A method for predicting arrival time of fuel transport vehicles

By analyzing the historical driving information and geospatial information of fuel transport vehicles, combining real-time traffic restrictions, a prediction model is built, and the accuracy of the arrival time prediction of fuel transport vehicles is solved, improving the operation management level and supply chain coordination.

CN118609373BActive Publication Date: 2024-11-05HUANENG INFORMATION TECH CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411080812.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-08
Publication Date
2024-11-05
Estimated Expiration
2044-08-08

AI Technical Summary

Technical Problem

The prior art cannot accurately predict the arrival time of fuel transport vehicles, resulting in waste of resources, increased costs and poor supply chain synergy, which in turn affects operational efficiency.

Method used

By obtaining the historical driving information and geospatial information of fuel transport vehicles, analyzing and building prediction models, combining real-time traffic restrictions information to accurately predict the arrival time of the vehicle.

Benefits of technology

A scientific and reasonable transportation planning and resource allocation have been achieved, resource waste has been avoided, emergency response capabilities and supply chain coordination have been improved, and overall operation and management level has been improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118609373B_ABST
    Figure CN118609373B_ABST
Patent Text Reader

Abstract

The present invention provides a method for predicting the arrival time of a fuel dispatch vehicle, which belongs to the field of intelligent transportation and data analysis technology, including obtaining historical driving information of the fuel dispatch vehicle, and at the same time, obtaining the geographic space information of the driving path of the fuel dispatch vehicle; analyzing the historical driving information and the geographic space information to determine the first feature, and building a prediction model based on the first feature; obtaining the driving conditions of the fuel dispatch vehicle in real time to determine the first information, and at the same time, obtaining the traffic restriction information of the driving path of the fuel dispatch vehicle in real time; based on the first information, the traffic restriction information and the prediction model, the real-time prediction of the arrival time of the fuel dispatch vehicle is realized. The vehicle arrival time can be predicted in real time and accurately, the transportation plan and resources can be planned scientifically and reasonably, and refined inventory management can be realized, resource waste and cost waste can be avoided, emergency handling capabilities can be improved, supply chain synergy can be improved, and the overall operation management level can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent transportation and data analysis, and in particular to a method for predicting the arrival time of a fuel transport vehicle. Background Art

[0002] Fuel transportation is a key link in maintaining normal operation of energy-consuming industries such as thermal power plants, refineries, gasoline and liquefied gas. The inability to accurately predict the arrival time of fuel transportation vehicles will lead to improper fuel inventory management, which will in turn cause waste of resources and increased costs. Faced with sudden increases in fuel demand or unforeseen supply disruptions, the emergency response capability will be weakened, and the supply chain coordination will be poor, resulting in low overall operational efficiency.

[0003] Therefore, the present invention provides a method for predicting the arrival time of a fuel transport vehicle. Summary of the invention

[0004] The invention provides a method for predicting the arrival time of a fuel transport vehicle, which is used to solve the defects of prediction in the prior art.

[0005] In one aspect, the present invention provides a method for predicting the arrival time of a fuel transport vehicle, comprising:

[0006] S101: Acquire historical driving information of fuel transport vehicles, and at the same time, acquire geographic space information of the driving path of the fuel transport vehicles;

[0007] S102: Analyze historical driving information and geographic space information to determine a first feature, and build a prediction model based on the first feature;

[0008] S103: Acquire the driving condition of the fuel dispatching vehicle in real time to determine the first information, and at the same time, acquire the traffic restriction information of the driving path of the fuel dispatching vehicle in real time;

[0009] S104: Realize real-time prediction of the arrival time of the fuel delivery vehicle based on the first information, the traffic restriction information and the prediction model.

[0010] According to a method for predicting the arrival time of a fuel dispatching vehicle provided by the present invention, the historical driving information includes the historical driving routes, historical loading amounts, historical driving times and historical meteorological information of all fuel dispatching vehicles;

[0011] The geographic space information includes the traffic network, traffic flow information and road condition information corresponding to the historical driving route.

[0012] According to a method for predicting the arrival time of a fuel transport vehicle provided by the present invention, historical driving information and geographic space information are analyzed to determine a first feature, including:

[0013] Divide the traffic network into sections based on the historical driving routes of all fuel-using vehicles;

[0014] Based on the traffic flow information of each road section in one day, a working day hyperbola and a non-working day hyperbola are drawn, wherein the working day hyperbola includes a first traffic flow curve and a first vehicle speed curve, and the non-working day hyperbola includes a second traffic flow curve and a second vehicle speed curve;

[0015] Analyze the change trends of the working day hyperbola and the non-working day hyperbola to determine the first fitting function , the second fitting function , and determine the traffic flow characteristics of each road segment based on weekdays and non-working days.

[0016] According to a method for predicting the arrival time of a fuel transport vehicle provided by the present invention, historical driving information and geographic space information are analyzed to determine a first feature, including:

[0017] Analyze the road condition information of all road sections after preprocessing and build a GIS model, where the preprocessing includes format conversion and coordinate system one;

[0018] Divide historical driving information into training set and test set;

[0019] Calculate the second predicted driving speed of the fuel delivery vehicle on the corresponding road section based on the road section length of each road section, all road section slopes, all turning radii, and the restricted driving speed determined by the GIS model, and the historical driving time of all fuel delivery vehicles on each road section under normal weather conditions in the training set;

[0020] Among them, the value of i is 1, 2, 3, ..., N, Indicates the fuel transport vehicle loading capacity is The first predicted driving speed on road section i, represents the impact of the load of the fuel transport vehicle on the driving speed in section i, It represents the impact of all slopes in section i on the driving speed of fuel transport vehicles. represents the impact of all turns in section i on the speed of fuel transport vehicles, represents the length of road segment i, It represents the time when the fuel transport vehicle a passes through the road section i for the jth time under normal weather conditions. represents the time when the fuel dispatching vehicle a passes through the road section i for the jth time under normal weather conditions, N1 represents the number of fuel dispatching vehicles, and N2 represents the number of times the fuel dispatching vehicle a travels on the road section i under normal weather conditions. Indicates the loading capacity of the fuel transport vehicle, represents the load of fuel calling vehicle a when it travels on road section i for the jth time, represents the load influencing factor of road section i, represents the number of slopes in road section i, represents the inclination of the k-th slope of section i, represents the slope influence factor of the k-th slope of section i, represents the number of turns in road section i, represents the lth turning radius of road section i, represents the turning influence factor of the lth turning radius of section i, Indicates the fuel transport vehicle loading capacity is The second predicted driving speed on road section i, Indicates the speed limit of road section i.

[0021] According to a method for predicting the arrival time of a fuel transport vehicle provided by the present invention, historical driving information and geographic space information are analyzed to determine a first feature, including:

[0022] Extracting the historical driving time of each road section under different historical meteorological information in the historical driving information, wherein the historical meteorological information includes multiple abnormal weather conditions;

[0023] Based on the historical driving time and the second predicted driving speed of each road section under each abnormal weather, the predicted impact value of the abnormal weather on the driving speed of the fuel transport vehicle on each road section is calculated;

[0024] in, represents the predicted impact value of abnormal weather m on the driving speed of the fuel transfer vehicle during its driving on section i, N3 represents the number of times the fuel transfer vehicle a drives on section i under abnormal weather m, It represents the time when the fuel transport vehicle a leaves the road section i for the pth time under abnormal weather m. It represents the time when the fuel transport vehicle a enters the road section i for the pth time under abnormal weather m. represents the intensity of abnormal weather m when fuel transport vehicle a travels on road section i for the pth time, It represents the first predicted impact value of abnormal weather m on the driving speed of the fuel transport vehicle during driving on road section i. represents the second predicted impact value of abnormal weather m on the driving speed of the fuel transport vehicle during its driving on road section i, , Respectively represent the weight coefficients of the first predicted impact value and the second predicted impact value.

[0025] According to a method for predicting the arrival time of a fuel transport vehicle provided by the present invention, historical driving information and geographic space information are analyzed to determine a first feature, including:

[0026] Extract each historical departure time of each fuel-calling vehicle in the historical driving information and perform first time coding;

[0027] in, The first time code representing the historical departure time of the fuel calling vehicle a during its b-th trip, Indicates the departure code for working day / non-working day. represents the departure hour code, and the value of b is 1, 2, 3, ..., Nb;

[0028] Extracting each historical arrival time of each fuel calling vehicle in the historical driving information and performing a second time coding;

[0029] in, The second time code representing the historical arrival time of the fuel calling vehicle a during its b-th trip, Indicates the driving code on weekdays. Indicates the driving code on non-working days. Indicates the arrival code for working day / non-working day. Indicates the arrival hour code, and the value of b is 1, 2, 3, ..., Nb;

[0030] Extract each historical driving route of each fuel-calling vehicle from the historical driving information, and encode the route according to the road section;

[0031] The first feature includes a first time code, a route code, traffic flow characteristics, a second predicted driving speed, and a predicted impact value of abnormal weather.

[0032] According to a method for predicting the arrival time of a fuel transport vehicle provided by the present invention, a prediction model is constructed based on a first feature, comprising:

[0033] The prediction model is constructed by taking the first feature as input and the second time code as output;

[0034] The first time codes, historical meteorological information, and historical loading amounts of all fuel-calling vehicles in the test set are respectively input into the prediction model, the corresponding first arrival times are predicted, and the first arrival times are given third time codes;

[0035] Based on the comparison results of the second time code and the third time code of each fuel-calling vehicle in the test set, the performance of the prediction model is evaluated and optimized.

[0036] According to a method for predicting the arrival time of a fuel transport vehicle provided by the present invention, a real-time prediction of the arrival time of a fuel transport vehicle is achieved based on first information, traffic restriction information and a prediction model, including:

[0037] Inputting the first information and the traffic restriction information into a prediction model to predict the arrival time of the fuel delivery vehicle;

[0038] Among them, the first information includes the real-time departure time, real-time driving route, real-time loading volume and real-time weather information of the fuel transportation vehicle.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] By analyzing the historical driving information and geographic spatial information of fuel transport vehicles, the first feature is determined and a prediction model is constructed. According to the first information of fuel transport vehicles and traffic restriction information obtained in real time, the vehicle arrival time is predicted in real time in combination with the prediction model. The vehicle arrival time can be accurately predicted in real time, and transportation plans and resources can be scientifically and rationally planned to achieve refined inventory management, avoid waste of resources and costs, improve emergency handling capabilities, enhance supply chain collaboration, and improve the overall operation management level. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0042] Figure 1 It is a flow chart of a method for predicting arrival time of a fuel transport vehicle provided by an embodiment of the present invention;

[0043] Figure 2 It is a workday hyperbola of a method for predicting arrival time of a fuel transport vehicle provided by an embodiment of the present invention;

[0044] Figure 3 It is a non-working day hyperbola of a fuel dispatch vehicle arrival time prediction method provided by an embodiment of the present invention;

[0045] Figure 4 It is a fitted hyperbola of a method for predicting arrival time of a fuel transport vehicle provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] Embodiment 1:

[0048] The embodiment of the present invention provides a method for predicting the arrival time of a fuel transport vehicle. Figure 1 As shown, including:

[0049] S101: Acquire historical driving information of fuel transport vehicles, and at the same time, acquire geographic space information of the driving path of the fuel transport vehicles;

[0050] S102: Analyze historical driving information and geographic space information to determine a first feature, and build a prediction model based on the first feature;

[0051] S103: Acquire the driving condition of the fuel dispatching vehicle in real time to determine the first information, and at the same time, acquire the traffic restriction information of the driving path of the fuel dispatching vehicle in real time;

[0052] S104: Realize real-time prediction of the arrival time of the fuel delivery vehicle based on the first information, the traffic restriction information and the prediction model.

[0053] In this embodiment, the historical driving information includes the historical driving route, historical loading amount, historical driving time and historical weather information of each driving of each fuel delivery vehicle.

[0054] In this embodiment, the geographic space information includes the traffic network, traffic flow information, and road condition information of each road section included in all historical driving routes.

[0055] In this embodiment, the first feature includes a first time code, a route code, traffic flow characteristics, a second predicted driving speed, and a predicted impact value of abnormal weather.

[0056] In this embodiment, the first information represents real-time information of the fuel transport vehicle.

[0057] In this embodiment, the traffic restriction information indicates restriction conditions that affect traffic flow in real time, including road closures or construction, traffic control, traffic accidents, and special events.

[0058] In this embodiment, the input and output of the prediction model are the first feature and the second time code respectively.

[0059] The beneficial effects of the above technical solution are as follows: by analyzing the historical driving information and geographic spatial information of the fuel transport vehicle to determine the first feature, and constructing a prediction model, the vehicle arrival time is predicted in real time based on the first information of the fuel transport vehicle and the traffic restriction information obtained in real time, combined with the prediction model. The vehicle arrival time can be predicted in real time and accurately, and the transportation plan and resources can be scientifically and reasonably planned, and refined inventory management can be achieved, thus avoiding waste of resources and costs, improving emergency handling capabilities, enhancing supply chain coordination, and improving the overall operation management level.

[0060] Embodiment 2:

[0061] The embodiment of the present invention provides a method for predicting the arrival time of a fuel dispatching vehicle, wherein the historical driving information includes the historical driving routes, historical loading amounts, historical driving times, and historical meteorological information of all fuel dispatching vehicles;

[0062] The geographic space information includes the traffic network, traffic flow information and road condition information corresponding to the historical driving route.

[0063] In this embodiment, the historical driving routes and historical times of the historical driving positions can be obtained by the same GPS tracking device or driving recorder.

[0064] In this embodiment, the historical travel time includes the historical departure time, the historical arrival time, and the historical time at the historical travel location.

[0065] In this embodiment, the historical meteorological information includes historical rainfall, historical wind speed and other information.

[0066] In this embodiment, the traffic network includes traffic infrastructure data such as road networks, intersections, highways, and main roads.

[0067] In this embodiment, the traffic flow includes traffic conditions in different time periods and different areas.

[0068] In this embodiment, the road condition information includes information such as road surface quality, slope, speed limit, and turning radius, which affect the speed and route selection of the vehicle.

[0069] The beneficial effects of the above technical solution are as follows: by determining historical driving information and geographic spatial information, sufficient and accurate data can be provided for building a prediction model, thereby improving prediction accuracy.

[0070] Embodiment 3:

[0071] The embodiment of the present invention provides a method for predicting the arrival time of a fuel transport vehicle, which analyzes historical driving information and geographic space information to determine a first feature, including:

[0072] Divide the traffic network into sections based on the historical driving routes of all fuel-using vehicles;

[0073] Based on the traffic flow information of each road section in one day, a working day hyperbola and a non-working day hyperbola are drawn, wherein the working day hyperbola includes a first traffic flow curve and a first vehicle speed curve, and the non-working day hyperbola includes a second traffic flow curve and a second vehicle speed curve;

[0074] Analyze the change trends of the working day hyperbola and the non-working day hyperbola to determine the first fitting function , the second fitting function , and determine the traffic flow characteristics of each road segment based on weekdays and non-working days.

[0075] In this embodiment, there is a flat straight road between every two road sections, and roads with slopes or turns are divided into sections.

[0076] In this embodiment, if Figure 2 As shown, the horizontal coordinate of the weekday hyperbola is 0-23 hours, and the vertical coordinate is the first average traffic volume and the first average speed corresponding to each hour on weekdays during the historical driving time. Figure 2 The blue curve in the figure represents the first average traffic flow curve of a certain working day, and the red curve represents the first average vehicle speed curve of a certain working day. In the actual process of determining the traffic flow characteristics, the first average traffic flow curves of all working days within the historical driving time are plotted in the working day hyperbola. At the same time, the first average vehicle speed curves of all working days within the historical driving time are plotted in the working day hyperbola.

[0077] In this embodiment, if Figure 3 As shown, the horizontal coordinate of the non-working day hyperbola is 0-23 hours, and the vertical coordinate is the second average traffic volume and the second average speed corresponding to each hour on non-working days during the historical driving time. Figure 3 The blue curve in the figure represents the second average traffic flow curve of a non-working day, and the red curve represents the second average vehicle speed curve of a non-working day. In the actual process of determining the traffic flow characteristics, the second average traffic flow curves of all non-working days within the historical driving time are plotted in the non-working day hyperbola. At the same time, the second average vehicle speed curves of all non-working days within the historical driving time are plotted in the working day hyperbola.

[0078] In this embodiment, if Figure 4 As shown, Figure 4 The blue curve in the figure represents the first fitting function, and the red curve represents the second fitting function. Figure 2 All the first average traffic flow curves and Figure 3 All the first average traffic flow curves in determine the first fitting function, according to Figure 2 All the second average traffic flow curves and Figure 3 The second fitting function is determined by all the second average traffic flow curves in the .

[0079] In this embodiment, the first vehicle flow curve reflects the trend of the average vehicle flow rate changing with the hour on a working day, and the first vehicle speed curve reflects the trend of the average vehicle speed changing with the hour on a working day.

[0080] In this embodiment, the second traffic flow curve reflects the trend of the average traffic flow on non-working days with the hour, and the second vehicle speed curve reflects the trend of the average vehicle speed on non-working days with the hour.

[0081] In this embodiment, the first fitting function reflects the changes in the traffic flow and the average speed measurement over time during working days.

[0082] In this embodiment, the second fitting function reflects the changes in the traffic flow and the average speed measurement over time on non-working days.

[0083] The beneficial effects of the above technical solution are as follows: by analyzing historical driving routes and traffic flow information to determine the traffic flow characteristics of each road section based on weekdays and non-working days, the accuracy and efficiency of real-time prediction of the arrival time of fuel transportation vehicles can be improved, thereby flexibly arranging vehicle driving time, optimizing scheduling strategies, and avoiding cost waste.

[0084] Embodiment 4:

[0085] The embodiment of the present invention provides a method for predicting the arrival time of a fuel transport vehicle, which analyzes historical driving information and geographic space information to determine a first feature, including:

[0086] Analyze the road condition information of all road sections after preprocessing and build a GIS model, where the preprocessing includes format conversion and coordinate system one;

[0087] Divide historical driving information into training set and test set;

[0088] Calculate the second predicted driving speed of the fuel delivery vehicle on the corresponding road section based on the road section length of each road section, all road section slopes, all turning radii, and the restricted driving speed determined by the GIS model, and the historical driving time of all fuel delivery vehicles on each road section under normal weather conditions in the training set;

[0089] Among them, the value of i is 1, 2, 3, ..., N, Indicates the fuel transport vehicle loading capacity is The first predicted driving speed on road section i, represents the impact of the load of the fuel transport vehicle on the driving speed in section i, It represents the impact of all slopes in section i on the driving speed of fuel transport vehicles. represents the impact of all turns in section i on the speed of fuel transport vehicles, represents the length of road segment i, It represents the time when the fuel transport vehicle a passes through the road section i for the jth time under normal weather conditions. represents the time when the fuel dispatching vehicle a passes through the road section i for the jth time under normal weather conditions, N1 represents the number of fuel dispatching vehicles, and N2 represents the number of times the fuel dispatching vehicle a travels on the road section i under normal weather conditions. Indicates the loading capacity of the fuel transport vehicle, represents the load of fuel calling vehicle a when it travels on road section i for the jth time, represents the load influencing factor of road section i, represents the number of slopes in road section i, represents the inclination of the k-th slope of section i, represents the slope influence factor of the k-th slope of section i, 4 represents the number of turns in road section i, represents the lth turning radius of road section i, represents the turning influence factor of the lth turning radius of section i, Indicates the fuel transport vehicle loading capacity is The second predicted driving speed on road section i, Indicates the speed limit of road section i.

[0090] In this embodiment, format conversion refers to converting different measurement and statistical units in the geospatial data.

[0091] In this embodiment, the second predicted travel speed of the fuel transport vehicle on the road section varies with the load amount.

[0092] In this embodiment, the formula , represents the average travel time of fuel transport vehicle a on road section i, It represents the average travel time of all fuel transport vehicles on road section i.

[0093] In this embodiment, the formula , represents the average load of fuel transport vehicle a on road section i, It represents the average load of all fuel transport vehicles traveling on road section i.

[0094] In this embodiment, the formula middle, Represents the angle of the kth slope of section i.

[0095] The beneficial effects of the above technical solution are as follows: by analyzing road condition information to build a GIS model, and combining historical driving time to calculate the second predicted driving speed of the fuel transport vehicle on each road section, the driving speed of each road section can be accurately predicted, and the prediction accuracy of the arrival time of the prediction model can be improved, providing more optimized route planning for fuel transport vehicles, reducing driving time and fuel consumption.

[0096] Embodiment 5:

[0097] The embodiment of the present invention provides a method for predicting the arrival time of a fuel transport vehicle, which analyzes historical driving information and geographic space information to determine a first feature, including:

[0098] Extracting the historical driving time of each road section under different historical meteorological information in the historical driving information, wherein the historical meteorological information includes multiple abnormal weather conditions;

[0099] Based on the historical driving time and the second predicted driving speed of each road section under each abnormal weather, the predicted impact value of the abnormal weather on the driving speed of the fuel transport vehicle on each road section is calculated;

[0100] in, represents the predicted impact value of abnormal weather m on the driving speed of the fuel transfer vehicle during its driving on section i, N3 represents the number of times the fuel transfer vehicle a drives on section i under abnormal weather m, It represents the time when the fuel transport vehicle a leaves the road section i for the pth time under abnormal weather m. It represents the time when the fuel transport vehicle a enters the road section i for the pth time under abnormal weather m. represents the intensity of abnormal weather m when fuel transport vehicle a travels on road section i for the pth time, It represents the first predicted impact value of abnormal weather m on the driving speed of the fuel transport vehicle during driving on road section i. represents the second predicted impact value of abnormal weather m on the driving speed of the fuel transport vehicle during its driving on road section i, , Respectively represent the weight coefficients of the first predicted impact value and the second predicted impact value.

[0101] In this embodiment, abnormal weather may be rainfall, strong wind, snowfall, etc.

[0102] In this embodiment, Represents the total time that all fuel transport vehicles travel on section i.

[0103] In this embodiment, It represents the total meteorological intensity of all fuel transport vehicles traveling on road section i.

[0104] In this embodiment, each abnormal weather condition in each road section corresponds to a predicted impact value.

[0105] The beneficial effects of the above technical solution are as follows: by calculating the predicted impact value of each abnormal weather condition on the driving speed of fuel transport vehicles on each road section, the impact of abnormal weather conditions on driving speed can be accurately predicted, possible travel delays can be dealt with, uncertainty can be reduced, emergency handling capabilities can be improved, and operational risks can be reduced.

[0106] Embodiment 6:

[0107] The embodiment of the present invention provides a method for predicting the arrival time of a fuel transport vehicle, which analyzes historical driving information and geographic space information to determine a first feature, including:

[0108] Extract each historical departure time of each fuel-calling vehicle in the historical driving information and perform first time coding;

[0109] in, The first time code representing the historical departure time of the fuel calling vehicle a during its b-th trip, Indicates the departure code for working day / non-working day. represents the departure hour code, and the value of b is 1, 2, 3, ..., Nb;

[0110] Extracting each historical arrival time of each fuel calling vehicle in the historical driving information and performing a second time coding;

[0111] in, The second time code representing the historical arrival time of the fuel calling vehicle a during its b-th trip, Indicates the driving code on weekdays. Indicates the driving code on non-working days. Indicates the arrival code for working day / non-working day. Indicates the arrival hour code, and the value of b is 1, 2, 3, ..., Nb;

[0112] Extract each historical driving route of each fuel-calling vehicle from the historical driving information, and encode the route according to the road section;

[0113] The first feature includes a first time code, a route code, traffic flow characteristics, a second predicted driving speed, and a predicted impact value of abnormal weather.

[0114] In this embodiment, the first time code represents the code of a historical departure time of a fuel calling vehicle. For example, the first time code of a fuel calling vehicle is (010), indicating that the departure time of the fuel calling vehicle is 10 o'clock on a non-working day.

[0115] In this embodiment, The value range is 0 or 1. =0 means non-working day, =1 indicates a working day.

[0116] In this embodiment, The value range is 0-23, indicating the departure time.

[0117] In this embodiment, the second time code represents the code of a historical arrival time of a fuel calling vehicle. For example, the second time code of a fuel calling vehicle is (2117), which means that the fuel calling vehicle has transported for 2 days on weekdays and 1 day on non-working days, and arrived at the destination at 7 o'clock on a weekday.

[0118] In this embodiment, The value range is 0 or 1. =0 means non-working day, =1 indicates a working day.

[0119] In this embodiment, The value range is 0-23, indicating the arrival time.

[0120] In this embodiment, the route code represents the driving route code of a fuel-calling vehicle. For example, the route code of a fuel-calling vehicle is (31567), which means that the driving route of the fuel-calling vehicle is section 3, section 1, section 5, section 6 and section 7.

[0121] The beneficial effects of the above technical solution are as follows: by performing first time coding, second time coding and route coding and determining the first feature, more accurate and comprehensive features can be provided for real-time prediction of arrival time of fuel transport vehicles, thereby enhancing the accuracy and generalization ability of the prediction model.

[0122] Embodiment 7:

[0123] The embodiment of the present invention provides a method for predicting the arrival time of a fuel transport vehicle, which constructs a prediction model based on a first feature, including:

[0124] The prediction model is constructed by taking the first feature as input and the second time code as output;

[0125] The first time codes, historical meteorological information, and historical loading amounts of all fuel-calling vehicles in the test set are respectively input into the prediction model, the corresponding first arrival times are predicted, and the first arrival times are given third time codes;

[0126] Based on the comparison results of the second time code and the third time code of each fuel-calling vehicle in the test set, the performance of the prediction model is evaluated and optimized.

[0127] In this embodiment, the third time code represents the code of the predicted arrival time of a certain historical travel of a certain fuel calling vehicle.

[0128] In this embodiment, the first feature is the input of the prediction model, the second time code is the output of the prediction model, and the prediction model generates a first arrival time based on the input and the prediction strategy and encodes to determine the third time code, wherein the prediction strategy can be PID control, fuzzy logic control, etc.

[0129] In this embodiment, the prediction model performance can be evaluated by recording the time error and direction error of the second time code and the third time code, and calculating the cumulative error of multiple comparison results, wherein the direction error includes early arrival and delayed arrival.

[0130] In this embodiment, an error index is determined according to the time error and direction error of each second time encoding and third time encoding, and the prediction model is optimized according to the error index and the accumulated error of multiple comparison results.

[0131] The beneficial effects of the above technical solution are as follows: by constructing a prediction model according to the first feature and performing performance evaluation and optimization on the model based on the test set, the accuracy and stability of real-time predictions can be improved, prediction errors can be reduced, and decision support can be improved.

[0132] Embodiment 8:

[0133] The embodiment of the present invention provides a method for predicting the arrival time of a fuel transport vehicle, which realizes real-time prediction of the arrival time of a fuel transport vehicle based on first information, traffic restriction information and a prediction model, including:

[0134] Inputting the first information and the traffic restriction information into a prediction model to predict the arrival time of the fuel delivery vehicle;

[0135] Among them, the first information includes the real-time departure time, real-time driving route, real-time loading volume and real-time weather information of the fuel transportation vehicle.

[0136] In this embodiment, the real-time driving route consists of multiple road sections.

[0137] In this embodiment, each road section corresponds to a piece of real-time weather information.

[0138] In this embodiment, each road section corresponds to a piece of traffic restriction information, including possible road closure or construction, traffic control, traffic accidents, special events, etc.

[0139] The beneficial effects of the above technical solution are as follows: through the first information, traffic restriction information and prediction model, the real-time prediction of the arrival time of the fuel transportation vehicle can be realized, the arrival time of the vehicle can be predicted in real time and accurately, the transportation plan can be planned and resources can be allocated scientifically and reasonably, and refined inventory management can be realized, thus avoiding waste of resources and costs, improving emergency handling capabilities, enhancing supply chain coordination, and improving the overall operation management level.

[0140] The method embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0141] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0142] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention 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 deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting the arrival time of a fuel transport vehicle, characterized in that: include: S101: Acquire historical driving information of fuel transport vehicles, and at the same time, acquire geographic space information of the driving path of the fuel transport vehicles; S102: Analyze historical driving information and geographic space information to determine a first feature, and build a prediction model based on the first feature; S103: Acquire the driving condition of the fuel dispatching vehicle in real time to determine the first information, and at the same time, acquire the traffic restriction information of the driving path of the fuel dispatching vehicle in real time; S104: Realizing a real-time prediction of the arrival time of the fuel transport vehicle based on the first information, the traffic restriction information and the prediction model; The first feature is determined by analyzing the historical driving information and the geographic space information, including: Divide the traffic network into sections based on the historical travel routes of all fuel-using vehicles; Based on the traffic flow information of each road section in one day, a working day hyperbola and a non-working day hyperbola are drawn, wherein the working day hyperbola includes a first traffic flow curve and a first vehicle speed curve, and the non-working day hyperbola includes a second traffic flow curve and a second vehicle speed curve; Analyze the change trends of the working day hyperbola and the non-working day hyperbola to determine the first fitting function , the second fitting function , and determine the traffic flow characteristics of each road section based on working days and non-working days; The first feature is determined by analyzing the historical driving information and the geographic space information, including: Analyze the road condition information of all road sections after preprocessing and build a GIS model, where the preprocessing includes format conversion and coordinate system one; Divide historical driving information into training set and test set; Calculate the second predicted driving speed of the fuel delivery vehicle on the corresponding road section based on the road section length of each road section, all road section slopes, all turning radii, and the restricted driving speed determined by the GIS model, and the historical driving time of all fuel delivery vehicles on each road section under normal weather conditions in the training set; Among them, the value of i is 1, 2, 3, ..., N, Indicates the fuel transport vehicle loading capacity is The first predicted driving speed on road section i, represents the impact of the load of the fuel transport vehicle on the driving speed in section i, represents the impact of all slopes in section i on the driving speed of fuel transport vehicles, represents the impact of all turns in section i on the speed of fuel transport vehicles, represents the length of road segment i, It represents the time when the fuel transport vehicle a passes through the road section i for the jth time under normal weather conditions. represents the time when the fuel dispatching vehicle a passes through the road section i for the jth time under normal weather conditions, N1 represents the number of fuel dispatching vehicles, and N2 represents the number of times the fuel dispatching vehicle a travels on the road section i under normal weather conditions. Indicates the loading capacity of the fuel transport vehicle, represents the load of fuel calling vehicle a when it travels on road section i for the jth time, represents the load influencing factor of road section i, represents the number of slopes in road section i, represents the inclination of the k-th slope of section i, represents the slope influence factor of the k-th slope of section i, 4 represents the number of turns in road section i, represents the lth turning radius of road section i, represents the turning influence factor of the lth turning radius of section i, Indicates the fuel transport vehicle loading capacity is The second predicted driving speed on road section i, Indicates the speed limit of road section i; The first feature is determined by analyzing the historical driving information and the geographic space information, including: Extracting the historical driving time of each road section under different historical meteorological information in the historical driving information, wherein the historical meteorological information includes multiple abnormal weather conditions; Based on the historical driving time and the second predicted driving speed of each road section under each abnormal weather, the predicted impact value of the abnormal weather on the driving speed of the fuel transport vehicle on each road section is calculated; in, represents the predicted impact value of abnormal weather m on the driving speed of the fuel transfer vehicle during its driving on section i, N3 represents the number of times the fuel transfer vehicle a drives on section i under abnormal weather m, It represents the time when the fuel transport vehicle a leaves the road section i for the pth time under abnormal weather m. It represents the time when the fuel transport vehicle a enters the road section i for the pth time under abnormal weather m. represents the intensity of abnormal weather m when fuel transport vehicle a travels on road section i for the pth time, It represents the first predicted impact value of abnormal weather m on the driving speed of the fuel transport vehicle during driving on road section i. represents the second predicted impact value of abnormal weather m on the driving speed of the fuel transport vehicle during its driving on road section i, , Respectively represent the weight coefficients of the first predicted impact value and the second predicted impact value; The first feature is determined by analyzing the historical driving information and the geographic space information, including: Extract each historical departure time of each fuel-calling vehicle in the historical driving information and perform first time coding; in, The first time code representing the historical departure time of the fuel calling vehicle a during its b-th trip, Indicates the departure code for working days / non-working days. represents the departure hour code, and the value of b is 1, 2, 3, ..., Nb; Extracting each historical arrival time of each fuel calling vehicle in the historical driving information and performing a second time coding; in, The second time code representing the historical arrival time of the fuel calling vehicle a during its b-th trip, Indicates the driving code on weekdays. Indicates the driving code on non-working days. Indicates the arrival code for working day / non-working day. Indicates the arrival hour code, and the value of b is 1, 2, 3, ..., Nb; Extract each historical driving route of each fuel-calling vehicle from the historical driving information, and encode the route according to the road section; The first feature includes a first time code, a route code, traffic flow characteristics, a second predicted driving speed, and a predicted impact value of abnormal weather; Wherein, building a prediction model based on the first feature includes: The prediction model is constructed by taking the first feature as input and the second time code as output; The first time codes, historical meteorological information, and historical loading amounts of all fuel-calling vehicles in the test set are respectively input into the prediction model, the corresponding first arrival times are predicted, and the first arrival times are encoded with a third time code; Based on the comparison results of the second time code and the third time code of each fuel-calling vehicle in the test set, the performance of the prediction model is evaluated and optimized.

2. A method for predicting the arrival time of a fuel transport vehicle according to claim 1, characterized in that: The historical driving information includes the historical driving routes, historical loading amounts, historical driving times and historical weather information of all fuel-requiring vehicles; The geographic space information includes the traffic network, traffic flow information and road condition information corresponding to the historical driving route.

3. A method for predicting the arrival time of a fuel transport vehicle according to claim 1, characterized in that: A real-time prediction of the arrival time of a fuel transport vehicle is achieved based on the first information, the traffic restriction information and the prediction model, including: Inputting the first information and the traffic restriction information into a prediction model to predict the arrival time of the fuel delivery vehicle; Among them, the first information includes the real-time departure time, real-time driving route, real-time loading volume and real-time weather information of the fuel transportation vehicle.