A monitoring and optimization system for abnormal carbon emissions and energy consumption on highways

Abstract

The application discloses a highway carbon emission energy consumption anomaly monitoring optimization system, relates to the technical field of intelligent traffic and carbon emission monitoring, and comprises a vehicle feature acquisition module, an environment dynamic perception module, a carbon emission dynamic calculation module, an anomaly intelligent diagnosis module and an attribution optimization execution module; real-time dynamic carbon emission values are calculated in combination with vehicle features, real-time driving speeds, wind speeds and environment factor data such as road gradients; dynamic carbon emission reference values are set according to current road section traffic flow and environment factor data; anomaly attribution types are identified by correlating vehicle speed mutations, environment factor mutations and road section traffic conditions and the like data during a carbon emission anomaly period, and corresponding optimization adjustment instructions are generated. The attribution accuracy of carbon emission anomalies is improved, real-time optimization decisions for traffic management are supported, and technical support is provided for green intelligent highway operation.

Description

Technical Field

[0001] This invention belongs to the field of highway carbon emission and energy consumption anomaly monitoring and optimization technology, and relates to a highway carbon emission and energy consumption anomaly monitoring and optimization system. Background Technology

[0002] Highway carbon emission energy consumption refers to the amount of carbon emissions and corresponding energy consumption generated by vehicles during highway driving due to fuel consumption or energy utilization. When highway carbon emission energy consumption is too high, it will exacerbate the greenhouse effect, pollute the environment, increase vehicle operating costs, and is often accompanied by poor driving or traffic congestion, which can easily lead to safety hazards. Therefore, it is crucial to carry out abnormal monitoring and optimization of highway carbon emission energy consumption.

[0003] Existing technologies have proposed optimizations for monitoring anomalies in carbon emissions and energy consumption on highways. For example, the invention patent with publication number CN118377988B proposes a real-time monitoring method for anomalies in carbon emissions and energy consumption on highways. By comparing the carbon emission power sequences of the target day with those of historical reference days, abnormal power segments are identified. Combined with fluctuation characteristics, deviation degree, and anomaly distribution in the extended time domain, the true anomaly probability of each suspected anomaly segment is comprehensively calculated, and finally, it is determined whether the carbon emissions and energy consumption of the highway are abnormal. Through accurate and reliable true probabilities, the accuracy of real-time monitoring of anomalies in carbon emissions and energy consumption on highways is improved.

[0004] Although existing technologies have achieved some success in optimizing the monitoring of abnormal carbon emissions and energy consumption on highways, they still have the following shortcomings: First, existing technologies rely solely on carbon emission power sequences as the data source for calculating carbon emissions. However, when vehicles are driving on highways, their carbon emissions change dynamically due to road conditions and environmental factors. This causes the carbon emission calculation to be completely detached from the dynamic changes in the actual road scenario, making it impossible to distinguish between normal carbon emission fluctuations caused by sudden environmental changes and a surge in false alarm rates due to real anomalies.

[0005] Secondly, carbon emissions from highways exhibit strong dynamism due to periodic fluctuations in traffic flow, extreme weather disturbances, and the widespread adoption of new energy vehicles. Existing technologies, which use fixed thresholds as anomaly criteria, cannot adapt to real-time scenario differences. When traffic flow or the environment changes suddenly, scenario-adaptive emissions are easily misjudged as abnormal, reducing monitoring accuracy.

[0006] Finally, carbon emission anomalies are essentially the result of the combined effects of multiple factors. However, existing technologies only determine the existence of anomalies through the statistical probability of carbon emission power sequences, which makes it impossible to analyze the root causes of anomalies, provide a basis for traffic management to solve problems, and support actual energy conservation and emission reduction management. Ultimately, this makes it difficult for management to formulate targeted governance measures. Summary of the Invention

[0007] In view of this, in order to solve the problems mentioned in the background art, the present invention provides a highway carbon emission energy consumption anomaly monitoring and optimization system.

[0008] The objective of this invention can be achieved through the following technical solution: a highway carbon emission and energy consumption anomaly monitoring and optimization system, comprising the following modules: a vehicle feature acquisition module, used to identify the license plate number and vehicle type of vehicles entering at the toll station gate.

[0009] The environmental dynamic perception module is used to collect real-time data on the speed of vehicles on specific sections of highways and environmental factors, including wind speed and road gradient, when vehicles are traveling on specific sections of highways.

[0010] The carbon emission dynamic calculation module is used to generate real-time dynamic carbon emission values ​​for vehicles based on the preset fuel consumption standard value matched to the vehicle model, combined with real-time vehicle speed, environmental factor data, and their respective directions of increase or decrease in energy consumption and emissions.

[0011] The abnormal intelligent diagnosis module is used to set a dynamic carbon emission benchmark value based on the current road traffic flow and environmental factor data. When the real-time dynamic carbon emission value of a vehicle exceeds the benchmark value, it is determined to be an abnormal carbon emission.

[0012] The attribution optimization execution module is used to obtain carbon emission-related data based on the characteristics of sudden changes in vehicle speed, changes in environmental factors, and the overall traffic conditions of road segments during periods of abnormal carbon emissions. It identifies the attribution type of the abnormality based on the carbon emission-related data and generates corresponding traffic operation optimization and adjustment instructions based on the attribution type.

[0013] Compared with the prior art, the beneficial effects of the present invention are as follows: (1) The present invention identifies the license plate number and vehicle type of the vehicle entering the vehicle through the vehicle feature acquisition module, and calculates the real-time dynamic carbon emission value of the vehicle by combining vehicle features, real-time driving speed and environmental factors such as wind speed and road slope, so that the carbon emission calculation is closely integrated with the dynamic changes of the actual road scene, and can distinguish between normal carbon emission fluctuations caused by environmental changes and real anomalies, thereby improving the authenticity of carbon emission calculation.

[0014] (2) The present invention sets a dynamic carbon emission benchmark value based on the current traffic flow and environmental factor data of the road segment, and updates it in real time as the vehicle moves. It can adapt to real-time scene differences, avoid misjudging scene-adaptive emissions as abnormal when traffic flow or environment changes suddenly, and improve monitoring accuracy.

[0015] (3) This invention identifies the attribution type of anomalies by associating data such as sudden changes in vehicle speed, sudden changes in environmental factors and road conditions during periods of abnormal carbon emissions, and generates corresponding optimization and adjustment instructions. This can analyze the root cause of the anomalies, provide a basis for traffic management to solve problems, support actual energy conservation and emission reduction management, and facilitate the management to formulate targeted governance measures. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a schematic diagram showing the connections of the various modules in the system of the present invention.

[0018] Figure 2 This is a flowchart of the real-time dynamic fuel consumption calculation process of the present invention.

[0019] Figure 3 This is a flowchart illustrating the process for determining the benchmark value for dynamic carbon emissions of vehicles according to the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] Please see Figure 1 As shown, this invention provides a highway carbon emission and energy consumption anomaly monitoring and optimization system, comprising the following modules: a vehicle feature acquisition module, an environmental dynamic perception module, a carbon emission dynamic calculation module, an anomaly intelligent diagnosis module, and an attribution optimization execution module. All modules are connected in the order described above.

[0022] The vehicle feature acquisition module is used to identify the license plate number and vehicle model of vehicles entering at the toll station gate.

[0023] The above-mentioned vehicle license plate numbers are obtained as follows: when the inductive loop detector detects a vehicle entering the ETC gate area, it triggers the infrared camera to capture the image of the front of the vehicle.

[0024] Candidate areas are generated based on license plate color gamut features. Horizontal gradient scanning is used to filter areas with continuous edge density exceeding the threshold and conforming to the aspect ratio as valid license plate areas.

[0025] It should be noted that edge density is an indicator that measures the density of edge pixels within a region. Its threshold needs to be determined by collecting a large number of standard license plate images, calculating the distribution range of their edge density, and selecting the lower limit of this range as the threshold to ensure that the vast majority of normal license plates can pass the screening.

[0026] The infrared camera captures images of the vehicle's front end, which undergo grayscale correction and noise reduction to minimize interference from uneven lighting or dirt. The original RGB image is then converted to the HSV color space, which provides a color description that is closer to human visual perception and is more robust to changes in lighting.

[0027] Based on the target license plate type, a corresponding HSV threshold range is preset. The image pixels are traversed and pixels that meet the preset HSV threshold range are marked as candidate pixels, forming a set of connected regions. Regions with too small a concentrated area or irregular shape are eliminated, and connected regions that may be license plates are retained.

[0028] Dynamic threshold binarization is used to segment the valid license plate area. If the spacing between adjacent characters exceeds a set ratio and the effective pixels of a single character exceed a set percentage, the segmented character is output.

[0029] Specifically, the valid license plate area image is first converted into a grayscale image. Then, a sliding window or local adaptive algorithm is used to dynamically determine the binarization threshold of each local region based on the grayscale mean, variance, or Gaussian distribution characteristics of the pixels within the window. Subsequently, pixels with grayscale values ​​higher than the threshold in the region are determined as background, and pixels with grayscale values ​​lower than the threshold are determined as foreground, thereby separating the characters from the background and forming a black and white binary image to highlight the character outline.

[0030] The set ratio and percentage were determined by collecting a large number of standard license plate samples, statistically analyzing the ratio range of character spacing to the total width of the license plate, and the ratio range of effective pixels of a single character to the pixels of its enclosing rectangular area. The thresholds were determined after multiple verifications to adapt to the character segmentation requirements of most normal license plates.

[0031] Extract character topological features and compare them with pre-stored templates at the pixel level. Output the recognition result when the features are completely consistent.

[0032] It should be noted that topological features include the number of strokes, the number of stroke intersections, the number of closed regions, the distribution of stroke endpoints, and the concavity and convexity of the overall outline.

[0033] The above vehicle model information is obtained as follows: Vehicle outline data is acquired simultaneously through multi-view cameras, and a preliminary model identification result is generated based on the length-width-height ratio and wheelbase features.

[0034] Specifically, the ratios of length to width and height to width are calculated, and combined with the specific values ​​of wheelbase, a combination of vehicle outline features is formed to generate a preliminary vehicle model assessment result.

[0035] The contour is geometrically aligned with the benchmark model in the vehicle model database to calculate the degree of overlap. If the degree of overlap between the models reaches a set threshold, the corresponding vehicle model data is output.

[0036] More specifically, the vehicle contour data acquired by multi-view cameras is geometrically aligned with various reference models pre-stored in the vehicle model database. This involves using coordinate transformations, such as translation, rotation, and scaling, to align the key feature points of the vehicle contour to be identified with those of the reference models, such as the apex of the front of the vehicle, the wheel axle, and the corners of the vehicle body, in the same coordinate system. After alignment, the number of pixels in the overlapping area between the vehicle contour and the reference model contour is counted. This number is then divided by the union of the total number of pixels in both contours, which is the total number of pixels covered by the contour, to obtain the overlap value between the two.

[0037] It should be noted that the threshold is set by collecting standard vehicle profile data covering different categories, establishing a database containing typical benchmark models of each category, selecting multiple sets of actual vehicle profiles of the same category for each benchmark model, performing geometric alignment and overlap calculation, statistically analyzing the distribution range of these overlaps, and selecting a value that can effectively distinguish different vehicle models while covering normal errors within the same category as the initial threshold based on the statistical results.

[0038] Abnormal vehicles can be located by license plate number, and targeted control instructions can be generated by combining vehicle type information. Vehicle type data also provides a classification basis for road segment-level traffic optimization, ensuring that optimization measures can accurately adapt to vehicle characteristics and road conditions.

[0039] The environmental dynamic perception module is used to collect in real time the interval driving speed of vehicles on a specific section of the highway and environmental factor data, including wind speed and road gradient, when the vehicle is driving on a specific section of the highway.

[0040] The steps for collecting the driving speed in the above-mentioned section are as follows: Several intermediate sensing points are added at preset intervals along the road segment where the vehicle is traveling.

[0041] Specifically, the preset distance needs to be determined through preliminary road section surveys combined with historical traffic data and environmental characteristics, and can be dynamically adjusted based on feedback from the accuracy of monitoring data during actual operation.

[0042] In areas with heavy traffic, the preset distance can be appropriately shortened, such as 500 meters to 1 kilometer, to capture more detailed changes in vehicle speed and improve the accuracy of speed calculation in sub-sections. In areas with sparse traffic, the preset distance can be appropriately extended, such as 1 kilometer to 3 kilometers, to meet monitoring needs while reducing equipment deployment costs. For road sections with complex environments such as slope changes and curves, the preset distance needs to be shortened, such as 300 meters to 800 meters, in order to accurately match the correlation between vehicle driving status and environmental factors such as road slope and wind speed. In straight and stable road sections, the preset distance can be widened to 1 kilometer to 2 kilometers.

[0043] When a vehicle passes any sensing point, its license plate number is captured and a precise timestamp is recorded.

[0044] For two adjacent sensing points that a vehicle passes consecutively within a road segment, the actual distance between the preset adjacent points is used as the driving distance, and the time difference between the timestamps of the vehicle passing the two adjacent sensing points is used as the driving time.

[0045] The average speed of a vehicle in the sub-interval between adjacent points is calculated based on the travel distance and travel time.

[0046] The above environmental factor data collection steps are as follows: call the real-time wind speed data of the existing roadside meteorological station of the target road section, dynamically match the wind speed monitoring value of the nearest meteorological station based on the real-time GPS location coordinates of the vehicle, and bind the latest wind speed data of the meteorological station associated with the sensing point when the vehicle passes through the sensing point.

[0047] The slope reference values ​​of each sub-section of the target road segment are pre-stored in the database. When a vehicle passes through the sensing point of the road segment, the real-time station number position of the vehicle is obtained based on the sensing device.

[0048] Based on the vehicle's real-time station location, query the database for the sub-interval containing that station number.

[0049] Extract the slope baseline value of the matching sub-interval as the current road slope value.

[0050] The environmental dynamic perception module is a key support for the realization of the core functions of the entire highway carbon emission and energy consumption anomaly monitoring and optimization system.

[0051] The carbon emission dynamic calculation module is used to generate real-time dynamic carbon emission values ​​for vehicles based on the preset fuel consumption standard value matched to the vehicle model, combined with real-time vehicle speed, environmental factor data, and their respective directions of increase or decrease in energy consumption and emissions.

[0052] See Figure 2 As shown, the specific details of the real-time dynamic carbon emission values ​​of the above vehicles are as follows: query the preset mapping database between vehicle models and fuel consumption.

[0053] When a matching vehicle model record exists in the mapping database, the base fuel consumption value per unit mileage corresponding to that vehicle model is extracted.

[0054] Obtain the vehicle's average speed in the current sub-interval. If the vehicle speed is within the speed range, generate a negative speed correction coefficient; otherwise, generate a positive speed correction coefficient.

[0055] It should be noted that the speed range was determined by collecting a large amount of energy consumption test data from vehicles of the same model to establish the basic speed range for each vehicle.

[0056] Different vehicle models have an economical driving speed range within which vehicle energy consumption is lowest; deviating from this range will lead to increased energy consumption. When the vehicle speed is within this range, the vehicle's engine efficiency is highest, and energy consumption and emissions are at a relatively optimal level, thus generating a negative speed correction coefficient. When the vehicle speed is below or above this range, engine efficiency decreases and energy consumption and emissions increase, thus generating a positive speed correction coefficient.

[0057] When the real-time wind speed value is read, a positive wind speed correction coefficient is generated when the wind speed exceeds the preset benchmark wind speed threshold; otherwise, the wind speed correction coefficient is set to zero.

[0058] It should be noted that the benchmark wind speed threshold is determined by retrieving historical wind speed monitoring data of the target road section, statistically analyzing the common wind speed distribution range of the road section, and using the upper limit of wind speed under most normal driving conditions, where the wind resistance effect can be ignored, as the threshold reference.

[0059] When wind speed exceeds a certain intensity, it significantly increases vehicle drag, leading to increased energy consumption and carbon emissions. However, when wind speed is low, its impact on energy consumption is negligible. When wind speed exceeds a preset baseline wind speed threshold, wind resistance forces the vehicle engine to output more power to maintain speed, directly increasing energy consumption. Therefore, a positive wind speed correction coefficient is generated to adjust the base fuel consumption value upwards to reflect the incremental impact of wind resistance on carbon emissions. When wind speed does not exceed the baseline threshold, the impact of wind resistance on vehicle energy consumption is minimal and can be considered within the normal error range. Therefore, the wind speed correction coefficient is set to zero to avoid unnecessary corrections that could interfere with the accuracy of carbon emission values.

[0060] Obtain the slope reference value corresponding to the current vehicle station number. If the slope value is positive, generate a positive slope correction coefficient; otherwise, generate a negative slope correction coefficient.

[0061] It should be noted that when a vehicle is driving uphill, it needs to overcome the component of gravity, and the engine needs to output more power to maintain the driving speed, which leads to increased energy consumption and carbon emissions. Therefore, a positive slope correction coefficient is generated to adjust the base fuel consumption value upward to reflect the incremental impact of uphill driving on carbon emissions. On the other hand, when a vehicle is driving downhill, the component of gravity will have a boosting effect on the vehicle, which can reduce engine power output and thus reduce energy consumption and carbon emissions. Therefore, a negative slope correction coefficient is generated to adjust the base fuel consumption value downward to reflect the reduction effect of downhill driving on carbon emissions.

[0062] Using the base fuel consumption value as an anchor, the vehicle's real-time dynamic carbon emission value is generated based on the vehicle speed correction coefficient, wind speed correction coefficient, and slope correction coefficient.

[0063] Specifically, the real-time dynamic carbon emission value of vehicles In the formula, This indicates the base fuel consumption value. This represents the vehicle speed correction factor. This represents the wind speed correction factor. Indicates the slope correction factor. Indicates the vehicle's current speed. Indicates the vehicle's initial speed. Indicates wind speed on the road surface. Indicates the road surface slope value. Indicates carbon emission factor.

[0064] It should be noted that in the above formula The base fuel consumption value represents the fuel consumption of a vehicle under standard, ideal driving conditions, typically on flat roads, in windless conditions, and at a stable, economical speed. It serves as the basic reference for calculating carbon emissions.

[0065] This reflects the degree of deviation from the speed limit; the quadratic term indicates that both exceeding and falling below the reference speed will affect fuel consumption. This refers to the adjustment factor for fuel consumption based on vehicle speed. When the vehicle speed deviates from the baseline speed, the vehicle's fuel efficiency changes. For example, if the speed is too high or too low, the engine may not be operating in its most economical state, leading to increased fuel consumption. By combining the vehicle speed correction factor, the correction ratio of the vehicle speed factor on the base fuel consumption can be obtained, which in turn affects carbon emissions.

[0066] This refers to the correction factor for wind speed on fuel consumption. When a vehicle is in motion, wind speed will generate resistance to the vehicle. For example, resistance increases when there is a headwind and decreases when there is a tailwind, thus affecting the vehicle's fuel consumption and consequently carbon emissions. The correction ratio of wind speed to base fuel consumption is obtained by multiplying the wind speed correction coefficient by the road surface wind speed.

[0067] This refers to the correction factor for fuel consumption caused by slope. When a vehicle is driving on a slope, it needs to do work to overcome gravity. For example, when going uphill, the work done increases and fuel consumption increases. When going downhill, some of the gravitational potential energy can be converted into kinetic energy, and fuel consumption decreases. Therefore, slope affects fuel consumption. The correction ratio of the slope factor to the base fuel consumption is obtained by multiplying the slope correction factor by the road slope value.

[0068] The carbon emission factor refers to the amount of carbon dioxide emitted after burning a unit volume or unit mass of fuel. Different types of fuel, such as gasoline and diesel, have different carbon emission factors. It is a key coefficient used to convert fuel consumption into carbon emissions, transforming the previously adjusted fuel consumption into the final carbon emissions.

[0069] The above factors each affect carbon emissions independently, and the way they affect emissions is by increasing or decreasing them proportionally from the baseline value. Therefore, multiplication can accurately reflect the law of carbon emissions changing with the multiplier of each factor under the combined effect of multiple factors, and finally obtain the real-time dynamic carbon emission value of the vehicle.

[0070] The abnormal intelligent diagnosis module is used to set a dynamic carbon emission benchmark value based on the current road traffic flow and environmental factor data. When the real-time dynamic carbon emission value of a vehicle exceeds the benchmark value, it is determined to be an abnormal carbon emission.

[0071] See Figure 3 As shown, the specific content of the above dynamic carbon emission benchmark value is as follows: Obtain the driving speed sequence of continuous vehicles in front of the target vehicle; when the speed of each subsequent vehicle in the driving speed sequence is lower than the speed of the preceding vehicle, a traffic flow deceleration signal is generated; when the distance between the target vehicle and the preceding vehicle increases within a continuous step size between continuous sensing points, a free driving signal is generated.

[0072] It should be noted that the fact that the speed of subsequent vehicles is lower than that of the preceding vehicles directly reflects the potential congestion and traffic backlog on the road. At this time, the vehicle's movement is significantly constrained by the vehicle in front, and its energy consumption and emission characteristics are significantly different from those of free driving. The continuous increase in the distance between the vehicle and the vehicle in front reflects that the vehicle is in a smooth driving state without interference from the vehicle in front. At this time, energy consumption and emissions are mainly affected by its own speed and environmental factors.

[0073] Calculate the angle between the vehicle's wind direction vector and its direction of travel. If the angle is obtuse, mark it as a headwind.

[0074] When the angle between the vehicle's wind direction vector and its direction of travel is obtuse, it means that the main force of the wind is in the opposite direction to the vehicle's direction of travel, i.e., headwind. Headwind will increase the vehicle's driving resistance, leading to increased energy consumption and carbon emissions.

[0075] Based on the matching relationship between the highway mileage increment direction and the vehicle travel direction, if the travel direction is consistent with the mileage increment direction and the slope value is positive, then an uphill action indicator is marked.

[0076] The direction of the highway mileage increments serves as a fixed road alignment reference. When a vehicle's travel direction aligns with this direction, a positive gradient indicates an upward slope, clearly indicating the vehicle is traveling uphill. When going uphill, the vehicle must overcome the force of gravity, increasing engine power output, energy consumption, and carbon emissions.

[0077] If a traffic slowdown signal is present, retrieve the set of dynamic carbon emission values ​​for vehicles of the same model and with the same environmental impact identifier for the current time period from the carbon emission database. Sort the values ​​in ascending order and take the maximum value in the last third of the sorted interval as the baseline value.

[0078] It should be noted that traffic flow intensity and driving habits may vary at different times. Data for the current time period can avoid deviations caused by time differences. The basic energy consumption characteristics of the same vehicle model are consistent, eliminating the impact of vehicle model differences on carbon emission values. The same environmental action label ensures that the impact of environmental factors on energy consumption is consistent, making the data comparable under the same environmental constraints.

[0079] If a free-driving signal is present, when the headwind action sign or uphill action sign is activated, a preset proportion of the dynamic carbon emission values ​​of vehicles of the same type on the current road segment is extracted as a benchmark value.

[0080] It should be noted that a free-driving signal means that a vehicle is not constrained by the vehicle in front and its driving state is relatively stable. At this time, energy consumption and emissions are mainly affected by its own speed and environmental factors, rather than the interference of traffic flow caused by frequent acceleration and deceleration. Therefore, the benchmark value should focus on reflecting the normal energy consumption range under the influence of environmental factors.

[0081] When the environmental impact indicator is not activated, the median carbon emissions of this vehicle model in the same historical period and on the same road segment are used as the benchmark value.

[0082] The specific details of the aforementioned carbon emission anomaly are as follows: Obtain the current vehicle's real-time dynamic carbon emission value and dynamic carbon emission baseline value.

[0083] Real-time dynamic carbon emission values ​​are compared with dynamic carbon emission benchmark values ​​in real time.

[0084] If the real-time dynamic carbon emission value exceeds the dynamic carbon emission benchmark value, the vehicle's carbon emission status at a specific road segment location and at the current moment will be marked as initially abnormal.

[0085] As the vehicle continues to travel and passes through subsequent monitoring points along the road segment, the real-time dynamic carbon emission value generated at each subsequent point and the corresponding updated dynamic carbon emission baseline value are obtained.

[0086] If the newly generated real-time dynamic carbon emission values ​​at each subsequent consecutive point continuously exceed the dynamic carbon emission baseline value updated at the corresponding time, then the abnormal carbon emission status is confirmed.

[0087] It should be noted that the energy consumption and emissions of vehicles on highways are usually continuous. If only a single point exceeds the standard, it may not be representative. However, if all points exceed the standard, it can reflect that there are indeed continuous factors causing abnormal carbon emissions when the vehicle is driving on that section of the road, making the judgment result more in line with the actual situation.

[0088] The attribution optimization execution module is used to obtain carbon emission associated data based on the characteristics of sudden changes in vehicle speed, changes in environmental factor data, and overall traffic conditions of road sections during periods of abnormal carbon emissions. It then identifies the abnormal attribution type based on the carbon emission associated data and generates corresponding traffic operation optimization adjustment instructions based on the attribution type.

[0089] A specific implementation process for the aforementioned carbon emission correlation data is as follows: extract the duration of abnormal carbon emission conditions and the corresponding sequence of continuous monitoring points.

[0090] Obtain the vehicle's speed sequence during the abnormal period. When the speed difference between adjacent points exceeds a preset speed threshold and the direction of change is consistent, mark the continuous speed change feature.

[0091] It should be noted that the preset speed threshold is obtained by collecting speed difference data of a large number of vehicles of the same type in the target road segment under normal driving conditions at adjacent points to form a speed change sample set. The distribution characteristics of the speed difference in the sample set, such as the mean and standard deviation, are analyzed to determine the maximum reasonable range of speed change at adjacent points under normal driving conditions. The upper limit of the normal range is used as the initial speed threshold. Through system trial operation, combined with the correlation between speed change and actual energy consumption in abnormal carbon emission cases, the initial threshold is iteratively optimized to obtain the final speed threshold.

[0092] Retrieve wind speed data for each monitoring point during the abnormal period. If the wind speed difference between adjacent points exceeds a preset wind speed threshold, mark the wind speed change feature.

[0093] It should be noted that the preset wind speed threshold is determined by collecting historical wind speed data of the target road section, statistically analyzing the distribution range of wind speed differences between adjacent monitoring points under normal weather conditions, and identifying the maximum difference of most normal wind speed changes as the wind speed threshold.

[0094] When the wind speed difference between adjacent points exceeds a preset threshold, it indicates an unnatural and sudden change in wind speed. This abrupt change significantly alters vehicle drag, leading to abnormal fluctuations in energy consumption and carbon emissions. Labeling wind speed abrupt changes can correlate these abnormal changes in environmental factors with periods of abnormal carbon emissions, providing crucial information for determining whether the anomaly is caused by a sudden environmental change.

[0095] Extract the slope baseline value of each sub-section through which the vehicle passes during the abnormal period, and mark the slope change feature when the signs of the slope values ​​of adjacent sub-sections are reversed.

[0096] The gradient changes between adjacent sections of a highway are usually continuous, and the sign of the gradient value generally does not suddenly reverse. When the sign of the gradient value reverses between adjacent sections, it means that the gradient of the road segment has changed drastically. This sudden change will significantly alter the direction of gravity acting on the vehicle, thereby affecting vehicle energy consumption and carbon emissions.

[0097] Obtain the traffic density in front of the target vehicle during the abnormal period. If the traffic density is higher than the congestion threshold, mark it as a high-density traffic feature; if it is lower than the smooth traffic threshold, mark it as a low-density traffic feature.

[0098] It should be noted that when the traffic density is higher than the congestion threshold, it indicates that there may be congestion on the road section. Vehicles are prone to frequent acceleration and deceleration, which leads to abnormal energy consumption and carbon emissions. This can help determine whether the abnormality is caused by traffic congestion.

[0099] When traffic density is below the smooth flow threshold, it indicates that traffic flow is smooth and vehicles are less constrained by traffic flow. At this time, abnormal carbon emissions are more likely to be related to the vehicles themselves or sudden environmental changes, which can help eliminate the influence of traffic flow factors.

[0100] The congestion threshold and the smooth flow threshold are determined by collecting historical traffic density data of the target road segment and analyzing the traffic operation status and energy consumption and emission characteristics under different densities.

[0101] The labeled continuous speed change features, wind speed change features, slope change features, and traffic density features are bound to the abnormal time periods and integrated into a carbon emission associated dataset.

[0102] The specific details of the above-mentioned anomaly attribution types are as follows: extracting continuous speed change characteristics, wind speed change characteristics, slope change characteristics, and traffic density characteristics from the carbon emission associated dataset.

[0103] If there are high-density traffic features and the associated dataset contains continuously abruptly marked speed changes, then retrieve the speed sequence of the vehicles ahead of the target vehicle during the abnormal period.

[0104] When the speed of a subsequent vehicle in a speed sequence is lower than the speed of the preceding vehicle, it is determined to be a traffic flow anomaly attribution type.

[0105] When a target vehicle is in a high-density traffic environment and its speed undergoes continuous abrupt changes, if the speed of subsequent vehicles ahead of it tends to be lower than that of the preceding vehicles, it indicates that there is a phenomenon of sequential deceleration of traffic flow on the road segment. This overall deceleration of traffic flow forces the target vehicle to frequently accelerate and decelerate, leading to abnormal carbon emissions. This characteristic clarifies that the abnormal carbon emissions are caused by problems inherent to the traffic flow itself, such as traffic congestion and poor traffic flow, rather than by individual vehicle factors or sudden environmental changes, thus accurately identifying the attribution type of traffic flow anomaly.

[0106] Retrieve the labeling status of wind speed change features or slope change features in the associated dataset. If any feature is labeled and its change time coincides with the abnormal period, it is determined to be an environmental change anomaly attribution type.

[0107] Wind speed and slope are important environmental factors affecting vehicle energy consumption and emissions. Abrupt changes in these factors can directly alter vehicle drag, leading to abnormal fluctuations in carbon emissions. When the associated dataset centrally identifies wind speed or slope abrupt changes, and the timing of these abrupt changes coincides with periods of abnormal carbon emissions, it indicates that sudden changes in these environmental factors are the primary cause of the carbon emission anomalies.

[0108] Check whether there is an independent continuous speed mutation feature in the associated dataset. If both conditions are met, it is determined to be an individual vehicle abnormal attribution type.

[0109] When the associated dataset contains only the independent characteristic of continuous speed change, without the characteristics of environmental factors such as wind speed change, slope change, or traffic flow anomaly such as high-density traffic, it indicates that the abnormal vehicle carbon emissions are not caused by environmental changes or traffic flow, but by the abnormal speed changes of the vehicle itself. These abnormal speed behaviors are usually related to the vehicle's own state, such as engine failure or abnormal driving habits, and are therefore judged as the vehicle individual abnormal attribution type.

[0110] The specific content of the above optimization and adjustment instructions is as follows: Based on the anomaly attribution type, a preset instruction library is matched. If it is a traffic flow anomaly, a road segment-level traffic optimization instruction is generated; if it is a sudden environmental change, a driving risk warning instruction is generated; if it is an individual vehicle anomaly, a targeted control instruction is generated.

[0111] Specifically, if there is an abnormal traffic flow, a lane opening or variable speed limit instruction will be generated; if there is a sudden change in the environment, a roadside warning broadcast instruction will be generated; if there is an individual vehicle abnormality, a target vehicle diversion instruction will be generated.

[0112] The parameters involved in the above formula are all dimensionless and calculated numerically. The formula is a formula obtained from the most recent real situation by collecting a large amount of data and simulating it with software. The preset parameters in the formula are set by those skilled in the art according to the actual situation.

[0113] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, in the form of a computer program product.

[0114] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0115] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0116] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0117] Finally, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A highway carbon emission energy consumption anomaly monitoring optimization system, characterized in that: The application relates to a dynamic carbon emission intelligent diagnosis and optimization system for a vehicle, which comprises the following modules: a vehicle feature acquisition module for identifying the license plate number and vehicle type of an entering vehicle at a toll gate; an environmental dynamic perception module for collecting the interval driving speed of a vehicle on a specific section of an expressway and environmental factor data, including wind speed and road slope value, in real time when the vehicle drives on the specific section of the expressway; a carbon emission dynamic calculation module for matching a preset fuel consumption standard value according to the vehicle type, combining real-time vehicle speed, environmental factor data and their respective increasing and decreasing influence directions on energy consumption emission to generate a real-time dynamic carbon emission value of the vehicle; an abnormal intelligent diagnosis module for setting a dynamic carbon emission reference value according to the current road traffic flow and environmental factor data, and determining that carbon emission is abnormal when the real-time dynamic carbon emission value of the vehicle exceeds the reference value; an attribution optimization execution module for obtaining carbon emission correlation data according to the vehicle speed mutation feature, environmental factor data mutation and road section overall traffic condition during the carbon emission abnormal period, identifying the abnormal attribution type according to the carbon emission correlation data, and generating corresponding traffic operation optimization adjustment instructions based on the attribution type; the specific content of the real-time dynamic carbon emission value of the vehicle is as follows: a mapping database between preset vehicle types and fuel consumption is inquired; when there is a completely matched vehicle type record in the mapping database, the unit mileage basic fuel consumption value corresponding to the vehicle type is extracted; the average driving speed of the vehicle in the current sub-interval is obtained, a negative vehicle speed correction coefficient is generated if the vehicle speed is within the speed interval range, otherwise a positive vehicle speed correction coefficient is generated; the real-time wind speed value is read, a positive wind speed correction coefficient is generated when the wind speed exceeds a preset reference wind speed threshold, otherwise the wind speed correction coefficient is set to zero; the slope reference value corresponding to the current vehicle stake number is obtained, a positive slope correction coefficient is generated if the slope value is positive, otherwise a negative slope correction coefficient is generated; the basic fuel consumption value is taken as an anchor point, and the real-time dynamic carbon emission value of the vehicle is generated according to the vehicle speed correction coefficient, the wind speed correction coefficient and the slope correction coefficient; the specific content of the dynamic carbon emission reference value is as follows: the driving speed sequence of the vehicle in front of the target vehicle is obtained, a traffic deceleration signal is generated when the speed of each subsequent vehicle in the driving speed sequence is lower than that of the previous vehicle, and a free driving signal is generated when the distance between the target vehicle and the front vehicle increases within the continuous sensing point interval; the included angle between the vehicle wind direction vector and the driving direction is calculated, and an adverse wind effect identifier is marked if the included angle is obtuse; based on the matching relationship between the expressway stake number increasing direction and the vehicle driving direction, an uphill effect identifier is marked if the driving direction is consistent with the stake number increasing direction and the slope value is positive; if the traffic deceleration signal exists, a set of dynamic carbon emission values of the vehicle in the current period, of the same vehicle type and with the same environmental effect identifier is called from a carbon emission database, the set is arranged in ascending order, and the maximum value in the last third interval is taken as the reference value; if the free driving signal exists, a preset proportion of the dynamic carbon emission value set of the same vehicle type on the current section is extracted as the reference value when the adverse wind effect identifier or the uphill effect identifier is activated; when no environmental effect identifier is activated, the median value of the carbon emission of the vehicle of the same type on the historical same period and same section is called as the reference value. The carbon emission correlation data specifically comprises the following steps: extracting a carbon emission abnormal state duration and corresponding continuous monitoring point sequence; obtaining a vehicle speed sequence in the abnormal duration, and marking a speed continuous mutation feature when a speed difference between adjacent points exceeds a preset speed threshold and a change direction is consistent; searching for wind speed data of each monitoring point in the abnormal duration, and marking a wind speed mutation feature when a wind speed difference between adjacent points exceeds a preset wind speed threshold; extracting a slope reference value of each sub-interval through which the vehicle passes in the abnormal duration, and marking a slope mutation feature when a sign of slope values of adjacent sub-intervals reverses; obtaining a vehicle flow density in front of the target vehicle in the abnormal duration, marking a high-density traffic feature when the vehicle flow density is higher than a congestion threshold, and marking a low-density traffic feature when the vehicle flow density is lower than a smooth threshold; and binding the marked speed continuous mutation feature, wind speed mutation feature, slope mutation feature and vehicle flow density feature to the abnormal duration, and integrating the features into a carbon emission correlation data set. The abnormal attribution type specifically comprises the following steps: extracting the speed continuous mutation feature, wind speed mutation feature, slope mutation feature and vehicle flow density feature of the carbon emission correlation data set; if the high-density traffic feature exists and the speed continuous mutation feature is marked in the correlation data set, the driving speed sequence of a continuous vehicle in front of the target vehicle in the abnormal duration is called; and when a speed of a subsequent vehicle in the driving speed sequence is lower than a speed of a previous vehicle, the traffic flow abnormal attribution type is determined. The marked state of the wind speed mutation feature or slope mutation feature in the correlation data set is searched, and if any feature is marked and a mutation time of the feature coincides with the abnormal duration, the environmental mutation abnormal attribution type is determined; and whether the speed continuous mutation feature exists independently in the correlation data set is checked, and if the feature exists, the vehicle individual abnormal attribution type is determined.

2. The highway carbon emission energy consumption anomaly monitoring optimization system of claim 1, wherein: The vehicle feature collection module specifically comprises the following steps: When a local induction coil detects that a vehicle enters an ETC gate area, an infrared camera is triggered to capture a vehicle head image; A candidate region set is generated by filtering based on a license plate color gamut feature, and an effective license plate region is screened through horizontal gradient scanning, in which a continuous edge density exceeds a threshold value and a length-width ratio is consistent; An effective license plate region is subjected to dynamic threshold binary segmentation, and if a distance between adjacent characters exceeds a set proportion and a single character effective pixel exceeds a set proportion, segmented characters are output; Character topological features are extracted and compared with a pre-stored template at a pixel level, and if the features are completely consistent, an identification result is output; Vehicle contour data is obtained through multiple-view cameras synchronously, and a vehicle type preliminary judgment result is generated based on a length-width-height ratio and an axle distance feature; The vehicle contour data is geometrically aligned with a vehicle type database reference model to calculate an overlap degree, and if a model overlap degree exceeds a set threshold value, corresponding vehicle type data is output.

3. The highway carbon emission energy consumption anomaly monitoring optimization system of claim 1, wherein: The interval driving speed collection steps are as follows: A plurality of intermediate sensing points are added at a preset distance interval on a vehicle driving road section; When a vehicle passes through any sensing point, a license plate number of the vehicle is captured and an accurate time stamp is recorded; For two adjacent sensing points through which the vehicle continuously passes on the road section, a preset actual distance between the adjacent points is taken as a driving distance, and a time stamp difference between the two adjacent sensing points through which the vehicle passes is taken as a driving time; An average driving speed of the vehicle in a sub-interval between the adjacent points is calculated based on the driving distance and the driving time.

4. The highway carbon emission energy consumption anomaly monitoring optimization system of claim 3, wherein: The environmental factor data collection step is as follows: Call the real-time wind speed data of the existing roadside weather station of the target section, dynamically match the wind speed monitoring value of the nearest weather station based on the real-time GPS position coordinates of the vehicle, and bind the latest wind speed data of the associated weather station of the sensing point when the vehicle passes through the sensing point. Pre-store the slope reference value of each sub-interval of the target section in the database, and obtain the real-time stake number position of the vehicle based on the sensing device when the vehicle passes through the sensing point of the section; According to the real-time stake number position of the vehicle, query the sub-interval containing the stake number in the database; Extract the slope reference value of the matched sub-interval as the current road slope value.

5. The highway carbon emission energy consumption anomaly monitoring optimization system of claim 1, wherein: The specific content of the carbon emission anomaly is as follows: Obtain the real-time dynamic carbon emission value and the dynamic carbon emission reference value of the current vehicle; Real-time comparison of real-time dynamic carbon emission value and dynamic carbon emission reference value; If the real-time dynamic carbon emission value exceeds the dynamic carbon emission reference value, mark the carbon emission state of the vehicle at the specific section position and the current time as preliminary anomaly; After the vehicle continues to drive and passes through the subsequent continuous monitoring point of the section, obtain the real-time dynamic carbon emission value newly generated at each subsequent point and the updated dynamic carbon emission reference value at the corresponding time; If the real-time dynamic carbon emission value newly generated at each subsequent continuous point continuously exceeds the updated dynamic carbon emission reference value at the corresponding time, the carbon emission anomaly state is confirmed to be established.

6. The highway carbon emission energy consumption anomaly monitoring optimization system of claim 1, wherein: The specific content of the optimization adjustment instruction is as follows: According to the anomaly attribution type, match the preset instruction library, generate road section level traffic optimization instructions if it is traffic flow anomaly, generate driving risk early warning instructions if it is environmental mutation, and generate directional control instructions if it is vehicle individual anomaly.

Images