A method for monitoring the quality of pollution source online monitoring data

Abstract

The present invention relates to the technical field of data quality monitoring, and specifically to a method for monitoring the quality of online monitoring data of pollution sources, comprising the following steps: using monitoring equipment to collect the exhaust gas emission concentration and wastewater discharge flow data of the pollution source, recording the data collection time and location, and generating monitoring data records. In the present invention, through the time series analysis and spatial correlation evaluation of the pollution source monitoring data, the accuracy and meticulousness of data processing and analysis are significantly improved, and the parameters of the monitoring equipment are dynamically monitored and adjusted to adapt to environmental changes, so as to effectively improve the adaptability and flexibility of data quality monitoring, ensure that the monitoring results can reflect the real environmental conditions, and use large-model artificial intelligence to adjust the spatial position and time interval, further optimize the comprehensiveness and systematicness of data collection, so that the monitoring network can respond to environmental changes and real-time needs of data quality more intelligently.

Description

Technical Field

[0001] The present invention relates to the technical field of data quality monitoring, and in particular to a method for monitoring the quality of pollution source online monitoring data. Background Art

[0002] The field of data quality monitoring technology focuses on ensuring that the data collected, processed and stored through various information systems has a high degree of accuracy, completeness, consistency and reliability, covering multiple aspects such as data verification, cleaning, processing and analysis. In practical applications, data quality monitoring not only identifies and corrects erroneous data, but also prevents the occurrence of data quality problems through various algorithms and tools. Data quality monitoring also includes continuous data quality assessment to ensure that data meets established quality standards throughout its life cycle, supports decision-making in a variety of industries, and enhances the effectiveness of data-driven strategies and operations.

[0003] Existing data quality monitoring technologies focus on static monitoring strategies in pollution source monitoring and lack the ability to respond quickly to dynamic environmental changes. Static monitoring methods result in data that cannot be adjusted in a timely manner when facing rapidly changing environmental factors, affecting the accuracy and real-time nature of the data. For example, when equipment parameters affected by environmental changes are not identified and adjusted in a timely manner, erroneous data will be collected, and data errors will directly affect the effectiveness of environmental management. Traditional methods rely on manual intervention in data anomaly identification and lack automated and intelligent processing mechanisms, which not only reduces processing speed but also increases the risk of human error. The lack of effective data integrity and consistency analysis tools is also a shortcoming of existing technologies, which limits the reliability of data in long-term monitoring and affects the scientific nature and implementation effect of environmental protection. Summary of the invention

[0004] The purpose of the present invention is to solve the shortcomings in the prior art and to propose a method for monitoring the quality of pollution source online monitoring data.

[0005] In order to achieve the above object, the present invention adopts the following technical scheme, a method for monitoring the quality of online monitoring data of pollution sources, comprising the following steps:

[0006] S1: Use monitoring equipment to collect data on waste gas emission concentration and wastewater discharge flow from pollution sources, record the data collection time and location, and generate monitoring data records;

[0007] S2: Performing time series analysis on the monitoring data records, identifying deviation points and trend anomalies, and evaluating the spatial correlation of online monitoring data of pollution sources, analyzing the distribution area of ​​abnormal data, and generating anomaly identification results;

[0008] S3: Perform integrity and consistency analysis on the pollution source online monitoring data for the abnormality identification result, and generate data integrity analysis results by comparing the information entropy changes during the data collection time;

[0009] S4: Based on the data integrity analysis results, using large model artificial intelligence, adjust the spatial location and time interval of the pollution source monitoring points, set data collection parameters, and generate an optimized monitoring configuration;

[0010] S5: using the optimized monitoring configuration, periodically evaluating and adjusting the monitoring equipment parameters, monitoring the data quality of the pollution source, dynamically monitoring and optimizing the equipment correction parameters with reference to environmental changes, and generating a dynamic correction strategy;

[0011] S6: According to the dynamic correction strategy, the online monitoring data quality of the pollution source is controlled through the large model artificial intelligence, the consistency with the preset pollution level is verified, and the data quality monitoring results are generated.

[0012] As a further solution of the present invention, the monitoring data records include waste gas emission concentration data, wastewater discharge flow data, data collection time and data collection location of the pollution source; the anomaly identification results include deviation points, trend anomalies, spatial correlation assessment of pollution sources and distribution areas of abnormal data in time series analysis; the data integrity analysis results include the integrity and consistency level of the data obtained by comparing the information entropy changes; the optimized monitoring configuration includes the adjusted spatial position of the pollution source monitoring point, the optimized data collection time interval and the reset data collection parameters; the dynamic correction strategy includes the periodic evaluation results of monitoring equipment parameters, the equipment correction parameters dynamically adjusted according to environmental changes and the monitoring of pollution source data quality; the data quality monitoring results include the data quality control scheme controlled by large model artificial intelligence and the consistency assessment verified with the preset pollution degree.

[0013] As a further solution of the present invention, the steps of using monitoring equipment to collect the exhaust gas emission concentration and wastewater discharge flow data of the pollution source, record the data collection time and location, and generate the monitoring data record are specifically as follows:

[0014] S101: Using monitoring equipment, by identifying and recording the location of pollution sources, recording the geographical coordinates of each online monitoring point of pollution sources, analyzing the spatial positioning of the monitoring points, and generating location positioning records;

[0015] S102: Synchronize the sampling time of each measuring point according to the position positioning record, bind the timestamp to the measuring point position, check the integrity of each online monitoring data point in time and location, and generate a time and location binding record;

[0016] S103: Based on the time and location binding records, collect exhaust gas emission concentration and wastewater discharge flow data, associate the data with the time and location records, verify the integrity of the online monitoring data of the pollution source, and generate monitoring data records.

[0017] As a further solution of the present invention, the steps of performing time series analysis on the monitoring data records, identifying deviation points and trend anomalies, evaluating the spatial correlation of online monitoring data of pollution sources, analyzing the distribution area of ​​abnormal data, and generating anomaly identification results are specifically as follows:

[0018] S201: constructing a time series according to the monitoring data record, sequentially arranging the data of each online monitoring point of the pollution source, detecting deviation points in the online monitoring data of the pollution source, verifying the time continuity and deviation of the data, and generating a time series deviation record;

[0019] S202: Based on the time series deviation record, trend line fitting is performed on the long-term data, trends and periodic changes of the online monitoring data of the pollution source are identified, normal fluctuations and abnormal trends are analyzed, and trend analysis results are generated;

[0020] S203: Analyze the spatial distribution of abnormal data using the trend analysis results, evaluate the data correlation between online monitoring points of differentiated pollution sources, identify the geographical pattern of abnormal distribution, and generate anomaly identification results.

[0021] As a further solution of the present invention, the steps of performing integrity and consistency analysis on the pollution source online monitoring data for the abnormal identification results and generating data integrity analysis results by comparing the information entropy changes during the data collection time are specifically as follows:

[0022] S301: Using the abnormal identification results, screening the monitoring points affected by data integrity, conducting data audit on the online monitoring points of the pollution sources, checking the integrity of the data records, avoiding erroneous data records, and generating data integrity audit records;

[0023] S302: Based on the data integrity audit record, a Kalman filter algorithm is used to perform state estimation and error correction on the monitoring point data, and by comparing the information entropy changes at the differentiated time, deviations in the data records are identified, and information entropy change analysis results are generated;

[0024] S303: According to the information entropy change analysis results, the data integrity and consistency information of the monitoring points are integrated, the quality of the online monitoring data of the pollution source is evaluated, the online monitoring data of the pollution source is verified to match the quality standards, and the data integrity analysis results are generated.

[0025] As a further solution of the present invention, the formula of the Kalman filter algorithm is as follows:

[0026] ;

[0027] in, For the moment State estimation of observation information, For the moment The previous state estimate, is the Kalman gain, For the moment The real-time observation value of is the observation model matrix, is the smoothing parameter.

[0028] As a further solution of the present invention, based on the data integrity analysis results, the steps of adjusting the spatial position and time interval of the pollution source monitoring point and setting the data collection parameters to generate the optimized monitoring configuration are as follows:

[0029] S401: Based on the data integrity analysis result, analyze the spatial distribution of the online monitoring point data of the pollution source and the real-time configuration of the time interval, identify the optimization space, and generate the monitoring point configuration optimization result;

[0030] S402: According to the monitoring point configuration optimization result, the spatial layout and time sampling frequency of the online monitoring points of the pollution source are adjusted through the large model artificial intelligence, the efficiency and scope of monitoring data collection are optimized, and a spatial and temporal adjustment plan is generated;

[0031] S403: Apply the space and time adjustment scheme to the data quality of the pollution source monitoring, reset the data collection parameters of the online monitoring points of the pollution source, verify the effectiveness of data collection and monitoring, and generate an optimized monitoring configuration.

[0032] As a further solution of the present invention, the optimized monitoring configuration is used to periodically evaluate and adjust the monitoring equipment parameters, monitor the data quality of the pollution source, refer to environmental changes, dynamically monitor and optimize the equipment correction parameters, and generate the dynamic correction strategy in the following steps:

[0033] S501: Based on the optimized monitoring configuration, using a machine learning algorithm, intelligently detect the functions and parameters of the monitoring equipment, analyze the consistency of the monitoring equipment running according to the set parameters, monitor the operating status and efficiency of the equipment, and generate equipment performance evaluation results;

[0034] S502: According to the equipment performance evaluation result, referring to the changes in the environment around the pollution source, automatically adjusting the monitoring equipment parameters to match the cyclically changing monitoring environment, evaluating the quality of the online monitoring data of the pollution source, and generating a parameter adjustment record;

[0035] S503: Implement the parameter adjustment record to the pollution source online monitoring network, check the effect of the parameter adjustment through real-time data feedback loop, cyclically update the monitoring equipment correction parameters to match the environment and data change requirements, and generate a dynamic correction strategy.

[0036] As a further solution of the present invention, the formula of the machine learning algorithm is as follows:

[0037] ;

[0038] in, It is a performance indicator for evaluating pollution source monitoring. is the information entropy, is the pollution source monitoring dataset, To monitor the parameters, Monitoring parameters for monitoring equipment gather, is the number of data points in the sub-dataset for the monitoring parameter, is the total number of data points in the monitoring dataset, and is the regulating factor, To consider monitoring parameters Next data set The parameter variation.

[0039] As a further solution of the present invention, according to the dynamic correction strategy, the steps of performing online monitoring data quality control of pollution sources through large-scale artificial intelligence to verify the consistency with the preset pollution degree and generate data quality monitoring results are specifically as follows:

[0040] S601: Based on the dynamic correction strategy, use the large model artificial intelligence to perform real-time analysis on the monitoring data stream, monitor the quality of the online monitoring data of the pollution source, identify and correct the deviations and anomalies in the data, and generate real-time data quality records;

[0041] S602: using the real-time data quality record, evaluating the consistency between the online monitoring data of the pollution source and the environmental changes, comparing the preset pollution degree with the real-time online monitoring data, verifying the reliability of the data, and generating a consistency verification result;

[0042] S603: According to the consistency verification result, the overall quality of the online monitoring data of the pollution source is evaluated, the pollution degree is predicted, and the target pollution threshold is adjusted by monitoring the quality of the online monitoring data of the pollution source to generate a data quality monitoring result.

[0043] Compared with the prior art, the advantages and positive effects of the present invention are:

[0044] In the present invention, through time series analysis and spatial correlation evaluation of pollution source monitoring data, the accuracy and meticulousness of data processing and analysis are significantly improved, and deviation points and trend anomalies are identified, which not only enhances the timeliness and accuracy of data, but also provides an in-depth understanding of the potential factors behind data anomalies. By dynamically monitoring and adjusting the parameters of monitoring equipment to adapt to environmental changes, the adaptability and flexibility of data quality monitoring are effectively improved to ensure that the monitoring results can reflect the real environmental conditions. Using large model artificial intelligence to adjust spatial position and time interval, the comprehensiveness and systematicness of data collection are further optimized, so that the monitoring network can respond more intelligently to environmental changes and real-time needs of data quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a schematic diagram of the main steps of the present invention;

[0046] Figure 2 It is a schematic diagram of the refinement of S1 of the present invention;

[0047] Figure 3 It is a schematic diagram of the refinement of S2 of the present invention;

[0048] Figure 4 It is a schematic diagram of the refinement of S3 of the present invention;

[0049] Figure 5 It is a schematic diagram of the refinement of S4 of the present invention;

[0050] Figure 6 It is a detailed schematic diagram of S5 of the present invention;

[0051] Figure 7 It is a detailed schematic diagram of S6 of the present invention. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0053] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0054] Example 1: Please refer to Figure 1 The present invention provides a technical solution, a method for monitoring the quality of online monitoring data of pollution sources, comprising the following steps:

[0055] S1: Use monitoring equipment to collect data on waste gas emission concentration and wastewater discharge flow from pollution sources, record the data collection time and location, and generate monitoring data records;

[0056] S2: Perform time series analysis on monitoring data records, identify deviation points and trend anomalies, evaluate the spatial correlation of online monitoring data of pollution sources, analyze the distribution area of ​​abnormal data, and generate anomaly identification results;

[0057] S3: Perform integrity and consistency analysis on the online monitoring data of pollution sources based on the abnormal identification results, and generate data integrity analysis results by comparing the information entropy changes during the data collection time;

[0058] S4: Based on the data integrity analysis results, use big model artificial intelligence to adjust the spatial location and time interval of pollution source monitoring points, set data collection parameters, and generate optimized monitoring configurations;

[0059] S5: Use the optimized monitoring configuration to periodically evaluate and adjust the monitoring equipment parameters, monitor the data quality of the pollution source, refer to environmental changes, dynamically monitor and optimize the equipment correction parameters, and generate dynamic correction strategies;

[0060] S6: Based on the dynamic correction strategy, the online monitoring data quality of pollution sources is controlled through large-scale artificial intelligence models to verify the consistency with the preset pollution level and generate data quality monitoring results.

[0061] The monitoring data records include the exhaust gas emission concentration data, wastewater discharge flow data, data collection time and data collection location of the pollution sources. The anomaly identification results include the deviation points of time series analysis, trend anomalies, spatial correlation assessment of pollution sources and distribution areas of abnormal data. The data integrity analysis results include the integrity and consistency level of the data obtained by comparing the changes in information entropy. The optimized monitoring configuration includes the adjusted spatial location of the pollution source monitoring points, the optimized data collection time interval and the reset data collection parameters. The dynamic correction strategy includes the periodic evaluation results of the monitoring equipment parameters, the equipment correction parameters dynamically adjusted according to environmental changes and the monitoring of the pollution source data quality. The data quality monitoring results include the data quality control plan controlled by large model artificial intelligence and the consistency assessment of verification and preset pollution levels.

[0062] See also Figure 2, using monitoring equipment to collect the exhaust gas emission concentration and wastewater discharge flow data of the pollution source, record the data collection time and location, and generate monitoring data records in the following steps:

[0063] S101: Using monitoring equipment, by identifying and recording the location of pollution sources, recording the geographical coordinates of each online monitoring point of pollution sources, analyzing the spatial positioning of the monitoring points, and generating the execution process of the location positioning record is as follows;

[0064] Sub-step S101 uses monitoring equipment to conduct a comprehensive scan of the designated area, and uses multi-source positioning technology (including GPS, Wi-Fi positioning, and cellular network positioning) to enhance the accuracy and reliability of geographic coordinates. The coordinate data of each monitoring point is determined by averaging the coordinate values ​​from three different sources to reduce the error caused by the deviation of a single technology. Dynamic time calibration technology is used to update the coordinate data of the monitoring point every 10 minutes to adapt to environmental changes, such as changes in geographic location caused by ground subsidence or construction activities, and generate location positioning records. The formula used is:

[0065] ;

[0066] in, For the calculation of position coordinates, , and Represents the coordinate data obtained through GPS, Wi-Fi and cellular networks respectively.

[0067] S102: Synchronize the sampling time of each measuring point according to the location positioning record, bind the timestamp to the measuring point position, check the integrity of each online monitoring data point in time and location, and generate the execution process of the time and location binding record as follows;

[0068] Substep S102 uses a precise time synchronization protocol based on the location location record to ensure that the internal clocks of all monitoring devices are synchronized with the international standard time. Each time data is collected, the exact time of data collection and the corresponding geographical location are recorded, and the data is sent to the central database through a secure encryption protocol. The central database uses a specially designed time and location association algorithm that can process batch data and quickly detect any abnormal data points in time or location, generating time and location binding records.

[0069] S103: Based on the time and location binding records, collect the exhaust gas emission concentration and wastewater discharge flow data, associate the data with the time and location records, verify the integrity of the online monitoring data of the pollution source, and generate the execution process of the monitoring data record as follows;

[0070] Sub-step S103 collects environmental monitoring data, including exhaust gas emission concentration and wastewater discharge flow, based on time and location binding records. Data is automatically collected by sensors installed at the emission outlets of pollution sources and transmitted to the monitoring center in real time. To ensure the accuracy of the data, each sensor undergoes strict field calibration to adapt to various environmental conditions. The monitoring center uses a complex data verification program to compare real-time data with historical data of the same period, identify any significant data changes or anomalies, and generate monitoring data records using the formula:

[0071] ;

[0072] in, represents the quality indicator of monitoring data, is the exhaust gas concentration, is the wastewater flow rate, and is the weight coefficient.

[0073] See also Figure 3 , conduct time series analysis on monitoring data records, identify deviation points and trend anomalies, evaluate the spatial correlation of online monitoring data of pollution sources, analyze the distribution area of ​​abnormal data, and generate anomaly identification results in the following steps:

[0074] S201: construct a time series based on the monitoring data records, arrange the data of each online monitoring point of the pollution source in sequence, detect the deviation points in the online monitoring data of the pollution source, verify the time continuity and deviation of the data, and generate the execution process of the time series deviation record as follows;

[0075] Sub-step S201 constructs a time series of pollution source data based on monitoring data records, arranges the data of each monitoring point in order, and uses high-performance data processing equipment to automatically scan and mark any discontinuities or deviations in the time series, such as sudden increases or decreases in data, indicating equipment failure or abnormal emission events. By calculating the deviation between the data point and the predicted value of the time series, the abnormal points in the time series can be accurately identified. The data continuity of each monitoring point is verified by the dynamic time warping (DTW) algorithm, which is suitable for processing time series data distortion caused by changes in operating conditions and generating time series deviation records. The formula used is:

[0076] ;

[0077] in, represents a measure of the total deviation in the time series, It is The observed value of data points, The first The value of the data point, is the total number of data points.

[0078] S202: Based on the time series deviation record, trend line fitting is performed on the long-term data, the trend and periodic changes of the online monitoring data of the pollution source are identified, normal fluctuations and abnormal trends are analyzed, and the execution process of generating trend analysis results is as follows;

[0079] Substep S202 uses statistical regression analysis to fit long-term data trend lines based on time series deviation records to identify periodicity and trend changes in pollution source data. By comparing real-time data with long-term trend lines, normal data fluctuations can be distinguished from atypical abnormal trends. Linear and nonlinear regression models are used to adapt to data patterns of different types and complexities. Periodic changes are identified through Fourier transform analysis, which can effectively distinguish seasonal and periodic fluctuations in data and generate trend analysis results. The formula used is:

[0080] ;

[0081] in, It's in time data points, is the intercept of the trend line, is the slope of the trend, and are the amplitude and frequency of the periodic function, is the error term.

[0082] S203: Analyze the spatial distribution of abnormal data using trend analysis results, evaluate the data correlation between online monitoring points of differentiated pollution sources, identify the geographical pattern of abnormal distribution, and generate the execution process of abnormal identification results as follows;

[0083] Sub-step S203 uses the trend analysis results to perform spatial distribution analysis of abnormal data, evaluate the data correlation between different pollution source monitoring points, and identify the geographical distribution pattern of abnormal data. Through spatial statistical analysis, such as Kriging interpolation and spatial autocorrelation analysis, the spatial dependence and abnormal clusters between data points are determined to help reveal pollution hot spots and pollution propagation paths, and generate abnormal identification results. The formula used is:

[0084] ;

[0085] in, It's location The pollution index, It is The pollution index of neighboring points, is the spatial weight, is a spatial random error.

[0086] See also Figure 4 ,The integrity and consistency analysis of the pollution source online monitoring data is performed on the abnormal identification results. By comparing the information entropy changes during the data collection time, the steps to generate the data integrity analysis results are as follows:

[0087] S301: Using the abnormal identification results, screen the monitoring points affected by data integrity, conduct data audit on the online monitoring points of the pollution source, check the integrity of the data records, avoid erroneous data records, and generate the execution process of the data integrity audit record as follows;

[0088] Sub-step S301 uses the anomaly identification results to conduct a preliminary screening of the data integrity of all monitoring points, and uses automated tools to review the continuity and logical consistency of each monitoring point record, with special attention to monitoring points that have been marked as abnormal. The data audit program identifies potential errors in data records by comparing the difference between each data point and the prediction of the time series model. For records with missing data or obvious errors, data cleaning and repair operations are performed. For records with inconsistent data consistency, manual review will be conducted to generate data integrity audit records, using the formula:

[0089] ;

[0090] in, Represents the data integrity indicator, It is The actual observed value of the data points, is the predicted value, is a binary function, is the total number of data points.

[0091] S302: Based on the data integrity audit record, the Kalman filter algorithm is used to perform state estimation and error correction on the monitoring point data, and the deviation in the data record is identified by comparing the information entropy changes at the differentiated time. The execution process of generating the information entropy change analysis result is as follows;

[0092] Substep S302 uses the Kalman filter algorithm to perform state estimation and error correction on the monitoring point data based on the data integrity audit record. By building a dynamic model, the data state is continuously estimated and the model is adjusted to adapt to actual observations. By analyzing the Kalman gain and error covariance, errors in data records can be accurately identified and corrected. By comparing the changes in the information entropy of the data, anomalies in the data records can be further identified, and the analysis results of the information entropy changes are generated.

[0093] The formula of the Kalman filter algorithm is as follows:

[0094] ;

[0095] in, For the moment State estimation of observation information, For the moment The previous state estimate, is the Kalman gain, For the moment The real-time observation value of is the observation model matrix, is the smoothing parameter.

[0096] The execution flow is as follows: Calculate the current time Estimated state and use To adjust by The predicted state of the map is The difference between the actual observations introduces an additional history state , and use the Kalman gain of the previous moment To adjust the difference between the previous moment's prediction and the actual observation, use the smoothing parameter To weight the two estimation results, a smoother and more accurate state estimation result is generated. The specific value of can be adjusted by minimizing the prediction error in the historical data set through optimization methods such as gradient descent to ensure the best smoothing effect and prediction accuracy.

[0097] S303: According to the information entropy change analysis results, the data integrity and consistency information of the monitoring points are integrated, the quality of the online monitoring data of the pollution source is evaluated, and the online monitoring data of the pollution source is verified to match the quality standards. The execution process of generating the data integrity analysis results is as follows;

[0098] Sub-step S303 integrates the data integrity and consistency information of the monitoring points based on the information entropy change analysis results, and comprehensively evaluates the quality of the online monitoring data of the pollution source. The data integrity analysis results of each monitoring point are compared with the historical data and quality standards to verify whether the data of each monitoring point meets the predetermined quality standards. A comprehensive evaluation model is used to quantify data quality. The model considers the integrity, consistency and information entropy indicators of the data and generates the data integrity analysis results. The formula used is:

[0099] ;

[0100] in, represents the data quality score, is an indicator of data integrity, is a consistency indicator, is the information entropy, , and is the weight coefficient.

[0101] See also Figure 5 Based on the data integrity analysis results, the steps to generate the optimized monitoring configuration are as follows:

[0102] S401: Based on the data integrity analysis results, the spatial distribution of the online monitoring point data of the pollution source and the real-time configuration of the time interval are analyzed, the optimization space is identified, and the execution process of generating the monitoring point configuration optimization result is as follows;

[0103] Based on the results of data integrity analysis, sub-step S401 identifies potential optimization space. By evaluating the spatial correlation and time series analysis of the data of each monitoring point, redundancy and blind spots in data collection can be identified. Use geographic information system (GIS) and time series analysis tools to conduct in-depth spatial and temporal data exploration to ensure the uniformity and efficiency of monitoring coverage. Use optimization algorithms such as genetic algorithms or simulated annealing to reconfigure the location and time sampling frequency of monitoring points to maximize the coverage area of ​​the monitoring network and the representativeness of the data, and generate the optimization results of the monitoring point configuration. The formula used is:

[0104] ;

[0105] in, To optimize the goal, and Respectively represent The distance and time interval between each monitoring point and its nearest neighboring monitoring point. For monitoring point The number of

[0106] S402: According to the monitoring point configuration optimization results, the spatial layout and time sampling frequency of the online monitoring points of the pollution source are adjusted through the large model artificial intelligence, the efficiency and scope of monitoring data collection are optimized, and the execution process of generating the spatial and temporal adjustment plan is as follows;

[0107] In sub-step S402, based on the optimization results of the monitoring point configuration, the large model artificial intelligence technology is used to readjust the spatial layout and temporal sampling frequency of the monitoring points, and the optimal monitoring point layout and sampling frequency are predicted by analyzing historical data and simulating future scenarios. This not only improves the data collection efficiency of the monitoring network, but also expands the monitoring scope, ensuring that the pollution level in key areas can be effectively monitored, and generates spatial and temporal adjustment plans, using the formula:

[0108] ;

[0109] in, represents the optimal spatial layout of monitoring points, and Monitoring points and The spatial distance and time interval between and are coefficients that adjust the spatial and temporal weights.

[0110] S403: Applying the spatial and temporal adjustment scheme to the data quality of the pollution source monitoring, resetting the data collection parameters of the pollution source online monitoring points, verifying the effectiveness of data collection and monitoring, and generating the optimized monitoring configuration. The execution process is as follows;

[0111] Substep S403 applies the spatial and temporal adjustment scheme to the data quality of the pollution source monitoring, and resets the data collection parameters of each pollution source monitoring point, including sampling frequency and monitoring range. Through simulation and prediction models, the impact of the new configuration on data quality is evaluated to ensure that the data of all monitoring points can meet the preset quality standards. A real-time data verification method is used to monitor the performance of the new configuration in actual applications, ensure the effectiveness of data collection and monitoring, and generate an optimized monitoring configuration using the formula:

[0112] ;

[0113] in, represents the data quality score of the new monitoring configuration, and Respectively represent the data quality after spatial and temporal adjustment, and is the weight coefficient.

[0114] See also Figure 6 , use the optimized monitoring configuration, periodically evaluate and adjust the monitoring equipment parameters, monitor the data quality of the pollution source, refer to environmental changes, dynamically monitor and optimize the equipment correction parameters, and generate the dynamic correction strategy in the following steps:

[0115] S501: Based on the optimized monitoring configuration, the machine learning algorithm is used to intelligently detect the functions and parameters of the monitoring equipment, analyze the consistency of the monitoring equipment running according to the set parameters, monitor the operating status and efficiency of the equipment, and generate the equipment performance evaluation results. The execution process is as follows;

[0116] Based on the optimized monitoring configuration, substep S501 uses machine learning algorithms to intelligently detect the device functions and parameters in the optimized monitoring configuration. By analyzing historical and real-time data, the consistency of each device's operation according to the preset parameters is evaluated, and the operating status and efficiency of the monitoring equipment are monitored. This includes evaluations of multiple dimensions, from the device's response time, data transmission speed to the accuracy of the sensor. It can also identify potential failures or performance degradation of the equipment, adjust the maintenance plan in a timely manner, and generate equipment performance evaluation results.

[0117] The formula for the machine learning algorithm is as follows:

[0118] ;

[0119] in, It is a performance indicator for evaluating pollution source monitoring. is the information entropy, is the pollution source monitoring dataset, To monitor the parameters, Monitoring parameters for monitoring equipment gather, is the number of data points in the sub-dataset for the monitoring parameter, is the total number of data points in the monitoring dataset, and is the regulating factor, To consider monitoring parameters Next data set The parameter variation.

[0120] The execution process is as follows: Calculate the entire monitoring data set Entropy , which measures the information richness of the entire data set. For each monitoring parameter , determine the subset of data that belongs to the parameter And calculate the entropy , calculate each The entire data set The proportion , and calculate the weighted The sum of the entropies of the whole data set minus the sum of the weighted entropies represents the information loss after removing each monitoring parameter, plus the information loss caused by the parameters The resulting data set Variability , multiplied by the weight coefficient ,use The overall effect of adjusting the residual entropy is Comprehensive impact of synthetic performance evaluation indicators ,make sure It can reflect the monitoring system’s responsiveness to environmental changes and data stability.

[0121] S502: According to the equipment performance evaluation results, referring to the changes in the environment around the pollution source, the monitoring equipment parameters are automatically adjusted to match the cyclically changing monitoring environment, the quality of the online monitoring data of the pollution source is evaluated, and the execution process of generating the parameter adjustment record is as follows;

[0122] Substep S502 automatically adjusts the monitoring equipment parameters to adapt to changes in the surrounding environment based on the equipment performance evaluation results. The process includes adjusting the sampling frequency, detection range and sensitivity, etc. to ensure the accuracy and real-time nature of data collection. The automatic adjustment mechanism dynamically optimizes equipment settings based on the pattern of environmental changes and the prediction model, evaluates the quality of online monitoring data of pollution sources, maintains data quality at the optimal level, and generates parameter adjustment records.

[0123] S503: Implement the parameter adjustment record to the pollution source online monitoring network, check the effect of the parameter adjustment through real-time data feedback loop, cyclically update the monitoring equipment correction parameters to match the environment and data change requirements, and generate the execution process of the dynamic correction strategy as follows;

[0124] Sub-step S503 implements the parameter adjustment record to the pollution source online monitoring network, and checks the effect of the parameter adjustment through real-time data feedback loop. The monitoring network continuously receives new environmental data and updates the correction parameters based on data feedback to adapt to the needs of environmental and data changes. The dynamic correction strategy ensures that the monitoring equipment can maintain the monitoring quality in a changing environment, and generates a dynamic correction strategy using the formula:

[0125] ;

[0126] in, is the new calibration parameter, is the old calibration parameter, This is the latest data collected. is the smoothing coefficient, is a function that provides correction suggestions.

[0127] See also Figure 7 ,According to the dynamic correction strategy, through the large model artificial intelligence, the online monitoring data quality control of pollution sources is carried out to verify the consistency with the preset pollution level. The specific steps for generating data quality monitoring results are as follows:

[0128] S601: Based on the dynamic correction strategy, the large model artificial intelligence is used to perform real-time analysis on the monitoring data stream, monitor the quality of the online monitoring data of the pollution source, identify and correct the deviations and anomalies in the data, and generate the execution process of real-time data quality records as follows;

[0129] Sub-step S601 uses large-model artificial intelligence technology based on a dynamic correction strategy to perform real-time analysis of online monitoring data streams of pollution sources to monitor data quality and identify and correct deviations and anomalies in the data. Large-model artificial intelligence achieves rapid recognition and response to complex data patterns by integrating multiple monitoring parameters and environmental factors. Using machine learning models, such as random forests or deep neural networks, each data stream is analyzed in real time to automatically mark data that does not conform to the expected pattern. The marked data is further calibrated or excluded through an automated correction process to generate a real-time data quality record using the formula:

[0130] ;

[0131] in, Represents the real-time data quality assessment results, is a single data point, is the number of data points, and represent the expected value and standard deviation of the data, respectively. is the evaluation function.

[0132] S602: Using real-time data quality records, evaluate the consistency between online monitoring data of pollution sources and environmental changes, compare the preset pollution level with real-time online monitoring data, verify the reliability of the data, and generate the execution process of consistency verification results as follows;

[0133] Substep S602 uses real-time data quality records to evaluate the consistency between online monitoring data of pollution sources and environmental changes, and compares the preset model of environmental changes with the actual monitored pollution data to verify the reliability and accuracy of the data. Through time series analysis and trend matching technology, any anomalies in the data that do not meet the expected environmental changes can be identified and the consistency verification results can be generated. The formula used is:

[0134] ;

[0135] in, is the consistency verification result, It is real-time monitoring data. is the number of data points, is the preset pollution level, is a comparison function.

[0136] S603: Based on the consistency verification results, the overall quality of the online monitoring data of the pollution source is evaluated, the pollution degree is predicted, and the target pollution threshold is adjusted by monitoring the quality of the online monitoring data of the pollution source. The execution process of generating the data quality monitoring results is as follows;

[0137] Substep S603 evaluates the overall quality of online monitoring data of pollution sources based on the consistency verification results, and predicts the degree of pollution. Based on the consistency and quality results of the data, the target pollution threshold is adjusted to reflect the current environmental conditions and pollution trends. The dynamic adjustment strategy enables the monitoring network to respond to environmental changes more flexibly, improve the timeliness and accuracy of the response, and generate data quality monitoring results. The formula used is:

[0138] ;

[0139] in, Indicates the data quality monitoring results. is the quality of the adjusted monitoring data, is the number of data points, is the target contamination threshold, is the correction factor, is the evaluation function.

[0140] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A method for monitoring the quality of online monitoring data of pollution sources, characterized in that: The following steps are involved: Use monitoring equipment to collect data on waste gas emission concentration and wastewater discharge flow from pollution sources, record the time and location of data collection, and generate monitoring data records; Performing time series analysis on the monitoring data records, identifying deviation points and trend anomalies, and evaluating the spatial correlation of online monitoring data of pollution sources, analyzing the distribution area of ​​abnormal data, and generating anomaly identification results; Performing integrity and consistency analysis on the pollution source online monitoring data on the abnormality identification results, and generating data integrity analysis results by comparing the information entropy changes during the data collection time; Based on the data integrity analysis results, the spatial location and time interval of the pollution source monitoring points are adjusted using large-scale model artificial intelligence, data collection parameters are set, and an optimized monitoring configuration is generated; Using the optimized monitoring configuration, periodically evaluate and adjust the monitoring equipment parameters, monitor the data quality of the pollution source, refer to environmental changes, dynamically monitor and optimize the equipment correction parameters, and generate a dynamic correction strategy; According to the dynamic correction strategy, the online monitoring data quality control of the pollution source is carried out through the large model artificial intelligence to verify the consistency with the preset pollution level and generate the data quality monitoring results; The steps of performing integrity and consistency analysis on the pollution source online monitoring data for the abnormal identification results and generating data integrity analysis results by comparing the information entropy changes during the data collection time are as follows: Using the abnormal identification results, screen the monitoring points affected by data integrity, conduct data audit on the online monitoring points of pollution sources, check the integrity of data records, avoid erroneous data records, and generate data integrity audit records; Based on the data integrity audit record, a Kalman filter algorithm is used to perform state estimation and error correction on the monitoring point data, and by comparing the information entropy changes over time, deviations in the data records are identified to generate information entropy change analysis results; According to the information entropy change analysis results, the data integrity and consistency information of the monitoring points are integrated, the quality of the online monitoring data of the pollution source is evaluated, the online monitoring data of the pollution source is verified to match the quality standards, and the data integrity analysis results are generated; The formula of the Kalman filter algorithm is as follows: ,in, For the moment State estimation of observation information, For the moment The previous state estimate, is the Kalman gain, For the moment The real-time observation value of is the observation model matrix, is the smoothing parameter.

2. The method for monitoring the quality of pollution source online monitoring data according to claim 1, characterized in that: The monitoring data records include the exhaust gas emission concentration data, wastewater discharge flow data, data collection time and data collection location of the pollution source; the anomaly identification results include the deviation points of time series analysis, trend anomalies, spatial correlation assessment of pollution sources and distribution areas of abnormal data; the data integrity analysis results include the integrity and consistency level of the data obtained by comparing the changes in information entropy; the optimized monitoring configuration includes the adjusted spatial position of the pollution source monitoring point, the optimized data collection time interval and the reset data collection parameters; the dynamic correction strategy includes the periodic evaluation results of monitoring equipment parameters, the equipment correction parameters dynamically adjusted according to environmental changes and the monitoring of pollution source data quality; the data quality monitoring results include the data quality control scheme controlled by large model artificial intelligence and the consistency assessment verified with the preset pollution degree.

3. The method for monitoring the quality of pollution source online monitoring data according to claim 1, characterized in that: The steps of using monitoring equipment to collect the exhaust gas emission concentration and wastewater discharge flow data of the pollution source, record the data collection time and location, and generate monitoring data records are as follows: Using monitoring equipment, by identifying and recording the location of pollution sources, recording the geographic coordinates of each pollution source online monitoring point, analyzing the spatial positioning of the monitoring point, and generating location positioning records; According to the location positioning record, synchronize the sampling time of each measuring point, bind the timestamp to the measuring point position, check the integrity of each online monitoring data point in time and location, and generate a time and location binding record; Based on the time and location binding records, waste gas emission concentration and wastewater discharge flow data are collected, the data are associated with the time and location records, the integrity of the online monitoring data of the pollution source is verified, and the monitoring data records are generated.

4. The method for monitoring the quality of pollution source online monitoring data according to claim 1, characterized in that: The steps of performing time series analysis on the monitoring data records, identifying deviation points and trend anomalies, evaluating the spatial correlation of online monitoring data of pollution sources, analyzing the distribution area of ​​abnormal data, and generating anomaly identification results are as follows: According to the monitoring data records, a time series is constructed, the data of each online monitoring point of the pollution source is arranged in sequence, the deviation points in the online monitoring data of the pollution source are detected, the time continuity and deviation of the data are verified, and a time series deviation record is generated; Based on the time series deviation records, trend line fitting is performed on long-term data to identify trends and periodic changes in online monitoring data of pollution sources, analyze normal fluctuations and abnormal trends, and generate trend analysis results; The trend analysis results are used to analyze the spatial distribution of abnormal data, evaluate the data correlation between online monitoring points of differentiated pollution sources, identify the geographical pattern of abnormal distribution, and generate anomaly identification results.

5. The method for monitoring the quality of pollution source online monitoring data according to claim 1, characterized in that: Based on the data integrity analysis results, the steps of adjusting the spatial location and time interval of the pollution source monitoring points and setting the data collection parameters to generate the optimized monitoring configuration are as follows: Based on the data integrity analysis results, analyze the spatial distribution of online monitoring point data of pollution sources and the real-time configuration of time intervals, identify optimization space, and generate monitoring point configuration optimization results; According to the monitoring point configuration optimization results, the spatial layout and temporal sampling frequency of the online monitoring points of the pollution sources are adjusted through the large-scale model artificial intelligence, the efficiency and scope of monitoring data collection are optimized, and the spatial and temporal adjustment plan is generated; The spatial and temporal adjustment scheme is applied to the data quality of monitoring pollution sources, the data collection parameters of online monitoring points of pollution sources are reset, the effectiveness of data collection and monitoring is verified, and an optimized monitoring configuration is generated.

6. The method for monitoring the quality of pollution source online monitoring data according to claim 1, characterized in that: The steps of using the optimized monitoring configuration to periodically evaluate and adjust the monitoring equipment parameters, monitor the data quality of the pollution source, dynamically monitor and optimize the equipment correction parameters with reference to environmental changes, and generate a dynamic correction strategy are as follows: Based on the optimized monitoring configuration, a machine learning algorithm is used to intelligently detect the functions and parameters of the monitoring equipment, analyze the consistency of the monitoring equipment running according to the set parameters, monitor the operating status and efficiency of the equipment, and generate equipment performance evaluation results; According to the equipment performance evaluation results, referring to the changes in the environment around the pollution source, automatically adjusting the monitoring equipment parameters to match the cyclically changing monitoring environment, evaluating the quality of the online monitoring data of the pollution source, and generating parameter adjustment records; The parameter adjustment records are implemented in the pollution source online monitoring network, the effect of the parameter adjustment is checked through a real-time data feedback loop, the correction parameters of the monitoring equipment are updated cyclically to match the environment and data change requirements, and a dynamic correction strategy is generated.

7. The method for monitoring the quality of pollution source online monitoring data according to claim 6, characterized in that: The formula for the machine learning algorithm is as follows: in, It is a performance indicator for evaluating pollution source monitoring. Information entropy, is the pollution source monitoring dataset, is the monitoring parameter, V Monitoring parameters for monitoring equipment gather is the number of data points in the sub-dataset for the monitoring parameter is the total number of data points in the monitoring dataset and is the regulating factor, To consider monitoring parameters Next data set The parameter change, is a subset of data.

8. The method for monitoring the quality of pollution source online monitoring data according to claim 1, characterized in that: According to the dynamic correction strategy, the steps of online monitoring data quality control of pollution sources and verification of consistency with the preset pollution level and generating data quality monitoring results are as follows: Based on the dynamic correction strategy, the monitoring data stream is analyzed in real time using large model artificial intelligence to monitor the quality of online monitoring data of pollution sources, identify and correct deviations and anomalies in the data, and generate real-time data quality records; Using the real-time data quality record, evaluate the consistency between the online monitoring data of the pollution source and the environmental changes, compare the preset pollution degree with the real-time online monitoring data, verify the reliability of the data, and generate a consistency verification result; According to the consistency verification results, the overall quality of the online monitoring data of the pollution source is evaluated, the degree of pollution is predicted, and the target pollution threshold is adjusted by monitoring the quality of the online monitoring data of the pollution source to generate data quality monitoring results.

Images