Comprehensive monitoring system of multifunctional mobile monitoring vehicle and control method thereof

Abstract

The invention relates to the technical field of data processing, in particular to a comprehensive monitoring system of a multifunctional mobile monitoring vehicle and a control method of the comprehensive monitoring system. The method comprises the following steps: dividing a time period of monitoring data into a first data mode time period, a second data mode time period and a third data mode time period according to data acquisition mobile data; obtaining time period segmentation nodes of all data acquisition mobile data, and segmenting the time period of the monitoring data to obtain a segmented data set; performing data processing on the segmented data set to obtain in-segment data indexes, and further obtaining pollution standard exceeding duration; in-segment data indexes corresponding to the segmented data are processed through discrete Fourier transform, and monitoring pollution data features are obtained; monitoring pollution data features of the historical data are acquired and processed, and time sequence monitoring pollution data features are generated; and processing the time sequence monitoring pollution data characteristics, obtaining a monitoring area index in combination with the pollution standard exceeding duration, and judging a pollution mode according to the monitoring area index.

Description

Technical Field

[0001] The invention relates to the technical field of data processing, in particular to a comprehensive monitoring system of a multifunctional mobile monitoring vehicle and a control method thereof. Background Art

[0002] Traditional environmental monitoring systems mostly rely on decentralized data collection from fixed sites or single mobile devices. The data from each monitoring unit is isolated and lacks a unified analysis framework, resulting in insufficient spatiotemporal correlation of multi-source heterogeneous data (such as VOCs mass spectrometry, inorganic factors, and meteorological parameters). Especially in mobile navigation scenarios, existing technologies make it difficult to achieve real-time data fusion and dynamic path optimization for multi-vehicle collaboration, and traditional algorithms cannot effectively process massive mass spectrometry data with a response time of seconds (such as a hybrid mode of TOF rapid monitoring and GC-MS precise analysis), resulting in delays in pollution tracing and frequent monitoring blind spots. In addition, the historical data comparison and navigation path playback functions rely on manual operations and lack automated analysis models, which reduces the efficiency of multi-dimensional pollution feature extraction.

[0003] In the existing technology, by building a data processing architecture, integrating multi-vehicle cruise monitoring terminals and cloud-based collaborative analysis platforms, using a spatiotemporal alignment algorithm to unify multi-source data streams (such as VOCs components, meteorological parameters, and GPS trajectories), and introducing machine learning models to achieve pollution diffusion simulation and autonomous path planning. Through multi-threaded parallel computing to optimize the real-time analysis of mass spectrometry data (supporting mixed processing of conventional mass spectrometry, rapid mass spectrometry, and gas chromatography-mass spectrometry data), combined with historical data playback and factor superposition automatic comparison, the positioning accuracy of pollution sources under multi-vehicle collaborative monitoring and dynamic decision-making response speed are improved, effectively solving the bottleneck of data integration and intelligent analysis in complex environmental scenarios.

[0004] Therefore, a comprehensive monitoring system of a multifunctional mobile monitoring vehicle and a control method thereof are proposed. Summary of the invention

[0005] The purpose of the present invention is to provide a comprehensive monitoring system of a multifunctional mobile monitoring vehicle and a control method thereof, so as to improve the pollution monitoring efficiency of traffic congestion areas such as intersections. First, the time period of the monitoring data is divided into the first data mode, the second data mode and the third data mode time period according to the data collection mobile data; the time period segmentation node of all data collection mobile data is obtained, and the time period of the monitoring data is segmented to obtain a segmented data set; the segmented data set is processed to obtain the data index within the segment, and further obtain the pollution exceeding the standard duration; the discrete Fourier transform is used to process the data index within the segment corresponding to the segmented data to obtain the monitoring pollution data characteristics; the monitoring pollution data characteristics of the historical data are obtained and processed to generate the time series monitoring pollution data characteristics; the time series monitoring pollution data characteristics are processed, and combined with the pollution exceeding the standard duration, the monitoring area indicators are obtained, and the pollution mode is judged according to the monitoring area indicators.

[0006] To achieve the above object, the present invention provides the following technical solutions: A comprehensive monitoring and control method for a multifunctional mobile monitoring vehicle, comprising: Collect data according to the data collection period and data collection route to obtain monitoring data; Furthermore, the step of obtaining the data collection period includes: Acquire multi-source data and perform data cleaning and spatiotemporal alignment to obtain multi-source heterogeneous data at intersections; The multi-source heterogeneous data at intersections were clustered and analyzed using a time series clustering analysis algorithm. Combined with historical environmental data, the Spearman correlation coefficient between vehicle flow and pollutants was calculated to screen the data collection period.

[0007] Furthermore, the step of obtaining the data collection route includes: Obtain and process the historical data of the intersection to be monitored, and obtain the first passing time of the intersection to be monitored during the data collection period; according to the number of monitoring vehicles The first passing time and the second passing time between adjacent intersections to be monitored are grouped to obtain sets, where the error between the sum of the first passing time and the second passing time in each set and the other sets is less than an error threshold, and a data collection route is further obtained.

[0008] dividing the time period of the monitoring data into a first data mode, a second data mode and a third data mode time period according to the data collection mobile data; Further, the step of obtaining the time periods of the first data mode, the second data mode and the third data mode includes: An XGBoost model is trained based on historical data, with vehicle speed, acceleration, and engine load as inputs, and outputs data patterns, including a first data pattern, a second data pattern, and a third data pattern; Get complete data collection mobile data, including vehicle speed, acceleration, engine load, etc. Seconds are used as the time window. Feature statistics are calculated through the sliding window, and the feature statistics are input into the trained XGBoost model to determine the data pattern; The time periods of the first data mode, the second data mode and the third data mode are divided according to the time when the data mode is located.

[0009] Obtain the time segmentation nodes of all data collection mobile data, and segment the time period of the monitoring data to obtain a segmented data set; process the segmented data set to obtain the data indicators within the segment, determine whether it exceeds the standard based on the data indicators within the segment, and further obtain the duration of pollution exceeding the standard; Furthermore, the step of obtaining the segmented data set includes: The time period segmentation nodes of all the first data mode, second data mode and third data mode time periods are obtained and merged to obtain a time period segmentation vector; all actual data collection time periods are segmented according to the time period segmentation vector to obtain a segmentation time period set, and a segmented data set is obtained according to the monitoring data corresponding to the segmentation time period.

[0010] Furthermore, the step of obtaining the duration of pollution exceeding the standard includes: Obtain segmented data sets and merge them to construct intra-segment data indicators based on pollution data; construct emission thresholds based on historical data and environmental indicator requirements. If the intra-segment data indicators are greater than the emission thresholds, the corresponding segmented time period will be marked as the first exceeding standard duration; judge all segmented data, and sum up the first exceeding standard duration to obtain the pollution exceeding standard duration.

[0011] Discrete Fourier transform processes the data indicators in the segment corresponding to the segmented data to obtain the characteristics of the monitored pollution data; Acquire and process the monitoring pollution data characteristics of historical data to generate time series monitoring pollution data characteristics; process the time series monitoring pollution data characteristics and combine them with the duration of pollution exceeding the standard to obtain monitoring area indicators, and judge the pollution mode of the area to be monitored based on the monitoring area indicators.

[0012] Furthermore, the steps of obtaining the monitoring area indicators include: The characteristics of the pollution data monitored in time series are processed and combined with the duration of exceeding the standard to obtain the first monitoring area index; the first monitoring area index of all monitoring vehicles is processed to obtain the monitoring area index; if the monitoring area index exceeds the threshold, the pollution mode is severe pollution.

[0013] The present application also provides a comprehensive monitoring system for a multifunctional mobile monitoring vehicle, comprising: A data collection module is used to collect data according to a data collection period and a data collection route to obtain monitoring data; A data segmentation module, for dividing the time period of the monitoring data into a first data mode, a second data mode and a third data mode time period according to the data collection mobile data; The data calculation module includes a data segmentation unit, a data index calculation unit and an over-standard duration calculation unit; wherein the data segmentation unit is used to obtain the time segmentation node of all data collection mobile data, and to segment the time period of the monitoring data to obtain a segmented data set; the data index calculation unit is used to process the segmented data set to obtain the data index within the segment, and the over-standard duration calculation unit is used to determine whether the pollution exceeds the standard according to the data index within the segment, and further obtain the pollution over-standard duration; The feature extraction module is used to process the data indicators in the segment corresponding to the segmented data according to the discrete Fourier transform to obtain the monitoring pollution data characteristics; obtain the monitoring pollution data characteristics of the historical data for processing to generate the time series monitoring pollution data characteristics; process the time series monitoring pollution data characteristics and combine them with the pollution exceeding the standard duration to obtain the monitoring area indicators; The pollution judgment module is used to judge the pollution mode of the area to be monitored based on the monitoring area indicators.

[0014] Compared with the prior art, the present invention has the following beneficial effects: 1. Through the detailed division and optimization of data collection periods and routes, not only can the spatiotemporal consistency and high quality of monitoring data be guaranteed, but also the most sensitive monitoring periods can be screened out. At the same time, historical data is used to calculate the passing time of the intersections to be monitored, and route balancing is achieved through grouping, so that the multifunctional mobile monitoring vehicle can efficiently cover and accurately locate key pollution areas in the entire area. The XGBoost model is then used to perform pattern recognition on the vehicle's driving data, and the data pattern is further subdivided, thereby providing scientific, accurate and efficient data support for environmental pollution warning, source tracing analysis and emergency response.

[0015] 2. Through fine segmentation and construction of intra-segment data indicators to quantify pollution conditions, the spatiotemporal resolution and accuracy of monitoring data have been effectively improved. A unified time segmentation vector is used to segment data under different data modes, and then historical data and emission thresholds set by environmental indicators are combined to determine whether each segmented data exceeds the standard, thereby accurately calculating the duration of pollution exceeding the standard. This not only provides scientific and reliable data support for pollution warning responses, but also further improves the efficiency of overall environmental monitoring.

[0016] 3. The frequency domain characteristics of pollution indicators in the segmented data are extracted through discrete Fourier transform, and then combined with the time series pollution characteristics constructed by historical data and the actual pollution exceeding the standard duration, which can fully reflect the fluctuation, periodicity and cumulative effect of pollutant concentration in the monitoring area. By integrating the first monitoring area indicators of each monitoring vehicle to generate the final monitoring area indicators, and judging the pollution mode based on this, quantitative evaluation and real-time early warning of regional pollution conditions can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A flowchart of a comprehensive monitoring control method for a multifunctional mobile monitoring vehicle provided by an embodiment of the present invention; Figure 2 A flowchart of obtaining a segmented data set provided by an embodiment of the present invention; Figure 3 A schematic structural diagram of a comprehensive monitoring system for a multifunctional mobile monitoring vehicle provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] Embodiment 1: In order to monitor the emission of pollutants at intersections during peak traffic hours, a company introduced a comprehensive monitoring and control method of a multifunctional mobile monitoring vehicle provided by the present invention to improve the monitoring efficiency and accuracy of the emission of pollutants at intersections during peak traffic hours. The process is as follows: Figure 1 As shown, the specific implementation is as follows: Firstly, the historical traffic flow data of the intersections in the monitoring area are processed and analyzed by clustering algorithm to obtain the data collection period and data collection route; Furthermore, the step of obtaining the data collection period includes: Acquire multi-source data and perform data cleaning and spatiotemporal alignment to obtain multi-source heterogeneous data at intersections; multi-source data includes traditional traffic flow data, online car-hailing trajectory density, logistics vehicle GPS, and social media events; The multi-source heterogeneous data at intersections were clustered and analyzed using a time series clustering analysis algorithm. Combined with historical environmental data, the Spearman correlation coefficient between vehicle flow and exhaust pollutants was calculated to screen the data collection period.

[0020] Furthermore, traditional traffic flow data includes data sources such as traffic monitoring cameras, traffic flow sensors, and checkpoint detection equipment, which record the historical traffic flow conditions at each intersection; potential traffic anomalies are monitored through social platform events (such as accidents, gatherings, emergencies, etc.); Furthermore, after removing outliers and interpolating data, the data from different data sources are uniformly mapped to the same spatiotemporal coordinate system to ensure that the timestamps, longitude and latitude information of various types of data are accurately matched, forming complete multi-source heterogeneous data at the intersection; Furthermore, time series clustering analysis is performed on the multi-source heterogeneous data at the intersection according to the time dimension (such as day, week, month) to extract the traffic flow pattern of each time period; common time series clustering algorithms such as K-shape, DTW (dynamic time warping) or DBSCAN are used to find time periods with similar traffic flow characteristics; Furthermore, historical environmental data, including PM2.5, NOx, CO, and VOCs, were obtained as a reference for pollution conditions. The Spearman correlation coefficient between the traffic volume and the concentration of various pollutants in time periods with similar traffic flow characteristics was calculated, and the time periods with strong correlation were selected as data collection periods. The formula is: ; in, Represents the Spearman correlation coefficient, with a value range of [-1, 1]. The larger the absolute value, the stronger the correlation. Indicates The rank difference between the traffic volume and pollutant concentration within the data point (traffic volume ranking - pollutant concentration ranking), Indicates the number of valid data points in the time window. If it is greater than the correlation threshold of 0.6, it indicates the data collection period.

[0021] Table 1. Data collection period Period 1 07:33-08:44 Period 2 11:15-12:45 Period 3 13:23-14:11 Period 4 17:19-18:34 As shown in Table 1, the data collection period of the area to be monitored is selected in this embodiment. Through multi-source heterogeneous data, the dynamic characteristics of the traffic flow can be restored more comprehensively; based on the time series clustering algorithm, the traffic flow fluctuation pattern in different time periods can be accurately identified to avoid the error of judging only by the daily average or hourly average flow, and improve the scientific nature of the data collection period screening; combined with the Spearman correlation coefficient to analyze the strong correlation period between the traffic flow and the pollutant concentration, the pollution source can be effectively identified to improve the pertinence of pollution monitoring.

[0022] Furthermore, the step of obtaining the data collection route includes: Obtain and process the historical data of the intersection to be monitored, and obtain the first passing time of the intersection to be monitored during the data collection period; according to the number of monitoring vehicles The first passing time and the second passing time between adjacent intersections to be monitored are grouped to obtain sets, where the error between the sum of the first passing time and the second passing time in each set and the other sets is less than an error threshold, and a data collection route is further obtained.

[0023] Furthermore, the average time of passing the intersection to be monitored during the data collection period can be calculated based on the historical passing time data of each intersection to be monitored, which is recorded as the first passing time; the average time from the previous intersection to be monitored to the next intersection to be monitored during the data collection period can be calculated based on the historical passing time data between each intersection to be monitored, which is recorded as the second passing time; Furthermore, in this embodiment, there are three multifunctional mobile monitoring vehicles, and the monitored intersections in the monitored area are divided into three sets. The three monitoring vehicles start running at the same time, and the sum of the first passing time and the second passing time in each set is calculated to ensure that the error between the sum of the time in each set and other sets does not exceed the error threshold. For example, the passing time of set 1 is 40 minutes, the passing time of set 2 is 38 minutes, and the passing time of set 3 is 41 minutes, which meets the error threshold of 10 minutes. Such division is acceptable.

[0024] By dividing the intersections to be monitored into multiple groups and assigning a monitoring vehicle to each group, it is ensured that each area can be fully monitored during the data collection period; this grouping method can effectively solve the problem of monitoring vehicles being unable to cover all key nodes due to large areas and too many intersections, thereby improving the integrity and accuracy of pollution data.

[0025] Collect data according to the data collection period and data collection route to obtain monitoring data; Furthermore, the collected data include VOCs, etc.; dividing the time period of the monitoring data into a first data mode, a second data mode and a third data mode time period according to the data collection mobile data; Furthermore, in this embodiment, the data collection mobile data refers to the driving data of the monitoring vehicle, the first data mode refers to the normal driving mode, the second data mode refers to the idle driving mode, and the third data mode refers to the start-stop driving mode. Further, the step of obtaining the time periods of the first data mode, the second data mode and the third data mode includes: An XGBoost model is trained based on historical data, with vehicle speed, acceleration, and engine load as inputs, and outputs data patterns, including a first data pattern, a second data pattern, and a third data pattern; Get complete data collection mobile data to Seconds are used as the time window. Feature statistics are calculated through the sliding window, and the feature statistics are input into the trained XGBoost model to determine the data pattern; The time periods of the first data mode, the second data mode and the third data mode are divided according to the time when the data mode is located.

[0026] Furthermore, through the hardware devices such as the vehicle-mounted GPS module, vehicle speed sensor, accelerometer, engine control module (ECU) and vibration sensor of the multifunctional mobile monitoring vehicle, the data collection mobile data of the monitoring vehicle can be obtained, including but not limited to vehicle speed, acceleration, engine complexity and vehicle vibration intensity (such as vibration amplitude and vibration frequency); Furthermore, the historical driving data is cleaned, anomalies, invalid data and noise interference are removed, and the vehicle speed, acceleration, engine load and vehicle vibration data are normalized to ensure the consistency of feature dimensions. The time series data is sliced ​​into second-level time windows as training samples for the XGBoost model. The label data clearly defines the data mode (first data mode, second data mode and third data mode) corresponding to each time window. After training, a trained XGBoost model is obtained. Further, the complete data collection mobile data is The time window is divided into seconds, and a sliding window mechanism is used to improve the timeliness and accuracy of recognition. The following feature statistics are calculated in each time window, including vehicle speed, acceleration, engine load, and vehicle vibration data. The obtained feature statistics are input into the trained XGBoost model and output as a data model.

[0027] Further, after the complete data collection mobile data processing is completed, the actual data collection time period is divided according to the obtained data pattern, and the time periods of adjacent patterns are merged into the same pattern to obtain the first data pattern, the second data pattern and the third data pattern time period; Furthermore, the actual data collection period refers to the time actually spent by the monitoring vehicle in the process of data collection, which is not the same as the data collection period mentioned above. The above-mentioned data collection period is only a time window for data collection; the length of the actual data collection period is approximately the sum of the first and second passing times in the above-mentioned set, but is not exactly the same.

[0028] Through the division and judgment of data by XGBoost model and the introduction of sliding windows, the interference of instantaneous data fluctuations on the judgment results is significantly reduced, and the accuracy of data pattern recognition is improved; the impact of different driving modes on pollutant emissions is significantly different. In the second data mode time period, the engine is running but the speed is low, and the exhaust emission efficiency is low, which may become a key period for pollutant accumulation. In the third data mode time period, there is frequent acceleration and braking, and the instantaneous emission of pollutants is high. In the first data mode time period, the engine runs stably and the pollutant emissions are more uniform. The time periods are accurately divided to optimize pollution monitoring and analysis.

[0029] Obtain the time segmentation nodes of all data collection mobile data, and segment the time period of the monitoring data to obtain a segmented data set; process the segmented data set to obtain the data indicators within the segment, determine whether it exceeds the standard based on the data indicators within the segment, and further obtain the duration of pollution exceeding the standard; Furthermore, the process of obtaining the segmented data set is as follows Figure 2 As shown, including: The time period segmentation nodes of the first data mode, the second data mode and the third data mode time periods of all monitoring vehicles are obtained and merged to obtain a time period segmentation vector; the actual data collection time period of all multifunctional mobile monitoring vehicles is segmented according to the time period segmentation vector to obtain a segmentation time period set; and a segmented data set of each monitoring vehicle is obtained according to the monitoring data corresponding to the elements in the segmentation time period set.

[0030] Furthermore, the vehicle status (including the first data mode, the second data mode and the third data mode) of each multifunctional mobile monitoring vehicle is first processed, and the time nodes of each mode switching are identified based on the results obtained by the previously trained XGBoost model. These switching nodes are the key time points when the monitoring vehicle switches from one mode to another.

[0031] Furthermore, the time segmentation nodes extracted by each monitoring vehicle are merged and normalized to generate a unified "time segmentation vector", which can reflect the pattern distribution of different time periods in the entire monitoring system and provide a unified standard for subsequent time segmentation; Furthermore, the time segmentation vector obtained above is used to segment the actual data collection time periods of all monitoring vehicles; here, the continuous operation time of each monitoring vehicle is divided into multiple continuous sub-time periods according to the segmentation node, and each sub-time period corresponds to a section of pollution data collected by the monitoring vehicle; Furthermore, the above processing is performed on all the data to obtain a segmented data set for each monitoring vehicle.

[0032] The continuous monitoring data is segmented according to time period nodes so that each data segment has a clear time period label, reducing the noise caused by mixed patterns and ensuring the consistency of the internal pattern of each data segment, thereby improving data quality and the reliability of subsequent analysis; significantly improving the efficiency of pollution source tracing, real-time monitoring and supervision, and providing solid data support and scientific basis for environmental pollution monitoring and control.

[0033] Furthermore, the step of obtaining the duration of pollution exceeding the standard includes: Acquire segmented data sets and merge them to construct intra-segment data indicators based on the collected pollution data such as VOCs and other parameters; construct emission thresholds based on historical data and environmental indicator requirements. If the intra-segment data indicator is greater than the emission threshold, the duration of the corresponding segmented time period will be marked as the first exceeding standard duration; judge all segmented data of the monitoring vehicle, and sum up the first exceeding standard duration to obtain the pollution exceeding standard duration monitored by the monitoring vehicle.

[0034] Furthermore, the calculation formula for the intra-segment data index is: ; in, Indicates the data index within the segment. Indicates the number of pollutant types, Indicates The average concentration of a pollutant in a given period of time. Indicates The emission thresholds of various pollutants are set according to national or local standards. Indicates The weight coefficient of each pollutant reflects its contribution to exceeding the standard. Indicates the duration of the time period. The longer the time, the greater the impact.

[0035] Furthermore, if the data indicator within the segment is greater than the emission threshold, the time period corresponding to the segmented data is marked as the first exceeding standard duration; all segmented data sets of the monitoring vehicle are judged, and the first exceeding standard duration is summed to obtain the pollution exceeding standard duration monitored by the monitoring vehicle.

[0036] By using segmented data sets, the pollution data collected by the monitoring vehicle in different time periods can be finely divided to ensure that the patterns in each data segment are consistent, thereby more accurately reflecting the actual pollution level in that segment; by calculating the data indicators within the segment and combining the average concentration, emission standards and weights of each pollutant, the pollution load in different time periods can be objectively quantified, providing a precise data basis for judging the exceeding of the standard; taking the duration into consideration means that the same average concentration has a greater pollution effect over a long period of time, and this design is closer to the actual environmental impact.

[0037] Discrete Fourier transform processes the data indicators in the segment corresponding to the segmented data to obtain the characteristics of the monitored pollution data; Acquire and process the monitoring pollution data characteristics of historical data to generate time series monitoring pollution data characteristics; process the time series monitoring pollution data characteristics and combine them with the duration of pollution exceeding the standard to obtain monitoring area indicators, and judge the pollution mode of the area to be monitored based on the monitoring area indicators.

[0038] Furthermore, the steps of obtaining the monitoring area indicators include: The time series monitoring pollution data characteristics of each multifunctional mobile monitoring vehicle are processed and combined with the duration of exceeding the standard to obtain the first monitoring area index; the first monitoring area indicators of all multifunctional mobile monitoring vehicles are processed to obtain the monitoring area index. If the monitoring area index exceeds the threshold, the pollution mode of the monitored area is severe pollution.

[0039] Furthermore, the intra-segment data indicators in each time period can be regarded as a discrete time signal, which reflects the change and accumulation of pollutant concentrations within a certain period of time. DFT is used to convert the intra-segment data indicators in each time period from the time domain to the frequency domain. Through the conversion, the spectrum information of the signal can be obtained, such as the main frequency components, amplitude and phase information. These frequency domain characteristics can reveal the potential periodic fluctuations (such as daily cycles and weekly cycles, etc.) in the pollution data collected by the monitoring vehicle during the actual data collection period and the frequency characteristics of sudden pollution events.

[0040] Furthermore, the main frequency components (such as the frequency corresponding to the maximum amplitude), spectrum energy distribution (reflecting the overall fluctuation intensity) and phase information (describing the time series characteristics of pollutant concentration fluctuations) are extracted from the spectrum. These characteristics will be used to quantify the pollution pattern in the current monitoring data segment and be compared and analyzed with the subsequent historical data characteristics; Furthermore, the same method (i.e., discrete Fourier transform of the data indicators in the segment corresponding to the segmented data set) is used to extract the frequency domain features of the monitoring pollution data from the historical data; the frequency domain features extracted in each historical time period are arranged in chronological order to form a complete time series monitoring pollution data feature; Furthermore, based on the above information, the first monitoring area index can be constructed, which can be expressed as: ; in, Indicates the first monitoring area indicator, Indicates the monitoring pollution data characteristics (such as main frequency, amplitude, energy distribution, etc.) extracted by DFT from each segment data of the current monitoring vehicle. represents the characteristics of time series monitoring pollution data, Indicates the duration of pollution exceeding the standard corresponding to the monitoring vehicle, function It can be constructed through weighted averaging, principal component analysis or machine learning models (such as multivariate regression) to output a quantitative first monitoring area indicator, which is convenient for comprehensive evaluation of different regions or time periods.

[0041] Furthermore, the first monitoring area indicators of all the multifunctional mobile monitoring vehicles are summed and weighted to obtain the monitoring area indicator of the area to be monitored. If it exceeds a threshold, the pollution mode of the area to be monitored is severe pollution.

[0042] Table 2. Regional monitoring indicators Period Number Regional monitoring indicators A023 0.78 A024 0.76 A025 0.77 A026 0.76 As shown in Table 2, the monitoring area indicators of the monitored area monitored in some time periods do not exceed the threshold of 0.9. By performing DFT processing on the cumulative indicators of the segmented data, the main frequency components, amplitude and phase information can be extracted from the frequency domain. These frequency domain characteristics can reveal the periodic fluctuations and emergency characteristics within the data segment; incorporating the key indicator of pollution exceeding the standard duration into the comprehensive assessment can better reflect the cumulative effect of long-term excessive concentrations of pollutants; extracting and quantifying the frequency domain characteristics of the monitoring data through discrete Fourier transform, and combining it with the exceeding duration and historical data characteristics, can comprehensively and finely describe the pollution situation in the region, thereby improving the accuracy, timeliness and decision-making support capabilities of pollution monitoring, and providing a scientific and reliable basis for environmental early warning and governance.

[0043] Through multi-source data cleaning, time-space alignment, data pattern recognition, fine segmentation, pollution index construction and frequency domain feature extraction, the whole process from data collection to pollution exceeding the standard duration and monitoring area indicators is automatically analyzed; this method not only improves the accuracy and time-space consistency of data collection, but also effectively captures the periodic fluctuations and emergency characteristics of pollutant concentrations through fine segmentation processing and DFT frequency domain analysis of the data of each monitoring vehicle; at the same time, combined with the pollution exceeding the standard duration, a comprehensive regional pollution index is constructed to achieve accurate judgment and real-time warning of the pollution mode of the monitored area, providing scientific, comprehensive and timely decision-making support for environmental management and pollution control.

[0044] Embodiment 2: The present application also provides a comprehensive monitoring system for a multifunctional mobile monitoring vehicle, the system structure of which is as follows: Figure 3 As shown, the specific implementation is as follows: A data collection module is used to collect data according to a data collection period and a data collection route to obtain monitoring data; Furthermore, the step of obtaining the data collection period includes: Acquire multi-source data and perform data cleaning and spatiotemporal alignment to obtain multi-source heterogeneous data at intersections; The multi-source heterogeneous data at intersections were clustered and analyzed using a time series clustering analysis algorithm. Combined with historical environmental data, the Spearman correlation coefficient between vehicle flow and pollutants was calculated to screen the data collection period.

[0045] Furthermore, the step of obtaining the data collection route includes: Obtain and process the historical data of the intersection to be monitored, and obtain the first passing time of the intersection to be monitored during the data collection period; according to the number of monitoring vehicles The first passing time and the second passing time between adjacent intersections to be monitored are grouped to obtain sets, where the error between the sum of the first passing time and the second passing time in each set and the other sets is less than an error threshold, and a data collection route is further obtained.

[0046] A data segmentation module, for dividing the time period of the monitoring data into a first data mode, a second data mode and a third data mode time period according to the data collection mobile data; Further, the step of obtaining the time periods of the first data mode, the second data mode and the third data mode includes: An XGBoost model is trained based on historical data, with vehicle speed, acceleration, and engine load as inputs, and outputs data patterns, including a first data pattern, a second data pattern, and a third data pattern; Get complete data collection mobile data to Seconds are used as the time window. Feature statistics are calculated through the sliding window, and the feature statistics are input into the trained XGBoost model to determine the data pattern; The time periods of the first data mode, the second data mode and the third data mode are divided according to the time when the data mode is located.

[0047] The data calculation module includes a data segmentation unit, a data index calculation unit and an over-standard duration calculation unit; wherein the data segmentation unit is used to obtain the time segmentation node of all data collection mobile data, and to segment the time period of the monitoring data to obtain a segmented data set; the data index calculation unit is used to process the segmented data set to obtain the data index within the segment, and the over-standard duration calculation unit is used to determine whether the pollution exceeds the standard according to the data index within the segment, and further obtain the pollution over-standard duration; Furthermore, the step of obtaining the segmented data set includes: The time period segmentation nodes of all the first data mode, second data mode and third data mode time periods are obtained and merged to obtain a time period segmentation vector; all actual data collection time periods are segmented according to the time period segmentation vector to obtain a segmentation time period set, and a segmented data set is obtained according to the monitoring data corresponding to the segmentation time period.

[0048] Furthermore, the step of obtaining the duration of pollution exceeding the standard includes: Get segmented data sets and build segment data indicators based on pollution data; build emission thresholds based on historical data and environmental indicator requirements. If the segment data indicator is greater than the emission threshold, the corresponding segmented time period will be marked as the first exceeding standard duration; judge all segmented data, and sum up the first exceeding standard duration to obtain the pollution exceeding standard duration. Table 3 shows the pollution exceeding standard duration counted by the four multifunctional mobile monitoring vehicles during this monitoring process.

[0049] Table 3. Duration of pollution exceeding the standard Vehicle number Actual data collection period Duration of pollution exceeding the standard JC001 2024.8.18 13:02-14:23 32min24s JC002 2024.8.18 13:01-14:17 31min15s JC003 2024.8.18 13:00-14:20 30min49s JC004 2024.8.18 13:04-14:19 31min25s The feature extraction module is used to process the data indicators in the segment corresponding to the segmented data according to the discrete Fourier transform to obtain the monitoring pollution data characteristics; obtain the monitoring pollution data characteristics of the historical data for processing to generate the time series monitoring pollution data characteristics; process the time series monitoring pollution data characteristics and combine them with the pollution exceeding the standard duration to obtain the monitoring area indicators; Furthermore, the steps of obtaining the monitoring area indicators include: The characteristics of the pollution data monitored in time series are processed and combined with the duration of exceeding the standard to obtain the first monitoring area index; the first monitoring area index of all monitoring vehicles is processed to obtain the monitoring area index.

[0050] The pollution judgment module is used to judge the pollution mode of the monitored area according to the monitoring area indicators. If the monitoring area indicators exceed the threshold, the pollution mode is severe pollution.

[0051] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A comprehensive monitoring and control method for a multifunctional mobile monitoring vehicle, characterized in that: include: Collect data according to the data collection period and data collection route to obtain monitoring data; dividing the time period of the monitoring data into a first data mode, a second data mode and a third data mode time period according to the data collection mobile data; Obtain the time segmentation nodes of all data collection mobile data, and segment the time period of the monitoring data to obtain a segmented data set; process the segmented data set to obtain the data indicators within the segment, determine whether it exceeds the standard based on the data indicators within the segment, and further obtain the duration of pollution exceeding the standard; Discrete Fourier transform processes the data indicators in the segment corresponding to the segmented data to obtain the characteristics of the monitored pollution data; Acquire and process the monitoring pollution data characteristics of historical data to generate time series monitoring pollution data characteristics; The characteristics of time series monitoring pollution data are processed and combined with the duration of pollution exceeding the standard to obtain the monitoring area indicators, and the pollution pattern of the area to be monitored is determined based on the monitoring area indicators.

2. The comprehensive monitoring and control method of a multifunctional mobile monitoring vehicle according to claim 1 is characterized in that: The steps to obtain the data collection period include: Acquire multi-source data and perform data cleaning and spatiotemporal alignment to obtain multi-source heterogeneous data at intersections; The multi-source heterogeneous data at intersections were clustered and analyzed using a time series clustering analysis algorithm. Combined with historical environmental data, the Spearman correlation coefficient between vehicle flow and pollutants was calculated to screen the data collection period.

3. The comprehensive monitoring and control method of a multifunctional mobile monitoring vehicle according to claim 1 is characterized in that: The steps to obtain the data collection route include: Obtain and process the historical data of the intersection to be monitored, and obtain the first passing time of the intersection to be monitored during the data collection period; according to the number of monitoring vehicles The first passing time and the second passing time between adjacent intersections to be monitored are grouped to obtain sets, where the error between the sum of the first passing time and the second passing time in each set and the other sets is less than an error threshold, and a data collection route is further obtained.

4. The comprehensive monitoring and control method of a multifunctional mobile monitoring vehicle according to claim 1 is characterized in that: The steps of obtaining the first data mode, the second data mode and the third data mode time periods include: An XGBoost model is trained based on historical data, with vehicle speed, acceleration, and engine load as inputs, and outputs data patterns, including a first data pattern, a second data pattern, and a third data pattern; Get complete data collection mobile data to Seconds are used as the time window. Feature statistics are calculated through the sliding window, and the feature statistics are input into the trained XGBoost model to determine the data pattern; The time periods of the first data mode, the second data mode and the third data mode are divided according to the time when the data mode is located.

5. The comprehensive monitoring and control method of a multifunctional mobile monitoring vehicle according to claim 1 is characterized in that: The steps of obtaining the segmented data set include: The time period segmentation nodes of all the first data mode, second data mode and third data mode time periods are obtained and merged to obtain a time period segmentation vector; all actual data collection time periods are segmented according to the time period segmentation vector to obtain a segmentation time period set, and a segmented data set is obtained according to the monitoring data corresponding to the segmentation time period.

6. The comprehensive monitoring and control method of a multifunctional mobile monitoring vehicle according to claim 1 is characterized in that: The steps to obtain the duration of pollution exceeding the standard include: Obtain segmented data sets and merge them to construct intra-segment data indicators based on pollution data; construct emission thresholds based on historical data and environmental indicator requirements. If the intra-segment data indicators are greater than the emission thresholds, the corresponding segmented time period will be marked as the first exceeding standard duration; judge all segmented data, and sum up the first exceeding standard duration to obtain the pollution exceeding standard duration.

7. The comprehensive monitoring and control method of a multifunctional mobile monitoring vehicle according to claim 1 is characterized in that: The steps to obtain indicators for the monitoring area include: The characteristics of the pollution data monitored in time series are processed and combined with the duration of exceeding the standard to obtain the first monitoring area index; the first monitoring area index of all monitoring vehicles is processed to obtain the monitoring area index; if the monitoring area index exceeds the threshold, the pollution mode is severe pollution.

8. A comprehensive monitoring system for a multifunctional mobile monitoring vehicle, characterized in that: include: A data collection module is used to collect data according to a data collection period and a data collection route to obtain monitoring data; A data segmentation module, for dividing the time period of the monitoring data into a first data mode, a second data mode and a third data mode time period according to the data collection mobile data; The data calculation module includes a data segmentation unit, a data index calculation unit and an over-standard duration calculation unit; wherein the data segmentation unit is used to obtain the time segmentation nodes of all data collection mobile data, and to segment the time period of the monitoring data to obtain a segmented data set; the data index calculation unit is used to process the segmented data set to obtain the data index within the segment; the over-standard duration calculation unit is used to determine whether the pollution exceeds the standard according to the data index within the segment, and further obtain the pollution over-standard duration; The feature extraction module is used to process the data indicators in the segment corresponding to the segmented data according to the discrete Fourier transform to obtain the monitoring pollution data characteristics; obtain the monitoring pollution data characteristics of the historical data for processing to generate the time series monitoring pollution data characteristics; Process the characteristics of time series monitoring pollution data and combine them with the duration of pollution exceeding the standard to obtain the monitoring area indicators; The pollution judgment module is used to judge the pollution mode of the area to be monitored based on the monitoring area indicators.

Images