be understood as indicating or implying that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application. In addition, in the description of the present application, the meaning of "a plurality of" is two or more, unless otherwise explicitly and specifically limited.

[0020] Referring to Figures 1 to 2 The present application provides a technical solution, a flue gas sensing system capable of realizing remote control management, comprising: The sensor calibration module is based on the flue gas detection sensor, analyzes the influence of environmental temperature and humidity changes on the sensor reading, calibrates the sensor, and collects flue gas detection data in real time to obtain environmental flue gas monitoring records; The flue gas type classification module identifies the flue gas composition by analyzing the flue gas data, compares it with known flue gas types, identifies the flue gas emission type, and predicts the emission source location to obtain type and source identification information; The time data analysis module is based on the type and source identification information, calculates the time variation of the flue gas concentration, compares the data variation at consecutive time points to predict the change trend of the flue gas concentration, and obtains the concentration trend prediction result; The flue gas anomaly detection module utilizes the concentration trend prediction result, identifies abnormal data by calculating the deviation of real-time flue gas concentration data and the predicted trend, analyzes the abnormal reason according to the data characteristics of the abnormal point, sends the early warning information to the management personnel, and obtains the abnormal event detection result; The emission source remote control module adjusts the parameters of the emission control equipment remotely according to the abnormal event detection result, combines the flue gas concentration prediction trend, monitors the adjustment effect, and obtains the flue gas response management result.

[0021] The environmental flue gas monitoring record includes sensor calibration record, environmental temperature and humidity monitoring record, and real-time flue gas concentration data, the type and source identification information includes flue gas component analysis result, flue gas type information, predicted emission source type and position information, the concentration trend prediction result includes flue gas concentration prediction change graph, predicted flue gas concentration peak, and predicted concentration change rate, the abnormal event detection result includes abnormal data point detection record, abnormal emission reason identification result, and abnormal detection threshold parameter, and the flue gas response management result includes the adjusted emission valve state, the adjusted fan running speed, and the monitored flue gas concentration change response effect.

[0022] Please refer to Figure 2 and Figure 3 , the sensor calibration module includes: The environmental influence analysis submodule calculates the calibration parameters under multiple environmental conditions by analyzing the influence of environmental temperature and humidity changes on flue gas sensor readings based on flue gas detection sensors, and generates a calibration parameter analysis record; In the environmental influence analysis submodule, based on multiple flue gas detection sensors, the changes of environmental temperature and humidity are continuously monitored, the influence of temperature and humidity on sensor readings is analyzed using a linear regression model, a prediction model is established using historical calibration data sets, the influence coefficient of temperature and humidity on flue gas detection accuracy is calculated, and by collecting real-time environmental data, combining calibrated sensor data, the model automatically calculates the calibration parameters for the current environmental conditions, adapts to different detection environments, ensures the accuracy and reliability of flue gas detection data, and generates a calibration parameter analysis record including parameter settings under different environmental conditions, such as calibration coefficient adjustment value when temperature rises or humidity changes. The target record is crucial for understanding how environmental factors affect sensor performance and provides data support for subsequent sensor adjustment.

[0023] The sensor dynamic adjustment submodule adjusts the calibration parameters of the sensor according to real-time environmental conditions based on the calibration parameter analysis record, optimizes the influence of environmental changes on flue gas detection, and generates calibrated sensor settings; In the sensor dynamic adjustment submodule, based on the calibration parameter analysis record, the adaptive filtering technique is used to dynamically adjust the calibration parameters of the sensor according to the real-time monitoring of the environmental temperature and humidity data. The adaptive filtering technique can adjust the filtering parameters according to the real-time changes of the input data, optimize the response of the sensor to environmental changes, and update the calibration parameters in real time by analyzing the relationship between environmental data and smoke concentration readings, reducing errors and improving the accuracy of measurement results. The generated calibrated sensor setting record records the latest values of the adjusted parameters such as temperature coefficient and humidity coefficient. The target adjustment helps the sensor better adapt to rapidly changing environmental conditions, ensuring the accuracy of data collection and the long-term stability of the sensor.

[0024] The data acquisition and recording submodule uses the calibrated sensor settings to collect smoke detection data in real time and records the corresponding sensor location and timestamp, generating an environmental smoke monitoring record. In the data acquisition and recording submodule, the calibrated sensor settings are used to collect smoke detection data in real time through time synchronization technology, and the sensor location and precise timestamp of each data point are recorded to ensure the synchronization and accuracy of data collection. The smoke data is analyzed in time and space, and during the collection process, data compression and optimized storage algorithms are used to effectively manage a large amount of collected data, reducing storage requirements while maintaining data integrity. The generated environmental smoke monitoring record includes detailed data logs, recording smoke types, concentrations, detection times, and sensor locations, supporting environmental monitoring analysis and subsequent data mining work, and providing scientific basis for environmental policy formulation and health and safety management.

[0025] Please refer to Figure 2 and Figure 4 , the smoke type classification module includes: The smoke data analysis submodule analyzes the environmental smoke monitoring record and analyzes the smoke detection data to identify smoke concentration and record various components in the smoke, generating smoke characteristic data. In the smoke data analysis submodule, through the analysis of the environmental smoke monitoring record, a multivariate linear regression model is used to deeply analyze the smoke detection data, which can effectively process multivariate data and predict smoke concentration, while identifying various components in the smoke. By calculating the concentration coefficients of different components, the total concentration is predicted and the component proportion is analyzed. The generated smoke characteristic data includes detailed chemical component proportions and total concentration estimates, which are very important for subsequent environmental impact assessment and health risk analysis, providing a basis for environmental regulation, and optimizing smoke treatment and pollution control strategies.

[0026] The smoke component identification submodule, based on the smoke characteristic data, compares the smoke components with known smoke types, calculates the similarity of the data characteristics, identifies the type of the target smoke, including wood burning and chemical leakage, and generates a smoke component classification result. The specific formula for calculating the similarity of the data characteristics is: ; Wherein, represents the cosine similarity, represents the index value, indicating the current dimension position, represents the first component in the feature vector of the target smoke, represents the first feature component of the corresponding smoke type in the known smoke type library, represents the total number of feature data dimensions. This calculation method can effectively improve the accuracy and response speed of smoke type judgment.

[0027] Formula: ; Formula details and formula calculation derivation process: The formula is used to calculate the cosine similarity between the smoke component data and the known smoke type data, and the result is used to judge the type of the smoke. Parameter meaning and setting value: is the feature component value in the target smoke sample, reflecting the chemical properties of the smoke. Assuming that the SO2 concentration is 20 ppm, the NO2 concentration is 15 ppm, the CO concentration is 10 ppm, and the O2 concentration is 5 ppm, i.e. ; is the feature component value of the corresponding smoke type in the known smoke type library, reflecting the component standard value of various typical smokes. Assuming that the smoke type is wood burning, SO2 is 18 ppm, NO2 is 12 ppm, CO is 8 ppm, and O2 is 6 ppm, i.e. ; is the total number of feature data dimensions. Assuming it is 4, i.e. considering the concentration of four chemical substances as features.

[0028] Substitute the parameters into the formula for calculation: ; ; The result of 0.981 indicates that the smoke sample is very close to the characteristics of wood burning smoke, and the high similarity value indicates that the target smoke is likely to come from wood burning, which helps to accurately identify the type of smoke and take appropriate environmental management and response measures.

[0029] The smoke source positioning submodule uses the smoke component classification result to predict the location of the smoke emission source according to the type and concentration of smoke, identify abnormal emission sources, and generate type and source identification information; In the smoke source positioning submodule, the smoke component classification result is used to predict the location of the smoke emission source through geographic information systems and spatial analysis techniques, combined with smoke type and concentration data, and spatial interpolation methods and emission models are used to estimate the emission source area. According to the type and concentration distribution detected, the potential risk area is depicted on the map, and the type and source identification information generated includes the coordinates of the emission source, the predicted impact area, and the environmental risk assessment. The target information is crucial for environmental protection agencies to develop pollution prevention and emergency response plans, ensuring timely pollution source control and implementation of environmental protection measures.

[0030] Please refer to Figure 2 and Figure 5 , the time data analysis module includes: The smoke concentration analysis submodule uses type and source identification information to calculate the change rate of smoke concentration in real time using smoke concentration information at multiple time points, and generates change rate calculation results; In the smoke concentration analysis submodule, based on the smoke concentration data collected at multiple time points, type and source identification information, and using difference algorithm to calculate the change rate of smoke concentration, the difference between consecutive time point concentration values is calculated, effectively revealing the short-term fluctuation of smoke concentration. Each time point concentration data is standardized to eliminate the reading deviation between different sensors. The data processed by the difference algorithm can directly show the change speed of smoke concentration in each time period, providing a basis for rapid response. The generated change rate calculation results include the increase and decrease rate of smoke concentration at each detection point. The results are crucial for understanding the activity rules of pollution sources and their immediate impact on the surrounding environment.

[0031] The change trend evaluation submodule uses the change rate calculation result to evaluate the increase and decrease trend and periodic change of smoke concentration through time series analysis, and generates trend analysis data; In the trend evaluation submodule, based on the change rate calculation results, the time series analysis method autoregressive moving average model is used to evaluate the long-term increasing and decreasing trend and periodic change of the flue gas concentration. The model combines autoregressive and moving average mechanisms, learns from historical data and predicts future trends. By comparing the changes in flue gas concentration in different time periods, seasonal or periodic changes are analyzed to provide scientific basis for environmental management and policy making. The generated trend analysis data records the predicted trend line and periodic fluctuations, providing precise scientific support for environmental protection strategies and helping decision makers develop more effective environmental governance measures.

[0032] The prediction value calculation submodule uses trend analysis data to calculate the flue gas concentration prediction value at multiple time points to generate concentration trend prediction results. The specific formula for calculating the flue gas concentration prediction value at multiple time points is: ; Where, represents the predicted concentration value at time point , which is the flue gas concentration prediction result obtained using the weighted moving average algorithm, represents the actual concentration value at time point , which is the flue gas concentration record at the most recent measurement time point before time , represents the actual concentration value at time point , which is the flue gas concentration record at the second most recent measurement time point before time , represents the actual concentration value at time point , which is the flue gas concentration record at the third most recent measurement time point before time , is the weight coefficient of the concentration value at time point , reflecting the relative importance of this data point in concentration prediction, is the weight coefficient of the concentration value at time point , is the weight coefficient of the concentration value at time point , is the current time point, used to indicate the specific time based on which the prediction value is calculated.

[0033] The formula is: ; Formula details and formula calculation derivation process: The formula predicts the flue gas concentration at multiple time points by using the flue gas concentration values at multiple known time points, providing data support for flue gas management and anomaly detection. Parameter meaning and set value: , , are the actual concentration values at time points , , , respectively, assuming 150 ppm, 145 ppm, and 147 ppm, respectively, representing the flue gas concentrations at the first three time points. , , are the weight coefficients of the data at each time point, assuming , , , reflecting the importance of data at different time points for prediction. Substitute the parameters into the formula for calculation: ; The results show that, according to the concentration data at the last three time points, the predicted flue gas concentration at time point is 148.2 ppm, which can be used to support immediate environmental response and decision-making.

[0034] Please refer to Figure 2 and Figure 6 , the flue gas anomaly detection module includes: The real-time data detection submodule identifies abnormal data points by comparing the deviation of actual concentration from predicted concentration based on the concentration trend prediction results combined with real-time flue gas concentration data, and generates real-time anomaly monitoring data; In the real-time data detection submodule, abnormal data points are identified using a deviation analysis model based on the concentration trend prediction results combined with real-time flue gas concentration data by comparing the deviation of actual concentration from predicted concentration. The formula is used to calculate the deviation between the predicted value and the actual monitoring value, generating real-time anomaly monitoring data, where represents the concentration deviation, used to evaluate whether there are abnormal data points, represents the real-time measured flue gas concentration, represents the predicted flue gas concentration based on historical data and trend analysis, If it exceeds the predetermined threshold , it is identified as an abnormal data point, Formula details and formula calculation derivation process: Assuming the predicted flue gas concentration unit, the real-time measured flue gas concentration units, set threshold units, calculate :

[0035] The result 15 units exceeds the set threshold 10 units, indicating an anomaly, the calculation process is used for real-time monitoring of flue gas concentration and identifying abnormal concentrations deviating from the predicted value, generating real-time anomaly monitoring data, ensuring continuous monitoring of flue gas emissions and timely discovery of anomalies, taking measures for processing, ensuring environmental safety and formulating effective response measures.

[0036] The data feature recording submodule analyzes real-time anomaly monitoring data, records the occurrence time, location, duration and intensity of target anomaly data points, and generates anomaly event feature information; In the data feature recording submodule, real-time anomaly monitoring data is analyzed, and the occurrence time, location, duration and intensity of each anomaly data point are recorded using geographic information systems and event recording technology, providing accurate spatial location records, and event recording technology ensures that all details of anomaly events are captured and recorded, allowing anomaly event feature information to be fully analyzed, and generated anomaly event feature information is used to help understand the environmental conditions and potential impact of anomalies, providing accurate data support for root cause analysis and response strategy formulation.

[0037] The anomaly cause analysis submodule identifies the causes of abnormal emissions based on anomaly event feature information by analyzing the data features of anomaly points, including equipment failure and operation errors, and sends warning information to management personnel, generating anomaly event detection results; In the anomaly cause analysis submodule, based on the generated anomaly event feature information, decision tree analysis technology is applied to identify the causes of abnormal emissions by analyzing anomaly point data features such as concentration mutation, duration and related environmental factors, and a decision tree model is used to distinguish between equipment failure and operation errors causing anomalies, providing intuitive warning information for management personnel by extracting decision rules from complex data, effectively pointing out possible fault points or operation errors, and generating anomaly event detection results including detailed cause analysis reports and warnings, providing a scientific basis for maintenance or prevention measures taken.

[0038] Please refer to Figure 2 and Figure 7 , the emission source remote control module includes: The adjustment parameter identification submodule analyzes flue gas emission anomaly conditions and concentration change trends based on anomaly event detection results and real-time flue gas concentration prediction trends, identifies equipment that needs to be adjusted, calculates the required adjustment range, and generates a list of control parameters; In the adjustment parameter identification submodule, based on the abnormal event detection results, multivariate regression analysis is used to analyze the abnormal situation of flue gas emission and the concentration change trend. Multivariate regression analysis helps to determine the most relevant equipment performance indicators related to flue gas concentration changes, such as temperature regulators and pressure sensor readings, to identify key equipment that needs to be adjusted. Based on the analysis results, the required adjustment range for each device is calculated, such as the percentage of valve opening or the change in fan speed. The demand calculation relies on the comprehensive evaluation of real-time data and predicted trends to ensure that the adjustment measures are quick and accurate. The generated regulation parameter list lists the adjustment parameters for each device and the expected adjustment effect, providing a basis for implementing adjustments and predicting the possible environmental impact after adjustment.

[0039] The device remote adjustment submodule adjusts the emission control equipment remotely based on the regulation parameter list, including the opening degree of the emission valve and the fan speed of the exhaust system, and generates a control device adjustment record. In the device remote adjustment submodule, based on the regulation parameter list, the parameters of the emission control equipment are adjusted remotely in real time using Internet of Things technology. Internet of Things technology enables instant and accurate transmission of instructions from the control center to the field equipment, enabling accurate adjustment of the opening degree of the emission valve and the fan speed of the exhaust system. The target adjustment is based on the parameter list derived from previous analysis, ensuring that each adjustment is accurate and meets the set adjustment requirements. The generated control device adjustment record details the parameters of each adjustment, the execution time, and the immediate feedback status after execution, providing data support for subsequent effect evaluation and adjustment.

[0040] The adjustment effect monitoring submodule monitors the real-time changes in flue gas concentration after adjustment based on the control device adjustment record, evaluates the real-time effect of the adjustment and the response state of the emission source, and generates a flue gas sensing management result. In the adjustment effect monitoring submodule, real-time data analysis technology is used to monitor the real-time changes in flue gas concentration after adjustment based on the control device adjustment record. By setting up real-time data stream analysis, the monitoring system can continuously track the changes in flue gas concentration and compare them with the data before adjustment to evaluate the real-time effect of the adjustment. Real-time dynamic model adjustment is used to dynamically adjust parameters to match the real-time collected environmental data. The generated flue gas sensing management result includes the adjusted flue gas concentration data, device response state, and environmental impact assessment, providing immediate feedback on adjustment measures and preliminary judgment of long-term effects, helping the management team make more scientific decisions.

[0041] Please refer to Figure 8 A flue gas sensing method capable of remote control management is based on the above-mentioned flue gas sensing system capable of remote control management and includes the following steps: S1: Based on the flue gas detection sensor, analyze the influence of temperature and humidity changes on the flue gas detection sensor readings, and calibrate the sensor according to the real-time environmental conditions to generate sensor calibration parameters; S2: Use sensor calibration parameters to collect real-time flue gas data in the environment, including flue gas concentration and flue gas composition, and generate environmental flue gas monitoring records; S3: Based on the environmental flue gas monitoring records, compare the flue gas composition with known flue gas types to identify the flue gas emission type and predict the emission source location, and generate type and source identification information; S4: Use type and source identification information to analyze the time variation of flue gas concentration data, compare the data variation at consecutive time points to predict the trend of flue gas concentration, and generate concentration trend prediction results; S5: Use the concentration trend prediction results to monitor the flue gas concentration in real time and compare it with the predicted value, identify and record the occurrence time, location, duration and intensity of abnormal data, and analyze the causes, and generate abnormal event detection results; S6: According to the abnormal event detection results, combined with the concentration trend prediction results, remotely adjust the parameters of the emission control equipment, including adjusting the opening degree of the emission valve and the speed of the fan, and monitoring the adjustment effect, and generating flue gas response management results.

[0042] The above is only the preferred embodiment of the present application, not other forms of the present application, any skilled in the art may use the above disclosed technical content to change or modify as equivalent embodiments applied to other fields, but any simple modification, equivalent change and modification of the above embodiments without departing from the technical solution content of the present application, according to the technical essence of the present application, still belongs to the protection scope of the present application technical solution.

Claims

1. A smoke sensing system capable of remote control and management, characterized in that: The system comprises: The sensor calibration module is based on the smoke detection sensor, analyzes the impact of changes in ambient temperature and humidity on the sensor readings, calibrates the sensor, collects smoke detection data in real time, and obtains environmental smoke monitoring records; The smoke type classification module analyzes the smoke data through the environmental smoke monitoring records, identifies the smoke components, compares them with known smoke types, identifies the smoke emission type, and predicts the emission source location to obtain type and source identification information; The time data analysis module calculates the time variation of the smoke concentration based on the type and source identification information, and predicts the trend of the smoke concentration by comparing the data changes at consecutive time points to obtain a concentration trend prediction result; The smoke anomaly detection module uses the concentration trend prediction results to calculate the deviation between the real-time smoke concentration data and the predicted trend, identifies abnormal data, analyzes the cause of the abnormality based on the data characteristics of the abnormal point, sends early warning information to the management personnel, and obtains the abnormal event detection results; The emission source remote control module remotely adjusts the parameters of the emission control equipment based on the abnormal event detection results and the flue gas concentration prediction trend, monitors the effect of the adjustment, and obtains the flue gas sensing management results.

2. The smoke sensing system capable of remote control and management according to claim 1 is characterized in that: The environmental flue gas monitoring records include sensor calibration records, environmental temperature and humidity monitoring records, and real-time flue gas concentration data. The type and source identification information includes flue gas composition analysis results, flue gas type information, predicted emission source type and location information. The concentration trend prediction results include flue gas concentration predicted change graph, predicted flue gas concentration peak, and predicted concentration change rate. The abnormal event detection results include abnormal data point detection records, abnormal emission cause identification results, and abnormal detection threshold parameters. The flue gas sensing management results include the adjusted emission valve status, the adjusted fan operating speed, and the monitored flue gas concentration change response effect.

3. The smoke sensing system capable of remote control and management according to claim 1 is characterized in that: The sensor calibration module includes: The environmental impact analysis submodule is based on the smoke detection sensor. It analyzes the impact of changes in ambient temperature and humidity on the smoke sensor readings, calculates calibration parameters under various environmental conditions, and generates calibration parameter analysis records. The sensor dynamic adjustment submodule adjusts the sensor calibration parameters based on the calibration parameter analysis record and according to the real-time environmental conditions, optimizes the impact of environmental changes on smoke detection, and generates calibrated sensor settings; The data acquisition and recording submodule uses the calibrated sensor settings to collect smoke detection data in real time, and records the corresponding sensor positions and timestamps to generate environmental smoke monitoring records.

4. The smoke sensing system capable of remote control and management according to claim 1 is characterized in that: The flue gas type classification module includes: The smoke data analysis submodule analyzes the environmental smoke monitoring records, analyzes the smoke detection data, identifies the smoke concentration, and records the various components in the smoke to generate smoke characteristic data; The smoke component identification submodule compares the smoke components with known smoke types based on the smoke characteristic data, calculates the similarity of the data characteristics, identifies the type of target smoke, such as wood burning and chemical leakage, and generates a smoke component classification result; The smoke source location submodule uses the smoke component classification results to predict the location of the smoke emission source according to the smoke type and concentration, identifies abnormal emission sources, and generates type and source identification information.

5. The smoke sensing system capable of remote control and management according to claim 4 is characterized in that: The specific formula for calculating the similarity of data features is: ； in, represents the cosine similarity, Represents the index value, which refers to the dimension position of the current calculation. The first feature vector representing the target smoke ingredients, Represents the first characteristic components, Represents the total dimension of characteristic data. This calculation method can effectively improve the accuracy and response speed of smoke type judgment.

6. The smoke sensing system capable of remote control and management according to claim 1 is characterized in that: The time data analysis module includes: The smoke concentration analysis submodule calculates the change rate of the smoke concentration in real time based on the type and source identification information and utilizes the smoke concentration information at multiple time points to generate a change rate calculation result; The change trend assessment submodule assesses the increase and decrease trend and periodic changes of the smoke concentration based on the change rate calculation result through time series analysis to generate trend analysis data; The predicted value calculation submodule uses the trend analysis data to calculate the predicted values ​​of the smoke concentration at multiple time points and generate a concentration trend prediction result.

7. The smoke sensing system capable of remote control and management according to claim 6 is characterized in that: The specific formula for calculating the predicted values ​​of flue gas concentration at multiple time points is: ； in, Represents at a point in time The predicted concentration value is obtained by using the weighted moving average algorithm. Representative time point The actual concentration value at time The smoke concentration record at the most recent measurement time point, Representative time point The actual concentration value at time The smoke concentration record at the second most recent measurement time point before, Representative time point The actual concentration value at time The smoke concentration record at the third most recent measurement time point before, It's the time point Concentration value The weight coefficient reflects the relative importance of the data point in the concentration prediction. It's the time point Concentration value The weight coefficient of It's the time point Concentration value The weight coefficient of is the current time point, which indicates the specific time based on which the forecast value is calculated.

8. The smoke sensing system capable of remote control and management according to claim 1 is characterized in that: The smoke anomaly detection module includes: The real-time data detection submodule is based on the concentration trend prediction result and combined with the real-time flue gas concentration data, and identifies abnormal data points by comparing the deviation between the actual concentration and the predicted concentration, thereby generating real-time abnormal monitoring data; The data feature recording submodule analyzes the real-time abnormal monitoring data, records the occurrence time, location, duration and intensity of the target abnormal data point, and generates abnormal event feature information; The abnormal cause analysis submodule analyzes the data characteristics of the abnormal points based on the abnormal event characteristic information, identifies the causes of abnormal emissions, including equipment failure and operational errors, sends warning information to management personnel, and generates abnormal event detection results.

9. The smoke sensing system capable of remote control and management according to claim 1 is characterized in that: The emission source remote control module includes: The adjustment parameter identification submodule analyzes the abnormality of flue gas emissions and the concentration change trend based on the abnormal event detection results and the real-time flue gas concentration prediction trend, identifies the equipment that needs to be adjusted, calculates the required adjustment range, and generates a list of control parameters; The device remote adjustment submodule remotely adjusts the emission control device in real time based on the control parameter list, including the opening and closing degree of the emission valve and the fan speed of the exhaust system, and generates a control device adjustment record; The adjustment effect monitoring submodule monitors the real-time changes of the flue gas concentration after adjustment based on the adjustment record of the control device, evaluates the real-time effect of the adjustment and the response status of the emission source, and generates a flue gas sensing management result.

10. A smoke sensing method capable of realizing remote control management, characterized in that: The smoke sensing system capable of remote control and management according to any one of claims 1 to 9 comprises the following steps: Based on the smoke detection sensor, analyze the impact of temperature and humidity changes on the smoke detection sensor readings, calibrate the sensor according to the real-time environmental conditions, and generate sensor calibration parameters; Using the sensor calibration parameters, real-time smoke data in the environment is collected, including smoke concentration and smoke composition, to generate environmental smoke monitoring records; Based on the environmental flue gas monitoring records, the type of flue gas emissions is identified by comparing the flue gas components with known flue gas types, and the location of the emission source is predicted to generate type and source identification information; Analyze the temporal variation of the smoke concentration data by using the type and source identification information, predict the trend of smoke concentration variation by comparing the data changes at consecutive time points, and generate a concentration trend prediction result; Using the concentration trend prediction results, the smoke concentration is monitored in real time and compared with the predicted value, the time, location, duration and intensity of abnormal data are identified and recorded, and the cause is analyzed to generate abnormal event detection results; According to the abnormal event detection results and combined with the concentration trend prediction results, the parameters of the emission control equipment are remotely adjusted, including adjusting the opening and closing degree of the emission valve and the speed of the fan, and the adjustment effect is monitored to generate the flue gas sensing management results.

Images