An intelligent vehicle dispatching optimization system based on big data

Abstract

The application relates to the technical field of vehicle scheduling optimization, and discloses an intelligent vehicle scheduling optimization system based on big data, which comprises a multi-source data acquisition unit, an oil consumption increment calculation unit, a refueling amount optimization unit and an information feedback module; the multi-source data acquisition unit is used for acquiring the oil consumption state, real-time traffic, weather and road geographic data of a truck; the oil consumption increment calculation unit dynamically predicts the additional oil consumption caused by real-time traffic, weather and road geographic data factors based on a machine learning model. According to the application, the oil consumption increase caused by additional weather changes, traffic jams, road maintenance and red light waiting time in the journey of a large truck is obtained based on big data, and the refueling amount of each time is planned according to the oil consumption increase, so that the problem that a large truck is stolen of oil when resting at a service area due to too much remaining amount of oil in the tank of the large truck is avoided by planning appropriate refueling amount.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle scheduling optimization, and particularly relates to an intelligent vehicle scheduling optimization system based on big data. BACKGROUND

[0002] In long-distance transportation of large trucks, excessive fuel tank capacity often results from experience-based refueling, and the trucks are prone to be stolen when parked at service areas (according to statistics, the annual loss of truck fuel theft in China exceeds 1 billion yuan). Traditional fuel consumption estimation relies on static road condition data and does not dynamically integrate real-time variables such as weather, congestion, and road slope, resulting in high error rate of refueling amount planning. Fixed refueling strategies cannot adapt to sudden road conditions (such as temporary road closure and extreme weather), which may cause the risk of running out of fuel or coexistence of excessive residual fuel.

[0003] The existing patent discloses a large vehicle anti-theft method based on artificial intelligence video recognition (publication number CN111046822A), which includes: a) capturing posture videos of thieves in various weather environments such as service areas, loading points, and unloading points of large vehicles, and intercepting images; b) manually labeling the images, with the labeling points being personnel appearing near the large vehicles; c) first establishing a training model, training according to the established neural network model, and obtaining a special target detection model for detecting whether a suspicious person is approaching the large vehicle; d) testing the recognition accuracy and improving and optimizing. In the disclosed technology of this patent, the problem of fuel theft cannot be completely avoided, especially at night when parking in remote service areas with low traffic. Due to poor network signal quality in remote areas, real-time monitoring and analysis of the network model is not timely, and the phenomenon of vehicle fuel tank damage still occurs. SUMMARY

[0004] The present application mainly solves the technical problem of providing an intelligent vehicle scheduling optimization system based on big data, which solves the problems in the background technology.

[0005] To solve the above technical problems, according to one aspect of the present application, more specifically, an intelligent vehicle scheduling optimization system based on big data, comprising a multi-source data acquisition unit, a fuel consumption increment calculation unit, a refueling amount optimization unit, and an information feedback module.

[0006] The multi-source data acquisition unit is used to acquire the fuel consumption state, real-time traffic, weather, and road geographic data of the truck.

[0007] The fuel consumption increment calculation unit dynamically predicts the additional fuel consumption caused by real-time traffic, weather, and road geographic data based on a machine learning model.

[0008] The refueling amount optimization unit is used to generate a refueling amount and a service area recommendation strategy.

[0009] Further, the intelligent vehicle scheduling optimization system further comprises a stolen oil risk estimation module and a historical data acquisition module.

[0010] Further, the stolen oil risk estimation module is configured to estimate the risk of stolen oil of the truck according to the remaining amount of gasoline or diesel in the fuel tank of the truck, the frequency of stolen oil of the truck in the current 100-kilometer region, and the night traffic volume of the current parking region of the truck, so that:

[0011] ;

[0012] In the formula, represents the risk coefficient of stolen oil of the truck parked in the current region, represents the remaining amount of oil in the fuel tank of the truck, represents the frequency of stolen oil of the truck in the current 100-kilometer region, represents the night traffic volume of the current parking region of the truck.

[0013] Further, when , it indicates that the risk of stolen oil of the truck parked in the current region is relatively large;

[0014] When , it indicates that there is a risk of stolen oil of the truck parked in the current region;

[0015] When , it indicates that the risk of stolen oil of the truck parked in the current region is very small.

[0016] Further, the historical data acquisition module is configured to acquire the stolen oil date, stolen oil location, service area information of gasoline or diesel stolen from trucks nationwide stored in the cloud database, and the traffic volume information of the current parking region of the truck.

[0017] Further, the oil consumption increment calculation unit is configured to calculate the extra fuel consumption per kilometer of the truck according to the influence of road traffic congestion degree, road average slope, red light waiting time, and wind speed, so that:

[0018] ;

[0019] In the formula, represents the extra fuel consumption per kilometer of the truck; , , , respectively represent the weight coefficients of road traffic congestion, road average slope, red light waiting time, and wind speed influence; represents the traffic congestion coefficient; represents the average slope of the road; represents the density of red and green lights in the road section; represents the headwind speed in the direction of vehicle travel.

[0020] Further, the refueling amount optimization unit calculates the remaining mileage required fuel amount according to the feedback of the fuel consumption increment calculation unit, and has:

[0021] ;

[0022] In the formula, represents the recommended refueling amount of the refueling amount optimization unit; represents the theoretical fuel consumption required to complete the remaining journey; represents the safety redundancy fuel amount for sudden road conditions; represents the current tank remaining fuel amount, which is obtained in real time by the vehicle-mounted fuel level sensor; then there is:

[0023] ;

[0024] In the formula, represents the remaining mileage from the current position to the destination or the next recommended service area; represents the reference fuel consumption of the vehicle when empty / full.

[0025] Further, the information feedback module is used to send the next refueling amount and the related information of the next refueling service area to the truck driver according to the refueling information analyzed by the refueling amount optimization unit.

[0026] The intelligent vehicle scheduling optimization system based on big data provided by the application has the following effects compared with the prior art:

[0027] 1. According to the big data, the present application obtains the distance of the large truck and the fuel consumption increase caused by additional weather changes, traffic jams, road repairs and red light waiting time in the distance, and plans the refueling amount each time according to the fuel consumption increase. By planning appropriate refueling amount, the problem of being stolen oil when the large truck rests in the service area due to too much remaining amount in the tank can be avoided.

[0028] 2. The present application associates the refueling amount planning with the oil stealing probability, introduces public security data to dynamically analyze the risk size of the current area of truck oil stealing, and through the risk coefficient, the driver can further assist in trip scheduling and tank oil amount planning.

[0029] 3. The present application quantifies the risk coefficient based on the tank remaining amount, the regional oil stealing frequency and the night traffic flow, and then assists the driver to select a low-risk service area, which can greatly avoid the economic loss of the truck driver.

[0030] 4. The present application obtains real-time traffic, weather and road geographic information through multi-source data, and accurately predicts the additional fuel consumption through a machine learning model, thereby improving the planning accuracy of the refueling amount. BRIEF DESCRIPTION OF DRAWINGS

[0031] Figure 1 Flow chart of the vehicle dispatching optimization system in the present application;

[0032] Figure 2 Relationship diagram of the oil stealing risk coefficient and the fuel tank remaining amount in the present application;

[0033] Figure 3 Relationship diagram of the additional fuel consumption and the traffic jam coefficient in the present application;

[0034] Figure 4 Relationship diagram of the recommended refueling amount and the remaining mileage in the present application. DETAILED DESCRIPTION

[0035] To make the technical solution of the present application clearer, the present application is further described in detail below in combination with the drawings and specific embodiments.

[0036] Embodiment 1

[0037] As shown in Figure 1 , according to one aspect of the present application, an intelligent vehicle dispatching optimization system based on big data is provided, which comprises a multi-source data acquisition unit, a fuel consumption increment calculation unit, a refueling amount optimization unit and an information feedback module; the multi-source data acquisition unit is used to acquire the fuel consumption state of the truck driving, real-time traffic, weather and road geographic data; the fuel consumption increment calculation unit is used to dynamically predict the additional fuel consumption caused by real-time traffic, weather and road geographic data factors based on a machine learning model; the refueling amount optimization unit is used to generate a refueling amount and service area recommendation strategy.

[0038] Embodiment 2

[0039] As shown in Figure 1 , 2 , the intelligent vehicle dispatching optimization system further comprises a stolen oil risk estimation module and a historical data acquisition module; the historical data acquisition module is used to acquire the stolen date, stolen location and service area information of the national truck gasoline or diesel oil stored in the cloud database and the vehicle flow information of the current parking area of the truck. The stolen oil risk estimation module is used to estimate the risk of the truck being stolen oil according to the remaining amount of gasoline or diesel oil in the fuel tank of the truck, the frequency of the truck being stolen oil in the current 100 km area, and the nighttime vehicle flow of the current parking area of the truck, so that:

[0040] ;

[0041] In the formula, represents the risk coefficient of the truck being stolen oil in the current area, represents the remaining oil amount in the current fuel tank of the truck, represents the frequency of the truck being stolen oil in the current 100 km area, Night traffic volume of the current parking area of the truck.

[0042] Wherein, the risk coefficient of the truck being stolen oil in the current area is calculated for each time. The current remaining fuel tank of the truck is taken as , the frequency of the truck being stolen oil in the current area is taken as (times / month), and the night traffic volume of the current parking area of the truck is taken as (vehicles / hour. The calculation of the night traffic volume is from 22:00 to 6:00 the next day). Then there is:

[0043]

[0044] From the above calculation, it can be known that the risk coefficient of the truck being stolen oil in the current area is . And by comparing multiple sets of data, there is:

[0045] Table 1 Partial implementation parameters and risk status of the truck being stolen oil

[0046]

[0047] From the above table 1 data, it can be known that when the sample data tends to infinity, a division line of the risk coefficient P is appeared to divide whether the truck is stolen oil or not, that is, when , it means that the risk of the truck being stolen oil in the current parking area is large; when , it means that there is a risk of the truck being stolen oil in the current parking area; when , it means that the risk of the truck being stolen oil in the current parking area is small.

[0048] Example 3

[0049] As shown in Figure 3 , the fuel consumption increment calculation unit is used to calculate the extra fuel consumption per kilometer of the truck according to the influence of road traffic congestion, road average slope, traffic light waiting time and wind speed, so there is:

[0050] ;

[0051] In the formula, , represents the extra fuel consumption per kilometer of the truck; , , , respectively represent the weight coefficients of road traffic congestion, road average slope, traffic light waiting time and wind speed influence. The calculation method of the fuel consumption influence weight coefficient of each factor is:

[0052] 1) Train the historical driving data by machine learning.

[0053] 2) Training data is collected by recording the actual fuel consumption of the vehicle on 100 different congested, sloped, and signalized road segments.

[0054] 3) Output data. The trained experience data has: ( L / km·congestion coefficient), ( L / km·slope), ( L / km·signal density), ( L / km·wind speed).

[0055] represents the traffic congestion coefficient (the traffic congestion coefficient takes the value range 0-1, wherein 0 represents smooth, and 1 represents severe congestion. The traffic congestion coefficient can obtain the congestion index through the real-time road condition API (such as Gaode map)).

[0056] represents the average slope of the road (the percentage of the climbing height difference to the horizontal distance of the road segment is calculated through the GIS elevation data. For example, if the climbing height is 10 meters per kilometer, then the slope is 1%); represents the signal density in the road segment (the signal density is calculated according to the map data to count the number of signals per kilometer. For example, there are 8 signals in a 5-kilometer road segment, and the density is 1.6 per kilometer); represents the headwind speed of the vehicle driving direction (the headwind speed is obtained through the weather API to obtain the real-time wind speed).

[0057] As shown in Figure 4 , the refueling amount optimization unit calculates the required refueling amount for the remaining mileage according to the feedback of the fuel consumption increment calculation unit, and has:

[0058] ;

[0059] In the formula, represents the recommended refueling amount of the refueling amount optimization unit; represents the theoretical fuel consumption required to complete the remaining journey; represents the safety redundancy oil amount, which is used to cope with sudden road conditions (the safety coefficient defaults the redundancy of 20%. And can be dynamically adjusted according to the security risk of the service area: only 10% redundancy in high-risk security areas to reduce stolen oil, and 30% redundancy in low-risk security areas to improve fault tolerance); represents the current tank remaining oil amount, which is obtained in real time through the vehicle-mounted oil level sensor; then there is:

[0060] ;

[0061] In the formula, represents the remaining mileage from the current position to the destination or the next recommended service area; represents the baseline fuel consumption of the vehicle when it is empty / full.

[0062] The remaining fuel quantity of a truck oil tank (liters), and the recommended refueling quantity of the refueling quantity optimization unit is calculated. The reference fuel consumption of the truck when fully loaded is (liters / km). Among them, the real-time environmental data of this trip are:

[0063] The traffic congestion coefficient is taken as , (indicating toxic congestion), the average road slope is taken as , , the density of traffic lights in the road section is taken as , , the wind speed of the vehicle driving direction is taken as , , then there is:

[0064]

[0065] From the above calculation, it can be known that the additional fuel consumption of the truck per kilometer is (liters / km). The theoretical fuel consumption required for the truck to complete the remaining journey is calculated, and there is:

[0066]

[0067] Then it can be known that the theoretical fuel consumption required for the truck to complete the remaining journey is (liters). Then the recommended refueling quantity of the refueling quantity optimization unit is calculated, and there is:

[0068]

[0069] From the above calculation, it can be known that the recommended refueling quantity of the refueling quantity optimization unit is (liters).

[0070] Example 4

[0071] The information feedback module is used to send the next refueling quantity and the related information of the next refueling service area to the truck driver according to the refueling information analyzed by the refueling quantity optimization unit.

[0072] The above-described embodiments only express several embodiments of the present application, and the description is more specific and detailed, but it cannot be understood as limiting the scope of the patent of the present application. It should be noted that for ordinary skilled persons in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A big data based intelligent vehicle dispatch optimization system, characterized in that, The system comprises a multi-source data acquisition unit, an oil consumption increment calculation unit, a refueling quantity optimization unit and an information feedback module. The multi-source data acquisition unit is configured to acquire the oil consumption state, real-time traffic, weather and road geographic data of the truck; The oil consumption increment calculation unit is configured to dynamically predict the additional oil consumption caused by real-time traffic, weather and road geographic data based on a machine learning model; The refueling quantity optimization unit is configured to generate a refueling quantity and a service area recommendation strategy; The intelligent vehicle scheduling optimization system further comprises a stolen oil risk estimation module and a historical data acquisition module. The stolen oil risk estimation module is configured to estimate the risk of stolen oil based on the remaining amount of gasoline or diesel in the truck tank, the current frequency of stolen oil in the truck in the current 100 km area, and the current night traffic volume in the truck parking area, so that: ； In the formula, represents the risk coefficient of the truck being stolen in the current area, represents the remaining fuel in the current fuel tank of the truck, represents the frequency of the truck being stolen in the current 100 km area, represents the night traffic volume of the current parking area of the truck; The oil consumption increment calculation unit is configured to calculate the additional oil consumption per kilometer of the truck based on the influence of road traffic congestion, road average slope, red light waiting time and wind speed, so that: ； In the formula, represents the extra fuel consumption per kilometer of the truck; , , , respectively represent the weight coefficients of road traffic congestion, road average slope, red light waiting time and wind speed influence; represents the traffic congestion coefficient; represents the road average slope; represents the red light density in the road section; represents the headwind speed in the vehicle driving direction; The refueling quantity optimization unit is configured to calculate the required oil quantity for the remaining mileage based on the feedback of the oil consumption increment calculation unit, so that: ； In the formula, represents the recommended refueling amount of the refueling amount optimization unit; represents the theoretical fuel consumption required to complete the remaining trip; represents the safety redundancy fuel amount for coping with sudden road conditions; represents the current tank remaining fuel amount, which is obtained in real time by the on-board fuel level sensor; then ； In the formula, represents the remaining mileage from the current position to the destination or the next recommended service area; represents the reference fuel consumption when the vehicle is empty / full.

2. The big data based intelligent vehicle dispatch optimization system of claim 1, wherein: When the truck is parked in the current area, it indicates that the truck is parked in the current area. When the truck is parked in the current area, it indicates that there is a risk of stolen oil. When then it indicates that the truck parking in the current area has a small chance of being stolen.

3. The big data based intelligent vehicle dispatch optimization system of claim 1, wherein: The historical data acquisition module is configured to acquire the stolen date, stolen location and service area information of the truck gasoline or diesel, and the traffic volume information of the current truck parking area stored in the cloud database.

4. The big data based intelligent vehicle dispatch optimization system of claim 1, wherein: The information feedback module is configured to send the next refueling quantity and the related information of the next refueling service area to the truck driver based on the refueling information analyzed by the refueling quantity optimization unit.

Images