Method for monitoring methane concentration in expressway service area and related equipment

Abstract

The invention provides a monitoring method for methane concentration in an expressway service area and related equipment, and relates to the technical field of gas monitoring. A dynamic association model is constructed by acquiring parameter data of indirect replacement gas concentration and methane concentration under different time periods and environmental conditions of a highway service area so as to determine an association relationship between the indirect replacement gas concentration and the methane concentration. And acquiring environmental monitoring data and indirect replacement gas concentration of a target time period by using monitoring equipment of a plurality of monitoring points in the service area, inputting the data into the dynamic correlation model, and finally outputting to obtain the methane concentration. Therefore, the rule that the gas concentration in the service area changes along with the environment can be truly reflected, and compared with a static model constructed under a single environment condition, the accuracy of methane concentration monitoring is improved.

Description

Technical Field

[0001] The present application relates to the field of gas monitoring technology, and in particular to a method and related equipment for monitoring methane concentration in a highway service area. Background Art

[0002] As the world pays more and more attention to environmental protection, the monitoring and control of greenhouse gas emissions has become an important research direction. As a densely populated area with people and vehicles, the gas emissions generated by highway service areas have a certain impact on the environment. Among them, methane is an important greenhouse gas, and accurate monitoring of its concentration is of great significance.

[0003] In the prior art, gas concentration monitoring usually uses a single sensor to measure at a fixed location and fixed time period. For example, in some industrial areas or environmental monitoring points, fixed methane sensors are set up to collect methane concentration data at fixed time intervals (such as once an hour). At the same time, the consideration of environmental conditions is also relatively simple, generally only recording the approximate temperature range during measurement.

[0004] However, this fixed monitoring method is difficult to adapt to the complex and changing environment of highway service areas. Since the traffic volume, pedestrian flow and surrounding environment of the service area vary greatly at different times and under different weather conditions, the data collected by a single sensor at a fixed location and fixed time period is difficult to fully reflect the true situation of methane concentration in the service area. Summary of the invention

[0005] The present application provides a method and related equipment for monitoring methane concentration in a highway service area, which are used to monitor the changes in methane concentration in a highway service area in real time and dynamically.

[0006] In the first aspect, the present application provides a method for monitoring methane concentration in a highway service area, which is applied to a monitoring management server, including: constructing a dynamic correlation model by acquiring indirect replacement gas concentration and methane concentration parameter data of the highway service area under different time periods and environmental conditions, and the dynamic correlation model is used to determine the correlation between the indirect replacement gas and the methane concentration; determining the environmental monitoring data and the indirect replacement gas concentration in the target time period by monitoring equipment set at multiple monitoring points in the service area; inputting the indirect replacement gas concentration and the environmental monitoring data into the dynamic correlation model, and outputting the methane concentration.

[0007] By adopting the above technical solution, gas concentration monitoring data under different time periods and different environmental conditions can be obtained. The constructed dynamic correlation model can therefore truly reflect the law of gas concentration changes in the service area with the environment. Compared with the static model constructed under a single environmental condition, it can greatly improve the accuracy of concentration prediction.

[0008] In combination with some embodiments of the first aspect, in some embodiments, the step of constructing a dynamic correlation model by obtaining indirect replacement gas concentration and methane concentration parameter data of the service area of ​​the highway under different time periods and environmental conditions specifically includes: obtaining temperature and humidity data of the monitoring point through a temperature and humidity sensor set at the monitoring point, obtaining weather data within a preset range of the monitoring point through a meteorological terminal, and monitoring gas concentration data through a gas sensor set at the monitoring point, wherein the gas concentration data includes at least indirect replacement gas concentration and methane concentration; after obtaining the temperature and humidity data, the weather data and the gas concentration data of each monitoring point under different time periods, using a machine learning algorithm to train to obtain an initial dynamic correlation model; and using newly collected monitoring point data to optimize the dynamic correlation model until the prediction error of the dynamic correlation model meets preset requirements.

[0009] By adopting the above technical solution, we can obtain the detailed environmental parameters of each monitoring point at different time periods. The initial dynamic correlation model trained by machine learning has reflected the relationship between gas concentration and environmental changes. Subsequent new data will further optimize the model, which can continuously reduce the prediction error, so that the final model can describe the dynamic change law of gas concentration in the service area with high accuracy.

[0010] In combination with some embodiments of the first aspect, in some embodiments, after the step of constructing a dynamic correlation model by obtaining parameter data of indirect replacement gas concentration and methane concentration in the service area of ​​the highway under different time periods and environmental conditions, it also includes: setting an image monitoring device to obtain images of vehicles passing through each monitoring point, and determining vehicle information through image recognition algorithm analysis, where the vehicle information includes vehicle type and fuel type; after obtaining the traffic flow and vehicle composition data of each monitoring point at different time periods, analyzing the influence relationship between the flow of different types of vehicles and the indirect replacement gas and methane concentrations; and adjusting the dynamic correlation model according to the influence relationship.

[0011] By adopting the above technical solution, the contribution of different vehicle models can be quantified and analyzed, and used as a parameter to adjust the dynamic correlation model. The adjusted model can take into account the impact of vehicle model factors on gas concentration, and the prediction results will be more accurate and reliable.

[0012] In combination with some embodiments of the first aspect, in some embodiments, after obtaining the vehicle flow and vehicle composition data of each monitoring point in different time periods, the step of analyzing the influence relationship between the flow of different types of vehicles and the indirect replacement gas and methane concentrations specifically includes: determining the flow distribution of each vehicle model based on the vehicle flow and the vehicle composition data; obtaining the indirect replacement gas concentration and methane concentration within the target time period, and comparing and analyzing the flow distribution and gas concentration change characteristics of different vehicle models within the target time period; determining the contribution of different vehicle models to the indirect replacement gas concentration based on the flow distribution and the gas concentration change characteristics; and adjusting the vehicle model related parameters in the dynamic association model according to the contribution degree.

[0013] By adopting the above technical solution, the flow data of each vehicle type in the target period can be accurately obtained, and the impact of different vehicle types can be analyzed in combination with the change of gas concentration. By adjusting the parameters of the dynamic model according to the analysis results, a quantitative relationship between vehicle type and gas concentration can be established, thereby improving the adaptability of the model.

[0014] In combination with some embodiments of the first aspect, in some embodiments, after the step of adjusting the dynamic correlation model according to the influence relationship, it also includes: after determining the vehicle information of the target time period through an image monitoring device, the environmental monitoring data and the indirect replacement gas concentration corresponding to the target time period are input into the adjusted dynamic correlation model to determine the final methane concentration.

[0015] By adopting the above technical solution, the adjusted dynamic correlation model comprehensively considers the vehicle model factors. After inputting the monitoring data of the target period, the output methane concentration prediction value will more accurately reflect the impact of different vehicle model compositions on the actual concentration.

[0016] In combination with some embodiments of the first aspect, in some embodiments, after the step of constructing a dynamic correlation model by obtaining indirect replacement gas concentration and methane concentration parameter data of the service area of ​​the highway under different time periods and environmental conditions, it also includes: obtaining real-time meteorological data of the highway service area to determine whether the current meteorological conditions are extreme; if they are extreme meteorological conditions, correcting the dynamic correlation model.

[0017] By adopting the above technical solution, it is possible to timely determine whether the current weather conditions are extreme. If so, using data samples under extreme conditions to correct the dynamic model can significantly improve the prediction accuracy of the model under extreme weather conditions and expand the scope of application of the model.

[0018] In combination with some embodiments of the first aspect, in some embodiments, after the step of inputting the indirect replacement gas concentration into the dynamic correlation model and outputting the methane concentration, it also includes: after obtaining multiple historical monitoring data, setting normal threshold values ​​of methane concentration for different time periods according to the historical monitoring data; comparing the methane concentration with the normal threshold value of the methane concentration for the corresponding time period to determine whether it is abnormal; if there is an abnormality, sending an alarm message to a preset monitoring end.

[0019] By adopting the above technical solution, historical data can be used to determine the normal concentration threshold. By comparing the real-time monitoring data with the threshold, abnormal concentrations can be quickly discovered, and timely alarms can be issued to remind relevant personnel to take measures, which can effectively reduce the risk of accidents.

[0020] In a second aspect, the present application provides a server, comprising: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to cause the server to execute the method described in the first aspect and any possible implementation of the first aspect.

[0021] In a third aspect, the present application provides a computer-readable storage medium comprising instructions, which, when executed on a server, causes the server to execute the method described in the first aspect and any possible implementation of the first aspect.

[0022] In a fourth aspect, the present application provides a computer program product, which, when executed on a server, enables the server to execute the method described in the first aspect and any possible implementation manner of the first aspect.

[0023] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. The technical means of building a dynamic correlation model by collecting gas concentration data in combination with different time periods and environmental conditions is adopted. Therefore, the problem that the static model in the existing technology is difficult to adapt to environmental changes is effectively solved, thereby achieving the improvement of the accuracy of gas concentration prediction.

[0024] 2. Due to the adoption of technical means to identify vehicle models and analyze the impact of different vehicle models on gas concentration, the problem of prediction deviation caused by the existing technology not considering vehicle model differences is effectively solved, thereby achieving accurate prediction of the impact of different vehicle model compositions on gas concentration.

[0025] 3. By adopting the technical means of identifying extreme meteorological conditions and using corresponding data to adjust the model, the problem of large prediction deviations of existing technical models in extreme environments is effectively solved, thereby expanding the scope of application of the model and improving the robustness of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a flow chart of a method for monitoring methane concentration in a highway service area in an embodiment of the present application; Figure 2 is another flow chart of the method for monitoring methane concentration in a highway service area in an embodiment of the present application; Figure 3 It is a schematic diagram of the structure of a physical device for monitoring the management server in an embodiment of the present application. DETAILED DESCRIPTION

[0027] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification and appended claims of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to and includes any or all possible combinations of one or more listed items.

[0028] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0029] Methane is a flammable gas. When the methane concentration in the air reaches a certain range (5%-15%), it will explode when it encounters a fire source. By monitoring the methane concentration, potential explosion hazards can be discovered in a timely manner to ensure the safety of people in the service area. For example, there are places such as gas stations and restaurant kitchens in highway service areas where fire sources may occur. Monitoring the methane concentration can effectively prevent explosion accidents caused by methane leaks. Methane is also a powerful greenhouse gas. Monitoring the methane concentration helps to comprehensively count and control greenhouse gas emissions. Since indirect gas monitoring costs are low, and high-precision methane sensors are expensive, the cost of large-scale deployment at multiple monitoring points is high, and indirect gas sensors are relatively cheap, this application mainly reverses the methane concentration through the indirect replacement gas concentration in the service area.

[0030] For ease of understanding, the following is a description of the process of the method provided by this implementation. Figure 1 , is a flow chart of a method for monitoring methane concentration in a highway service area in an embodiment of the present application.

[0031] S101, constructing a dynamic correlation model by acquiring indirect replacement gas concentration and methane concentration parameter data of a service area of ​​a highway under different time periods and environmental conditions, wherein the dynamic correlation model is used to determine the correlation relationship between the indirect replacement gas and the methane concentration; Staff can set up monitoring points near the drain outlet in advance, because the decomposition of organic matter in sewage may produce methane and related indirect replacement gases. At the same time, areas where diesel vehicles gather are also key monitoring areas, and incomplete combustion of diesel engines may emit some methane-related gas components. At these monitoring points, a variety of sensor equipment are deployed. The temperature and humidity sensor is used to obtain the temperature and humidity data of the environment. Its accuracy must be able to accurately reflect minor environmental changes, such as temperature measurement accuracy of ±0.1°C and humidity measurement accuracy of ±2%RH. The gas sensor must have high sensitivity and selectivity, and be able to accurately distinguish and measure the concentration of indirect replacement gases and methane. In this step, the sensor that monitors the methane concentration can be a high-precision sensor with a detection limit as low as the ppm level. For example, the detection limit for methane reaches 1ppm. The indirect replacement gas concentration in this application mainly refers to some easily measured gases, such as carbon dioxide.

[0032] Collect data at different times. The environment of the service area will change significantly within 24 hours a day. For example, there is a large amount of traffic during the day, and vehicle emissions have a greater impact on gas concentration; vehicle activity decreases at night, but there may be other factors that affect gas concentration, such as the operating status of sewage treatment facilities at night. Therefore, data collection should be carried out at certain time intervals, such as collecting data once an hour. At the same time, different environmental conditions should be considered, including different weather conditions (sunny, rainy, cloudy, foggy, etc.) and seasonal changes obtained from the meteorological terminal. When collecting data, ensure the accuracy and completeness of the data, perform real-time verification of the collected data, and eliminate outliers. For temperature and humidity data, if the collected temperature value exceeds the reasonable range under normal local climatic conditions (such as in summer, the temperature is higher than 50°C or lower than 0°C), it is treated as an outlier and processed; for gas concentration data, if the detected value exceeds the reasonable measurement range of the sensor, the outlier is also processed.

[0033] Clean the collected data to remove erroneous and duplicate data. For example, if a gas sensor fails and collects abnormally high or low concentration values, or if data is sent repeatedly due to communication problems, these data should be removed. Normalize data of different magnitudes so that they are in the same magnitude range to facilitate model training and processing. Select a suitable machine learning algorithm to build the model, such as a neural network algorithm. Neural networks have strong nonlinear fitting capabilities and can handle complex gas concentration correlations well. Design the structure of the neural network, including the input layer, hidden layer, and output layer. The number of nodes in the input layer is determined according to the number of features of the input data. For example, features such as temperature and humidity, weather conditions, indirect replacement gas concentration, and methane concentration may require dozens of nodes. The number of layers and nodes in the hidden layer should be determined through experiments and optimization. Generally, 3-5 hidden layers can be set first, and the number of nodes in each layer is between 10-100. The output layer outputs the predicted value of methane concentration. Use the large amount of collected data to train the model, and by continuously adjusting the weights and biases of the neural network, the model can accurately reflect the correlation between indirect replacement gas and methane concentration. During the training process, a suitable loss function is used to evaluate the prediction error of the model, such as the mean square error (MSE), and the model parameters are adjusted according to the error until the model achieves satisfactory prediction accuracy.

[0034] In some embodiments, after obtaining the real-time meteorological data of the highway service area through the professional meteorological data interface of the meteorological department, the judgment criteria of extreme meteorological conditions can also be established. For example, heavy rain is defined as rainfall reaching or exceeding 16mm within 1 hour, heavy snow is defined as snowfall reaching or exceeding 10mm within 1 hour, strong wind is defined as wind speed reaching or exceeding 17.2m / s (level 8 wind), high temperature is defined as temperature reaching or exceeding 35℃ and lasting for more than 2 hours, low temperature is defined as temperature below -10℃ and lasting for more than 2 hours, etc. For some special meteorological phenomena, such as typhoons and cold waves, judgment is made according to the warning level and relevant standards issued by the meteorological department. The monitoring management server judges in real time whether the current situation belongs to extreme meteorological conditions based on the integrated real-time meteorological data and the set extreme meteorological condition standards. When it is determined that the current situation belongs to extreme meteorological conditions, all relevant data collected under extreme meteorological conditions are marked. These data include temperature and humidity data, gas concentration data, vehicle information data (if any), etc. The marked content may include information such as the type of extreme meteorological conditions (such as heavy rain, strong wind, etc.), start time, duration, etc.

[0035] Extract characteristic data related to gas concentration from the labeled data. For example, under heavy rain conditions, extract data such as rainfall, rain wash time, temperature and humidity changes, and corresponding gas concentration data; under strong wind conditions, extract data such as wind speed, wind direction, gas diffusion direction and speed, and corresponding gas concentration data. According to the extracted data features under extreme meteorological conditions, adjust the dynamic correlation model. Specifically, the adjustment may include retraining part or all of the weights and biases of the model using data under extreme meteorological conditions. Take the extracted characteristic data as input and the corresponding gas concentration data as output, and adjust the weights and biases of the model through the back propagation algorithm so that the model can better adapt to the changes in gas concentration under extreme meteorological conditions.

[0036] S102, determining environmental monitoring data and indirect replacement gas concentration during a target period of time through monitoring equipment installed at multiple monitoring points in the service area; In the highway service area, multiple monitoring points are reasonably set up according to the layout of the service area and possible gas emission sources and diffusion areas. Each monitoring point is equipped with temperature and humidity sensors, gas sensors and other equipment to determine the environmental monitoring data and indirect replacement gas concentration in the service area. The temperature and humidity sensor should have high precision and stability, and be able to accurately measure the temperature and humidity changes in the environment. The target period should be determined according to the operating characteristics of the service area and the purpose of the study. For example, if you want to study the impact of daytime vehicle activities on gas concentration, the target period can be set from 6 am to 6 pm. During the target period, the monitoring equipment should work continuously and stably, and collect data according to the predetermined sampling frequency. The sampling frequency can be adjusted according to the speed of environmental changes, generally between 1-3 times per hour. The collected data should be recorded and marked in detail. Including information such as the time of collection, the location of the monitoring point, and the equipment number. At the same time, the data should be preliminarily processed and verified.

[0037] In order to ensure data quality, the collected data must be strictly quality controlled. First, the monitoring equipment must be calibrated and maintained regularly. For example, the temperature and humidity sensors should be calibrated once a month, and the gas sensors should be tested for sensitivity and cleaned once a quarter. Secondly, the collected data must be verified and screened in real time. If abnormal fluctuations are found in the data, such as sharp changes in temperature and humidity in a short period of time, or sudden increases or decreases in gas concentrations, the causes must be analyzed and appropriate measures must be taken.

[0038] S103, inputting the indirect replacement gas concentration and the environmental monitoring data into the dynamic correlation model, and outputting the methane concentration.

[0039] The indirect replacement gas concentration and environmental monitoring data are sorted and preprocessed according to the input requirements of the dynamic correlation model. First, ensure that the format and unit of the data are consistent with the model requirements. Process the data for missing values ​​and outliers. If there are missing values, you can use mean filling, median filling and other methods to supplement them. For outliers, judge and handle them according to the specific situation. If the outliers are caused by equipment failure or measurement error, check and repair the relevant equipment, and remove the outliers; if the outliers may be caused by special environmental events (such as local gas leaks), record and analyze the events. Input the preprocessed indirect replacement gas concentration and environmental monitoring data into the dynamic correlation model. The dynamic correlation model operates based on pre-trained algorithms and parameters. After the model operation, the predicted value of methane concentration is finally output. After the predicted value is output, the prediction result should be evaluated and verified. The cross-validation method can be used to divide the data set into a training set and a validation set, and the accuracy of the model can be evaluated by comparing the error between the predicted value and the actual value on the validation set.

[0040] The predicted value of methane concentration output by the model is output and applied. The predicted value can be output to the display screen of the monitoring management server so that the management personnel can view the methane concentration in the service area in real time.

[0041] In some embodiments, the methane concentration value obtained in real time is compared with the normal threshold value of the methane concentration in the corresponding time period. If the methane concentration value is greater than the upper threshold value or less than the lower threshold value (if the threshold range is set), it is determined to be abnormal. When the methane concentration is determined to be abnormal, it is further determined whether the alarm triggering condition is met. In addition to the condition of abnormal methane concentration, the duration of the abnormality can also be considered. For example, it can be set that the alarm is triggered only when the duration of the abnormal methane concentration exceeds 20 minutes. This can avoid false alarms due to short-term abnormal fluctuations. If the alarm triggering condition is met, the monitoring management server sends an alarm message to the preset monitoring terminal. The monitoring terminal can be a mobile phone, computer terminal or other device of the service area manager. The alarm information should contain detailed abnormal information, such as abnormal methane concentration value, abnormal time period, monitoring point location, etc., so that the manager can quickly understand the situation and take corresponding measures.

[0042] In the embodiments of the present application, a variety of technical means are used to improve the methane concentration monitoring method in highway service areas from different angles, thereby improving the accuracy and reliability of monitoring, effectively solving the problem that traditional monitoring methods cannot adapt to the complex environment of service areas and cannot accurately consider the influence of multiple factors, thereby realizing dynamic and accurate monitoring of methane concentration in service areas.

[0043] After combining the above embodiments, the method provided by this embodiment is further described in more detail below. Figure 2 , is another flow chart of the method for monitoring methane concentration in a highway service area in an embodiment of the present application.

[0044] S201, obtaining temperature and humidity data of the monitoring point through a temperature and humidity sensor disposed at the monitoring point, obtaining weather data within a preset range of the monitoring point through a meteorological terminal, and monitoring gas concentration data through a gas sensor disposed at the monitoring point, the gas concentration data including at least indirect replacement gas concentration and methane concentration; Specifically, a temperature and humidity sensor is set at the monitoring point, and a capacitive or resistive humidity sensor and a thermistor temperature sensor are used to monitor the temperature and humidity in real time. The temperature and humidity sensor transmits the temperature and humidity data to the monitoring management server in real time through an analog or digital interface at a sampling frequency of 1 Hz. A meteorological station is installed near the monitoring point, equipped with a wind speed and direction sensor, a rainfall sensor, an air pressure sensor, etc., to collect weather parameter data including temperature, humidity, wind force, precipitation, air pressure, etc. The meteorological station transmits weather data to the server at a set frequency through digital interfaces such as ZigBee. The server calls a third-party weather API to obtain weather forecast data within a range of 1 km around the monitoring point. In this step, a high-precision methane measurement sensor can be used to measure the methane concentration, which can also determine accurate input data for the establishment of the model.

[0045] S202, after obtaining the temperature and humidity data, the weather data, and the gas concentration data of each monitoring point in different time periods, using a machine learning algorithm to train and obtain an initial dynamic correlation model; Among them, weather data includes categories such as sunny days, rainy days, and cloudy days. For gas concentration data, features such as the ratio of indirect replacement gas concentration and methane concentration, and the rate of change of gas concentration can be extracted. Based on the gas concentration data, weather data, temperature and humidity data combined with the preset algorithm, an initial dynamic correlation model can be trained.

[0046] S203, optimizing the dynamic correlation model using the newly collected monitoring point data until the prediction error of the dynamic correlation model meets the preset requirements; Extract useful features from new data. For weather data, if the newly collected data contains some special weather conditions that have not been considered before (such as hail weather), relevant features can be further extracted, such as the size and density of hail. For gas concentration data, features such as the ratio of indirect replacement gas concentration and methane concentration can be recalculated to reflect the relationship between gas concentrations in the new environment, and the dynamic association model is optimized using the updated data set. The data set is divided into training set and validation set according to a certain ratio again, and the model is retrained using the training set. By adjusting the weights and biases of the model, the model can better adapt to the new data. During the optimization process, a suitable loss function is still used to evaluate the prediction error of the model, such as the mean square error (MSE). Calculate the error between the predicted value and the actual value, and continuously adjust the weights and biases of the model according to the size of the error to gradually reduce the error. When the error meets the preset requirements, stop the optimization and obtain the final dynamic association model.

[0047] S204, setting an image monitoring device to obtain images of vehicles passing through each monitoring point, and determining vehicle information through image recognition algorithm analysis, where the vehicle information includes vehicle type and fuel type; Image monitoring equipment should be installed at appropriate locations near each monitoring point in the highway service area. These devices should be able to cover the vehicle traffic area near the monitoring point to ensure that clear vehicle images can be captured. For example, a high-definition camera can be selected with a resolution sufficient to identify detailed features of the vehicle, such as license plate number, vehicle appearance, etc. The camera should be installed at a reasonable angle to avoid blind spots, and the shooting effect under different weather conditions should be considered, such as obtaining usable images in rainy or foggy days. The image monitoring equipment should be connected to the monitoring management server so that the captured vehicle images can be transmitted to the server for processing in a timely manner.

[0048] After the vehicle image is transmitted to the monitoring management server, the image recognition algorithm is used to analyze the vehicle image. First, the image is preprocessed, including grayscale, noise reduction, enhancement and other operations to improve the image quality and recognition effect. Then, the target detection algorithm is used to identify the position of the vehicle in the image. Then, the detected vehicle is classified and identified to determine the vehicle type and fuel type. A classification algorithm based on deep learning, such as convolutional neural network (CNN), can be used. The vehicle image is input into the trained CNN model, and the model outputs the vehicle type (such as car, truck, bus, etc.) and fuel type (such as gasoline, diesel, natural gas, etc.) based on the vehicle's appearance characteristics and other information.

[0049] Finally, the identified vehicle information (vehicle type and fuel type) is stored in the database together with the corresponding monitoring point location and time information for subsequent analysis of the impact of different types of vehicles on gas concentration. In addition to image monitoring equipment, other data sources can also be combined to obtain vehicle composition data. For example, the type and fuel type information of refueling vehicles are recorded at gas stations in service areas, which can serve as a supplement to vehicle composition data.

[0050] S205, determining the flow distribution of each vehicle type according to the vehicle flow and the vehicle composition data; Traffic flow data is collected through vehicle counting devices installed at the entrance and exit of highway service areas. These devices can be vehicle counters based on technologies such as induction coils, radar or video analysis. For example, the induction coil vehicle counter counts vehicles by detecting the change in magnetic field caused by the passage of vehicles; the radar vehicle counter uses the principle of radar wave reflection to determine the passage of vehicles; and the video analysis vehicle counter counts the number of vehicles by analyzing the video images of the entrance and exit of the service area. The vehicle counting equipment must be able to accurately record the traffic flow data of different time periods, and the time interval can be set to every 15 minutes or every 30 minutes, etc. The collected traffic flow data must be marked with the corresponding time period, for example, the traffic flow from 9:00 to 9:15 in the morning is 50 vehicles.

[0051] A unified vehicle classification standard can be established in advance. For example, the vehicle models can be divided into several categories such as sedans, SUVs, trucks, buses, and vans. Some special vehicles, such as engineering vehicles and sanitation vehicles, can be classified separately. The classification standard must be clear so that the flow of each vehicle model can be accurately counted. The flow of each vehicle model is counted based on the traffic flow data and vehicle composition data. For each time period, the vehicles passing through the service area are classified according to the vehicle model classification standard. For example, in the time period of 9:00-9:15 in the morning, the image recognition algorithm determines that 30 sedans, 15 SUVs, and 5 trucks pass through the service area.

[0052] Calculate the proportion of each vehicle type in the total traffic flow to determine the traffic distribution. For example, in the above example, the traffic share of sedans is 30 / 50=60%, the traffic share of SUVs is 15 / 50=30%, and the traffic share of trucks is 5 / 50=10%. Repeat the above process, collect statistics and analyze the traffic flow and vehicle composition data in different time periods, and obtain the traffic distribution of each vehicle type in different time periods. For example, you can get the traffic distribution chart of each vehicle type in different time periods such as morning, afternoon, and evening, which can intuitively show the traffic change pattern of each vehicle type.

[0053] Verify the traffic distribution data of each vehicle type obtained by statistics. The cross-validation method can be used to compare and analyze the data of different time periods. For example, compare whether the traffic changes of each vehicle type in two adjacent 15-minute time periods are reasonable. If the traffic of a certain vehicle type increases or decreases abnormally in adjacent time periods, check whether there are problems with the vehicle counting equipment and image recognition algorithm.

[0054] It can also be compared with historical data for verification. If the current traffic distribution of a certain vehicle model is significantly different from the historical data for the same period, further analysis is needed. It may be due to special events (such as holidays, road construction, etc.) that cause vehicle travel patterns to change. As new traffic flow and vehicle composition data are continuously collected, the traffic distribution data of each vehicle model should be updated in a timely manner. For example, the data can be updated once an hour to ensure that the traffic distribution data can reflect the latest situation of vehicles in the service area.

[0055] S206, obtaining the indirect replacement gas concentration and methane concentration within the target period, and comparing and analyzing the flow distribution and gas concentration change characteristics of different vehicle models within the target period; Correlate the flow distribution data of different vehicle models with the corresponding gas concentration change data within the same target period. For example, when the proportion of car flow is large, observe the change of gas concentration at this time; when the proportion of truck flow is large, compare the difference in gas concentration with that when the flow of cars is large. Use statistical analysis methods, such as calculating correlation coefficients. Calculate the correlation coefficient between the flow proportion of different vehicle models and the change of gas concentration to determine the degree of correlation between them. If the correlation coefficient is high (close to 1 or -1), it means that the flow distribution of the vehicle model has a strong correlation with the change of gas concentration; if the correlation coefficient is close to 0, it means that the correlation is weak. Analyze the changing characteristics of the flow distribution and gas concentration changes of different vehicle models within the target period. For example, observe whether the flow of different vehicle models increases or decreases regularly over time within the target period, and whether the gas concentration changes accordingly.

[0056] You can also draw a line graph of the flow rate of different models over time and a line graph of the gas concentration over time, and analyze the relationship between them by comparing the two graphs. For example, if the car flow rate gradually increases from 9:00 to 10:00 in the morning, and the gas concentration also rises to a certain extent, then it can be preliminarily judged that the change in car flow rate may have an impact on the gas concentration.

[0057] S207, determining the contribution of different vehicle models to the indirect replacement gas concentration according to the flow distribution and the gas concentration change characteristics; A multiple linear regression model can be used to establish the relationship between vehicle type flow distribution and indirect replacement gas concentration changes. The multiple linear regression model can handle the relationship between multiple independent variables (vehicle type flow ratio) and one dependent variable (indirect replacement gas concentration change).

[0058] More specifically, let the dependent variable Y be the change in the concentration of the indirect replacement gas, and the independent variables X1, X2, ..., Xn be the flow ratio of different vehicle models (n is the vehicle model). For example, if there are three vehicle models, namely, sedan, truck, and bus, then n=3, X1 is the flow ratio of sedan, X2 is the flow ratio of truck, and X3 is the flow ratio of bus. The flow ratio of vehicle models here can be calculated from the flow distribution in step S206.

[0059] The general form of the multiple linear regression model is: Y = + *X1+ *X2+…+ *Xn+ε, where is the intercept, , , …, is the regression coefficient and ε is the error term.

[0060] Regression coefficients in the trained multiple linear regression model , , …, It reflects the contribution of different vehicle models to the change in indirect replacement gas concentration. =0.2, which means that for every 1% increase in the proportion of passenger car traffic, the concentration of indirect replacement gas will increase by 0.2ppm.

[0061] S208, adjusting vehicle model related parameters in the dynamic association model according to the contribution degree; According to the analysis in the previous step, the contribution ranking of different models can be obtained. The model with the greatest contribution can have its tuning factor set to 1; the tuning factors of other models are set to values ​​between 0 and 1 according to their contribution. For example, if the diesel vehicle has the highest contribution, its tuning factor is set to 1; the gasoline vehicle is second, with a tuning factor of 0.8; the electric vehicle contributes very little, with a tuning factor of 0.2. Use the tuning factors determined in the previous step to adjust the model parameters in the model. For example, each model parameter can be multiplied by the corresponding tuning factor, so that the effect of adjusting the parameters of different models according to the contribution degree is achieved. The adjusted model can more accurately characterize the contribution differences of different models.

[0062] S209: After determining the vehicle information of the target period through the image monitoring device, the environmental monitoring data and the indirect replacement gas concentration corresponding to the target period are input into the adjusted dynamic correlation model to determine the final methane concentration.

[0063] The vehicle composition data of the target period obtained previously, as well as the environmental parameter data such as temperature, humidity, air pressure, wind speed, etc. collected by the monitoring equipment during this period, and the indirect gas concentration data are input into the dynamic correlation model after the vehicle model parameter adjustment and optimization. The adjusted and optimized dynamic correlation model has comprehensively considered the influence of vehicle model factors. After inputting the specific vehicle model composition data of the target period, the model can calculate a more accurate methane concentration prediction value for this period as the final monitoring concentration result.

[0064] In the embodiments of the present application, a variety of technical means are used to improve the methane concentration monitoring method in highway service areas from different angles, thereby improving the accuracy and reliability of monitoring, effectively solving the problem that traditional monitoring methods are difficult to adapt to the complex environment of service areas and cannot accurately consider the influence of multiple factors, thereby achieving dynamic and accurate monitoring of methane concentration in service areas and effective early warning and prevention of related risks.

[0065] The monitoring management server in the embodiment of the present invention is described below from the perspective of hardware processing. Figure 3 , which is a schematic diagram of a physical device structure of a monitoring management server in an embodiment of the present application.

[0066] It should be noted that Figure 3 The structure of the monitoring management server shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0067] like Figure 3 As shown, the monitoring management server includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method described in the above embodiment. In RAM 303, various programs and data required for system operation are also stored. CPU 301, ROM 302 and RAM 303 are connected to each other through bus 304. Input / output (I / O) interface 305 is also connected to bus 304.

[0068] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, a button switch, etc.; an output section 307 including a liquid crystal display (LCD) and an audio output device, an indicator light, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.

[0069] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 309, and / or installed from a removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, various functions defined in the present invention are performed.

[0070] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0071] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings.

[0072] Specifically, the monitoring management server of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the method for monitoring the methane concentration in the highway service area provided in the above embodiment is implemented.

[0073] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the monitoring management server described in the above embodiment; or may exist independently without being assembled into the monitoring management server. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of the monitoring management server, the monitoring management server implements the method for monitoring the methane concentration in the highway service area provided in the above embodiment.

[0074] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0075] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0076] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. A method for monitoring methane concentration in a highway service area, applied to a monitoring management server, characterized in that: include: A dynamic correlation model is constructed by acquiring indirect replacement gas concentration and methane concentration parameter data of the service area of ​​the expressway at different time periods and environmental conditions, wherein the dynamic correlation model is used to determine the correlation relationship between the indirect replacement gas and the methane concentration; The environmental monitoring data and indirect replacement gas concentrations during the target period are determined by monitoring equipment installed at multiple monitoring points within the service area; The indirect replacement gas concentration and the environmental monitoring data are input into the dynamic correlation model, and the methane concentration is output.

2. The method according to claim 1, characterized in that: The steps of constructing a dynamic correlation model by obtaining the indirect replacement gas concentration and methane concentration parameter data of the service area of ​​the expressway under different time periods and environmental conditions include: The temperature and humidity data of the monitoring point are obtained by a temperature and humidity sensor arranged at the monitoring point, the weather data within a preset range of the monitoring point is obtained by a meteorological terminal, and the gas concentration data is monitored by a gas sensor arranged at the monitoring point, wherein the gas concentration data includes at least an indirect replacement gas concentration and a methane concentration; After obtaining the temperature and humidity data, the weather data, and the gas concentration data of each monitoring point in different time periods, an initial dynamic correlation model is obtained by training using a machine learning algorithm; The dynamic correlation model is optimized using the newly collected monitoring point data until the prediction error of the dynamic correlation model meets the preset requirements.

3. The method according to claim 1, characterized in that After the step of constructing a dynamic correlation model by acquiring the indirect replacement gas concentration and methane concentration parameter data of the service area of ​​the expressway under different time periods and environmental conditions, it also includes: Setting an image monitoring device to obtain images of vehicles passing through each monitoring point, and determining vehicle information through image recognition algorithm analysis, wherein the vehicle information includes vehicle type and fuel type; After obtaining the traffic volume and vehicle composition data of each monitoring point at different time periods, the influence relationship between the traffic volume of different types of vehicles and the concentration of indirect replacement gases and methane was analyzed; The dynamic association model is adjusted according to the influence relationship.

4. The method according to claim 3, characterized in that After obtaining the traffic flow and vehicle composition data of each monitoring point at different time periods, the steps of analyzing the influence relationship between the traffic flow of different types of vehicles and the indirect replacement gas and methane concentration include: Determining the traffic flow distribution of each vehicle type according to the vehicle flow and the vehicle composition data; Obtaining the indirect replacement gas concentration and methane concentration within the target period, and comparing and analyzing the flow distribution and gas concentration change characteristics of different vehicle models within the target period; Determining the contribution of different vehicle types to the indirect replacement gas concentration according to the flow distribution and the gas concentration change characteristics; The vehicle type related parameters in the dynamic association model are adjusted according to the contribution degree.

5. The method according to claim 3, characterized in that: After the step of adjusting the dynamic association model according to the influence relationship, the method further includes: After the vehicle information of the target period is determined by the image monitoring device, the environmental monitoring data and the indirect replacement gas concentration corresponding to the target period are input into the adjusted dynamic correlation model to determine the final methane concentration.

6. The method according to claim 1, characterized in that After the step of constructing a dynamic correlation model by acquiring the indirect replacement gas concentration and methane concentration parameter data of the service area of ​​the expressway under different time periods and environmental conditions, it also includes: Obtain real-time weather data from highway service areas to determine whether the current weather conditions are extreme; If it belongs to the extreme meteorological conditions, the dynamic correlation model is corrected.

7. The method according to claim 1, characterized in that After the step of inputting the indirect replacement gas concentration into the dynamic correlation model to output the methane concentration, the method further includes: After obtaining a plurality of historical monitoring data, setting normal thresholds of methane concentrations for different time periods according to the historical monitoring data; Compare the methane concentration with the normal threshold of the methane concentration in the corresponding time period to determine whether it is abnormal; If there is any abnormality, an alarm message will be sent to the preset monitoring terminal.

8. A server, characterized in that: The server includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the server to execute the method described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instructions are executed on a server, the server is caused to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is run on a server, the server is caused to execute the method according to any one of claims 1 to 7.

Images