System and method for planning charging path of mobile charging vehicle for engineering vehicle in real time

Abstract

The invention discloses a charging path real-time planning system and method for a mobile charging vehicle for an engineering vehicle, and belongs to the technical field of charging path planning of charging vehicles, and the charging path real-time planning system for the mobile charging vehicle for the engineering vehicle comprises a data collection module which is used for collecting the vehicle condition of the engineering vehicle in real time; the data processing module is used for processing and analyzing data, calculating an optimal path and optimizing scheduling of multi-vehicle charging tasks; the path planning module is used for planning the optimal path of the charging vehicle in combination with the real-time road condition information; and the control module is used for scheduling and controlling a plurality of engineering vehicles. The method can monitor the road condition change in real time, receive the charging request of the engineering vehicle, predict the model to plan the optimal path, reduce the risk that the mobile charging vehicle enters the congestion path, reduce the residence time of the charging vehicle on the road, and can arrive at the designated position more quickly to provide the charging service for the engineering vehicle.

Description

Technical Field

[0001] The present invention belongs to the technical field of charging path planning for charging vehicles, and more specifically, it relates to a real-time charging path planning system and planning method for a mobile charging vehicle for engineering vehicles. Background Art

[0002] With the development of society, electric vehicles have the characteristics of high policy subsidies, low operating costs and low unmanned operation. Therefore, electric vehicles are gradually used in engineering vehicles, and the usage is gradually increasing. However, compared with fuel vehicles, electric vehicles have lower mileage and insufficient charging infrastructure (plug-in charging piles, charging lanes and battery replacement stations). Therefore, the popularization of electric engineering vehicles on a larger scale is greatly limited. As an emerging charging mode, mobile charging vehicles can flexibly move to the parking location of electric vehicles with insufficient power to help them replenish their power.

[0003] However, there are some problems with the existing technology: in the mobile charging vehicle path planning, priority is given to focusing on a single goal, such as the shortest distance or the fastest arrival time. When traffic congestion or other traffic accidents occur on the route, the path of the mobile charging vehicle cannot be adjusted in time, causing the charging vehicle to be stranded in the congested section for a long time and unable to reach the designated location in time, resulting in insufficient power for the engineering vehicle and the risk of operation interruption. Therefore, we propose a real-time planning system and planning method for the charging path of a mobile charging vehicle for engineering vehicles. Summary of the invention

[0004] In view of the problems existing in the prior art, the purpose of the present invention is to provide a real-time planning system and method for charging routes of mobile charging vehicles for engineering vehicles. Based on the prediction model and historical data, it can efficiently plan the optimal route, predict the possible congestion on the route in advance, and make timely adjustments to the charging route through real-time data, so as to reduce unnecessary driving time and energy consumption. To achieve the above purpose, the present invention provides the following technical solutions:

[0005] First, the real-time planning system for charging routes of mobile charging vehicles for engineering vehicles includes:

[0006] Data acquisition module: including GPS positioning unit, vehicle-mounted sensor and wireless communication unit, used to collect the vehicle condition of the engineering vehicle in real time;

[0007] Data processing module: Process and analyze the collected information, including evaluating the urgency of the charging needs of engineering vehicles, calculating the optimal path, and optimizing the scheduling of multi-vehicle charging tasks;

[0008] Route planning module: According to the real-time location and charging needs of the engineering vehicle, combined with real-time traffic information, the charging location of the engineering vehicle is specified, and the optimal route for the charging vehicle is planned;

[0009] Control module: dispatches and controls the charging requests of multiple engineering vehicles based on task priority, real-time road conditions, and charging vehicle status factors;

[0010] User interaction module: provides users with real-time traffic conditions, charging station information, route planning results, and charging progress display and query, and receives user feedback;

[0011] Database: Responsible for storing and managing various types of data in the system, including engineering vehicle information, charging vehicle information, real-time road condition data, charging station information and historical dispatch data.

[0012] Optionally, in the data acquisition module:

[0013] The GPS positioning unit activates the receiver, captures satellite signals, and extracts the location, direction information, destination, and driving path of the engineering vehicle in real time;

[0014] The vehicle-mounted sensor unit is used to detect the battery life status, vehicle status and environmental parameters of the engineering vehicle;

[0015] The wireless communication unit is installed on the engineering vehicle onboard terminal, and is used to upload the collected data to the data processing module, and receive control instructions and parameter updates from the real-time planning system of the charging path of the mobile charging vehicle for the engineering vehicle.

[0016] Optionally, the data processing module includes:

[0017] 1) Data preprocessing: receiving collected information data, removing noise data, outliers or incomplete records, and unifying the data format;

[0018] 2) Charging demand assessment: Set the power threshold, and use the machine learning algorithm to train prediction and assess the urgency of charging demand based on the importance of the current task and the remaining time of the engineering vehicle, combined with historical data;

[0019] 3) Optimal path calculation: Integrate real-time traffic information data into map data to calculate the optimal path from the current location of the engineering vehicle to the charging station;

[0020] 4) Multi-vehicle task scheduling optimization: Use intelligent optimization algorithms to sort the charging requests of engineering vehicles by urgency to form a task queue.

[0021] Optionally, the charging demand assessment includes:

[0022] The power thresholds include: 20% is the low power threshold, which requires immediate scheduling of charging tasks; 40% is the medium power threshold, which prioritizes charging tasks based on the distance and urgency of the tasks; 80% is the high power threshold, which serves as a reference point for charging completion;

[0023] Task urgency assessment: Based on the importance of the task, the remaining working time, and the backup plan, the task urgency is comprehensively assessed, with scores of 1-10 for general, 11-20 for medium, and 21-30 for emergency. The final score is obtained by rounding down the sum of the three scores, as follows:

[0024] Total score = (task importance assessment score + remaining working time assessment score + backup plan assessment score) / 3

[0025] Machine learning model prediction: at least receive the current power percentage, remaining task time, task importance score, and historical charging behavior data, and output a prediction result based on the above feature inputs to indicate the urgency of the charging demand, including urgent, relatively urgent, and general.

[0026] Optionally, calculating the optimal path includes:

[0027] Get information about road conditions, including congestion levels, accident reports, and road closures;

[0028] Access map data, including road networks, intersections, and charging station locations;

[0029] Based on the real-time traffic conditions, the algorithm is used to search for paths, and the traffic condition function h(n) is defined as:

[0030] Traffic condition function h(n) = straight-line distance (x, y) * traffic condition factor (n, g)

[0031] Where: straight-line distance (x, y) is the straight-line distance from node x to target node y;

[0032] The traffic factor (n, g) is a data factor based on real-time traffic conditions and is adjusted according to the real-time traffic conditions;

[0033] 1) When the road section is unobstructed, the road condition factor is close to 1;

[0034] 2) The more congested the road is, the road condition factor is much greater than 1;

[0035] Set the starting point s and the target point g;

[0036] Based on the map grid, the s coordinate is (0,0) and the g coordinate is (x,y);

[0037] Get real-time traffic information: On the straight road from the starting point s to the target g, a certain section of the path is congested due to an accident, so the traffic factor is 2, and the rest of the road is in good condition, so the traffic factor is 1;

[0038] Calculate the size of the traffic function h(n) of any node and obtain the value of the time cost of the node;

[0039] Initialize the list of nodes to be calculated, open list, and the list of selected nodes, closed list;

[0040] Add the starting point s to the initialized list of nodes to be calculated, openlist. The specific formula is:

[0041] f(s)=g(s)+h(s);

[0042] Among them, g(s) is the actual time cost from the starting point to the current node;

[0043] h(s) is the estimated time cost from the current node to the target node;

[0044] f(s) is the sum of the above two;

[0045] Loop through the open list to select the node n with the smallest f(s), process its neighboring node n′, update g(n′) and f(n′), and if the neighboring node n′ is not in the closed list and f(n′) is smaller, update it and add it to the open list;

[0046] Repeat the above steps until the target point g is found;

[0047] Calculate the total cost of the complete path;

[0048] Generate and output multiple routes with the shortest time under current traffic conditions.

[0049] Optionally, the total cost of the complete path includes:

[0050] Traverse each node on the path and integrate the costs between adjacent nodes;

[0051] Assuming the path consists of a node sequence P = {s, n1, n2, ..., g}, the total cost C can be calculated as:

[0052]

[0053] Where: cost_to_move_from_n i-1 _to_n i is from node n i-1 Move to node n i Costs;

[0054] Among them, n i is a node on the path.

[0055] Optionally, the path planning module includes:

[0056] Obtain real-time data through multiple channels, including vehicle location data, road condition data and traffic flow;

[0057] Integrate and analyze historical traffic data, charging demand data, and weather data to build a predictive model;

[0058] Clean the collected data, remove noise and outliers, and perform standardization;

[0059] Use machine learning algorithms to learn historical traffic data and real-time traffic data to predict traffic congestion and road closure information in the future;

[0060] Obtain the optimal path for the output of the data processing module;

[0061] Integrate the results of road condition prediction and charging demand prediction into the path planning algorithm to correct and calculate the optimal path that meets charging needs while avoiding sections where congestion may occur;

[0062] Send the planned path instructions to the mobile charging vehicle and the charging engineering vehicle to guide them to the target location for charging;

[0063] Real-time detection of vehicle driving conditions and road condition changes through on-board equipment;

[0064] Obtain charging task completion status and feedback, collect vehicle driving data and traffic congestion during traffic hours, and evaluate route planning results;

[0065] Continuously optimize the prediction model and path planning algorithm based on feedback data.

[0066] Optionally, establishing a prediction model includes:

[0067] Obtain raw data from the database and perform feature extraction, including time, location, weather conditions, historical traffic flow, and historical congestion index, and generate training sets, validation sets, and test sets;

[0068] According to the data characteristics, construct new features, including time period features, weather impact index, and remove irrelevant or redundant features;

[0069] Based on traffic congestion prediction, set up a machine learning algorithm model, and train and test the model's performance through a training set;

[0070] Adjust model parameters, improve features, or try different algorithms based on the evaluation results;

[0071] Finally, the trained machine learning algorithm model is deployed in the path planning module;

[0072] The new features include setting up morning and evening peak congestion, traffic congestion at irregular time periods, and seasonal climate changes.

[0073] In a second aspect, a method for real-time planning of a charging path for a mobile charging vehicle for an engineering vehicle adopts the real-time planning system for a charging path for a mobile charging vehicle for an engineering vehicle described in any one of the first aspects above, comprising the following steps:

[0074] S1, data collection: obtain the location, status and environmental data of engineering vehicles and mobile charging vehicles in real time through GPS, sensors and wireless communication units;

[0075] S2, data processing: pre-process the collected data, evaluate the urgency of charging demand, calculate the optimal path, and optimize the scheduling of multi-vehicle charging tasks;

[0076] S3, route planning: intelligently plan the route through the prediction model, and adjust the charging route of the mobile charging vehicle in real time based on the real-time road conditions and charging demand;

[0077] S4, control and dispatch: send the planned path instructions to the mobile charging vehicle and the engineering vehicle to be charged, and guide them to go to the target location for charging;

[0078] S5, user interaction: providing real-time traffic conditions, charging station information, route planning results, and charging progress display and query, and receiving user feedback;

[0079] S6, database management: stores and manages various types of data in the system, including engineering vehicle information, charging vehicle information, real-time road condition data, charging station information, and historical scheduling data.

[0080] Optionally, step S3 includes:

[0081] S31, collects a large amount of raw data, including road congestion, traffic accidents, construction information, weather changes, and generates a large number of road condition training sets;

[0082] S32, building a prediction model, using historical data and machine learning algorithms to build a prediction model, integrating time, weather, and holiday factors to predict changes in road conditions and charging demand distribution in the future;

[0083] S33, based on the prediction model and real-time data, a path planning algorithm is used to plan the optimal path for the mobile charging vehicle;

[0084] S34, monitoring the road condition changes of the driving route in real time, adjusting the driving route, and replanning the route;

[0085] S35, collect actual data during the charging process, evaluate the effect of path planning, and optimize the prediction model and path planning algorithm based on user feedback and actual results.

[0086] The technical effects and advantages of the present invention application are as follows: the system monitors changes in road conditions in real time, including traffic congestion, accidents and other emergencies. After receiving a charging request from an engineering vehicle, it can reasonably plan the optimal route. Then, the prediction model corrects the route based on the probability of congestion on the route in historical data to ensure that the mobile charging vehicle will not enter a congested route while driving. In addition, through real-time route adjustment, the retention time of the charging vehicle on the road is reduced, so that it can arrive at the designated location faster to provide charging services for the engineering vehicle. This helps to avoid the problem of insufficient power for the engineering vehicle due to the long-term absence of the charging vehicle, thereby reducing the risk of operational interruption.

[0087] Other features and advantages of the present invention will become apparent from the following detailed description of exemplary embodiments of the present invention with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0088] Figure 1 It is a schematic diagram of the composition of the real-time planning system for charging paths of mobile charging vehicles for engineering vehicles provided by the present invention;

[0089] Figure 2 It is a flow chart of a real-time planning method for a charging path of a mobile charging vehicle for an engineering vehicle provided by the present invention;

[0090] Figure 3 It is a flow chart of step S3 provided in the present application. DETAILED DESCRIPTION

[0091] In order to make the purpose, technical solutions and advantages of the present invention application more clear, the present invention application is further described in detail below in conjunction with specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention application and are not used to limit the present invention application. Based on the embodiments in the present invention application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention application.

[0092] like Figure 1 As shown, the present invention provides a real-time planning system for charging paths of mobile charging vehicles for engineering vehicles, including:

[0093] Data acquisition module: including GPS positioning unit, vehicle-mounted sensor and wireless communication unit, used to collect the vehicle condition of the engineering vehicle in real time;

[0094] Data processing module: Process and analyze the collected information, including evaluating the urgency of the charging needs of engineering vehicles, calculating the optimal path, and optimizing the scheduling of multi-vehicle charging tasks;

[0095] Route planning module: According to the real-time location and charging needs of the engineering vehicle, combined with real-time traffic information, the charging location of the engineering vehicle is specified, and the optimal route for the charging vehicle is planned;

[0096] Control module: dispatches and controls the charging requests of multiple engineering vehicles based on task priority, real-time road conditions, and charging vehicle status factors;

[0097] User interaction module: provides users with real-time traffic conditions, charging station information, route planning results, and charging progress display and query, and receives user feedback;

[0098] Database: Responsible for storing and managing various types of data in the system, including engineering vehicle information, charging vehicle information, real-time road condition data, charging station information and historical dispatch data.

[0099] Furthermore, through real-time data collection and analysis, we can quickly respond to the charging needs of engineering vehicles, reduce waiting time, improve overall operational efficiency, and use intelligent route planning and scheduling strategies to ensure the rational allocation of charging station and charging vehicle resources, avoid resource waste, and reduce energy consumption and labor costs caused by long waiting or driving. At the same time, we can optimize routes to reduce unnecessary driving distances and promote sustainable development: by optimizing charging management, reducing carbon emissions, and helping companies achieve green development goals.

[0100] Specifically, in the data acquisition module:

[0101] The GPS positioning unit activates the receiver, captures satellite signals, and extracts the location, direction information, destination, and driving path of the engineering vehicle in real time;

[0102] The vehicle-mounted sensor unit is used to detect the battery life status, vehicle status and environmental parameters of the engineering vehicle;

[0103] The wireless communication unit is installed on the on-board terminal of the engineering vehicle and is used to upload the collected data to the data processing module and receive control instructions and parameter updates from the system.

[0104] Furthermore, firstly, the real-time activation of the GPS positioning unit and the capture of satellite signals ensure the precise tracking of the location of the engineering vehicle and the accurate recording of the driving path, which not only provides reliable basic data for route planning, but also enables the system to monitor the dynamics of the engineering vehicle in real time, effectively preventing charging delays or resource mismatches caused by inaccurate location information;

[0105] Secondly, the comprehensive detection function of the on-board sensor unit covers multiple dimensions such as battery life status, vehicle status and environmental parameters, providing the system with rich real-time vehicle condition information;

[0106] Finally, the efficient data transmission and command receiving functions of the wireless communication unit realize the seamless connection between the data acquisition module and the data processing module. In summary, the workflow of the data acquisition module greatly improves the intelligence level and operational efficiency of the mobile charging vehicle management system.

[0107] Specifically, the data processing module includes:

[0108] 1) Data preprocessing: receiving collected information data, removing noise data, outliers or incomplete records, and unifying the data format;

[0109] 2) Charging demand assessment: Set the power threshold, and use the machine learning algorithm to train prediction and assess the urgency of charging demand based on the importance of the current task and the remaining time of the engineering vehicle, combined with historical data;

[0110] 3) Optimal path calculation: Integrate real-time traffic information data into map data to calculate the optimal path from the current location of the engineering vehicle to the charging station;

[0111] 4) Multi-vehicle task scheduling optimization: Use intelligent optimization algorithms to sort the charging requests of engineering vehicles by urgency to form a task queue.

[0112] Furthermore, through the data preprocessing step, the system can automatically identify and eliminate noise, anomalies and incomplete data, ensuring that subsequent analysis is based on high-quality data sets, thereby improving the accuracy and reliability of decision-making; in the charging demand assessment stage, machine learning algorithms are used to combine the importance of the current task of the engineering vehicle, the remaining time and historical data to accurately predict and assess the urgency of charging needs. This not only improves the accuracy and efficiency of the assessment, but also enables the system to flexibly respond to charging needs in different scenarios, ensuring that key tasks are not affected.

[0113] Optionally, the charging demand assessment includes:

[0114] The power thresholds include: 20% is the low power threshold, which requires immediate scheduling of charging tasks; 40% is the medium power threshold, which prioritizes charging tasks based on the distance and urgency of the tasks; 80% is the high power threshold, which serves as a reference point for charging completion;

[0115] Task urgency assessment: Based on the importance of the task, the remaining working time, and the backup plan, the task urgency is comprehensively assessed, with scores of 1-10 for general, 11-20 for medium, and 21-30 for emergency. The final score is obtained by rounding down the sum of the three scores, as follows:

[0116] Total score = (task importance assessment score + remaining working time assessment score + backup plan assessment score) / 3

[0117] Machine learning model prediction: at least receive the current power percentage, remaining task time, task importance score, and historical charging behavior data, and output a prediction result based on the above feature inputs to indicate the urgency of the charging demand, including urgent, relatively urgent, and general.

[0118] Furthermore, by setting the power threshold, the charging priority at different power levels can be clearly defined, thereby achieving refined management and efficient scheduling of charging tasks. Immediate scheduling at the low power threshold ensures that the engineering vehicle will not interrupt the task due to exhaustion of power, and flexible scheduling at the medium power threshold balances the task distance and urgency, making resources more reasonably utilized. The high power threshold serves as a reference point for charging completion, which helps reduce the waste of resources caused by overcharging.

[0119] Specifically, calculating the optimal path includes:

[0120] Get information about road conditions, including congestion levels, accident reports, and road closures;

[0121] Access map data, including road networks, intersections, and charging station locations;

[0122] Based on the real-time traffic conditions, the algorithm is used to search for paths, and the traffic condition function h(n) is defined as:

[0123] Traffic condition function h(n) = straight-line distance (x, y) * traffic condition factor (n, g)

[0124] Where: straight-line distance (x, y) is the straight-line distance from node x to target node y;

[0125] The traffic factor (n, g) is a data factor based on real-time traffic conditions and is adjusted according to the real-time traffic conditions;

[0126] 1) When the road section is unobstructed, the road condition factor is close to 1;

[0127] 2) The more congested the road is, the road condition factor is much greater than 1;

[0128] Set the starting point s and the target point g;

[0129] Based on the map grid, the s coordinate is (0,0) and the g coordinate is (x,y);

[0130] Get real-time traffic information: On the straight road from the starting point s to the target g, a certain section of the path is congested due to an accident, so the traffic factor is 2, and the rest of the road is in good condition, so the traffic factor is 1;

[0131] Calculate the size of the traffic function h(n) of any node and obtain the value of the time cost of the node;

[0132] Initialize the list of nodes to be calculated, open list, and the list of selected nodes, closed list;

[0133] Add the starting point s to the initialized list of nodes to be calculated, openlist. The specific formula is:

[0134] f(s)=g(s)+h(s)

[0135] Among them, g(s) is the actual time cost from the starting point to the current node;

[0136] h(s) is the estimated time cost from the current node to the target node;

[0137] f ( s ) is the sum of the above two;

[0138] Loop through the open list to select the node n with the smallest f(s), process its neighboring node n′, update g(n′) and f(n′), and if the neighboring node n′ is not in the closed list and f(n′) is smaller, update it and add it to the open list;

[0139] Repeat the above steps until the target point g is found;

[0140] Calculate the total cost of the complete path;

[0141] Generate and output multiple routes with the shortest time under current traffic conditions.

[0142] It should be noted that the above algorithm can combine the global search capability of the Dijkstra algorithm and the heuristic characteristics of the best-first search, and can give priority to expanding nodes close to the target during the search process, thereby reducing unnecessary search space and improving search efficiency. Under the guidance of an appropriate road condition function, the algorithm can find the shortest path from the starting point to the end point. When the road condition function h(n) is exactly equal to the actual cost from node n to the end point, the algorithm will guarantee to find the optimal solution; further, the above algorithm can show strong robustness when facing complex environments or uncertain factors, and can tolerate noise and uncertainty to a certain extent and find a reasonable path.

[0143] Specifically, the total cost of the complete path is:

[0144] The total cost of the complete path includes:

[0145] Traverse each node on the path and integrate the costs between adjacent nodes;

[0146] Assuming the path consists of a node sequence P = {s, n1, n2, ..., g}, the total cost C can be calculated as:

[0147]

[0148] Where: cost_to_move_from_n i-1 _to_n i is from node n i-1 Move to node n i Costs;

[0149] Among them, n i is a node on the path.

[0150] Specifically, the path planning module includes:

[0151] Obtain real-time data through multiple channels, including vehicle location data, road condition data and traffic flow;

[0152] Integrate and analyze historical traffic data, charging demand data, and weather data to build a predictive model;

[0153] Clean the collected data, remove noise and outliers, and perform standardization;

[0154] Use machine learning algorithms to learn historical traffic data and real-time traffic data to predict traffic congestion and road closure information in the future;

[0155] Obtain the optimal path for the output of the data processing module;

[0156] Integrate the results of road condition prediction and charging demand prediction into the path planning algorithm to correct and calculate the optimal path that meets charging needs while avoiding sections where congestion may occur;

[0157] Send the planned path instructions to the mobile charging vehicle and the charging engineering vehicle to guide them to the target location for charging;

[0158] Real-time detection of vehicle driving conditions and road condition changes through on-board equipment;

[0159] Obtain charging task completion status and feedback, collect vehicle driving data and traffic congestion during traffic hours, and evaluate route planning results;

[0160] Continuously optimize the prediction model and path planning algorithm based on feedback data.

[0161] Furthermore, by integrating and analyzing historical traffic data, charging demand data, and weather data, a comprehensive prediction model was built, which enables route planning to more accurately consider various factors, such as road congestion, charging station distribution, weather impact, etc., thereby improving the reliability and practicality of the route;

[0162] Furthermore, the above historical data include: frequency of road accidents, frequency of road congestion, morning rush hour road congestion, evening rush hour road congestion, etc. The prediction model uses a large number of training sets to predict possible road congestion, so that when planning the route, it can avoid sections with a high probability of congestion, thereby preventing mobile charging vehicles from entering congested sections and causing delays.

[0163] Finally, the vehicle-mounted equipment detects vehicle driving conditions and road condition changes in real time, collects charging task completion status and feedback data, and realizes a closed-loop evaluation of the path planning effect. This feedback mechanism enables the system to continuously learn and optimize, improving the accuracy and efficiency of the prediction model and path planning algorithm.

[0164] Specifically, the establishment of the prediction model includes:

[0165] Obtain raw data from the database and perform feature extraction, including time, location, weather conditions, historical traffic flow, and historical congestion index, and generate training sets, validation sets, and test sets;

[0166] According to the data characteristics, construct new features, including time period features, weather impact index, and remove irrelevant or redundant features;

[0167] Based on traffic congestion prediction, set up a machine learning algorithm model, and train and test the model's performance through a training set;

[0168] Adjust model parameters, improve features, or try different algorithms based on the evaluation results;

[0169] Finally, the trained machine learning algorithm model is deployed in the path planning module;

[0170] The new features include setting up morning and evening peak congestion, traffic congestion at irregular time periods, and seasonal climate changes.

[0171] like Figure 2 As shown, a method for real-time planning of charging paths for mobile charging vehicles for engineering vehicles adopts a real-time planning system for charging paths for mobile charging vehicles for engineering vehicles as described in any one of the first aspects above, comprising the following steps:

[0172] S1, data collection: obtain the location, status and environmental data of engineering vehicles and mobile charging vehicles in real time through GPS, sensors and wireless communication units;

[0173] S2, data processing: pre-process the collected data, evaluate the urgency of charging demand, calculate the optimal path, and optimize the scheduling of multi-vehicle charging tasks;

[0174] S3, route planning: intelligently plan the route through the prediction model, and adjust the charging route of the mobile charging vehicle in real time based on the real-time road conditions and charging demand;

[0175] S4, control and dispatch: send the planned path instructions to the mobile charging vehicle and the engineering vehicle to be charged, and guide them to go to the target location for charging;

[0176] S5, user interaction: providing real-time traffic conditions, charging station information, route planning results, and charging progress display and query, and receiving user feedback;

[0177] S6, database management: stores and manages various types of data in the system, including engineering vehicle information, charging vehicle information, real-time road condition data, charging station information, and historical scheduling data.

[0178] like Figure 3 As shown, specifically, step S3 includes:

[0179] S31, collects a large amount of raw data, including road congestion, traffic accidents, construction information, weather changes, and generates a large number of road condition training sets;

[0180] S32, building a prediction model, using historical data and machine learning algorithms to build a prediction model, integrating time, weather, and holiday factors to predict changes in road conditions and charging demand distribution in the future;

[0181] S33, based on the prediction model and real-time data, a path planning algorithm is used to plan the optimal path for the mobile charging vehicle;

[0182] S34, monitoring the road condition changes of the driving route in real time, adjusting the driving route, and replanning the route;

[0183] S35, collect actual data during the charging process, evaluate the effect of path planning, and optimize the prediction model and path planning algorithm based on user feedback and actual results.

[0184] In summary, the application system of the present invention monitors changes in road conditions in real time, including emergencies such as traffic congestion and accidents. After receiving a charging request from an engineering vehicle, it can reasonably plan the optimal route. Then, the prediction model corrects the route based on the probability of congestion in the route in historical data to ensure that the mobile charging vehicle will not enter a congested route while driving, and through real-time route adjustment, it reduces the detention time of the charging vehicle on the road, so that it can arrive at the designated location faster to provide charging services for the engineering vehicle. This helps to avoid the problem of insufficient power of the engineering vehicle due to the long-term absence of the charging vehicle, thereby reducing the risk of operational interruption.

[0185] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A real-time planning system for charging routes of mobile charging vehicles for engineering vehicles, characterized in that: include: Data acquisition module: including GPS positioning unit, vehicle-mounted sensor and wireless communication unit, used to collect the vehicle condition of the engineering vehicle in real time; Data processing module: Process and analyze the collected information, including evaluating the urgency of the charging needs of engineering vehicles, calculating the optimal path, and optimizing the scheduling of multi-vehicle charging tasks; Route planning module: According to the real-time location and charging needs of the engineering vehicle, combined with real-time traffic information, the charging location of the engineering vehicle is specified, and the optimal route for the charging vehicle is planned; Control module: dispatches and controls the charging requests of multiple engineering vehicles based on task priority, real-time road conditions, and charging vehicle status factors; User interaction module: provides users with real-time traffic conditions, charging station information, route planning results, and charging progress display and query, and receives user feedback; Database: Responsible for storing and managing various types of data in the system, including engineering vehicle information, charging vehicle information, real-time road condition data, charging station information and historical dispatch data.

2. The real-time planning system for charging paths of mobile charging vehicles for engineering vehicles according to claim 1 is characterized in that: In the data acquisition module: The GPS positioning unit activates the receiver, captures satellite signals, and extracts the location, direction information, destination, and driving path of the engineering vehicle in real time; The vehicle-mounted sensor unit is used to detect the battery life status, vehicle status and environmental parameters of the engineering vehicle; The wireless communication unit is installed on the engineering vehicle onboard terminal, and is used to upload the collected data to the data processing module, and receive control instructions and parameter updates from the real-time planning system of the charging path of the mobile charging vehicle for the engineering vehicle.

3. The real-time charging path planning system for a mobile charging vehicle for engineering vehicles according to claim 1 is characterized in that: The data processing module comprises: 1) Data preprocessing: receiving collected information data, removing noise data, outliers or incomplete records, and unifying the data format; 2) Charging demand assessment: Set the power threshold, and use the machine learning algorithm to train prediction and assess the urgency of charging demand based on the importance of the current task and the remaining time of the engineering vehicle, combined with historical data; 3) Optimal path calculation: Integrate real-time traffic information data into map data to calculate the optimal path from the current location of the engineering vehicle to the charging station; 4) Multi-vehicle task scheduling optimization: Use intelligent optimization algorithms to sort the charging requests of engineering vehicles by urgency to form a task queue.

4. The real-time charging path planning system for a mobile charging vehicle for engineering vehicles according to claim 3 is characterized in that: The charging demand assessment includes: The power thresholds include: 20% is the low power threshold, which requires immediate scheduling of charging tasks; 40% is the medium power threshold, which prioritizes charging tasks based on the distance and urgency of the tasks; 80% is the high power threshold, which serves as a reference point for charging completion; Task urgency assessment: Based on the importance of the task, the remaining working time, and the backup plan, the task urgency is comprehensively assessed, with scores of 1-10 for general, 11-20 for medium, and 21-30 for emergency. The final score is obtained by rounding down the sum of the three scores, as follows: Total score = (task importance assessment score + remaining working time assessment score + backup plan assessment score) / 3 Machine learning model prediction: at least receive the current power percentage, remaining task time, task importance score, and historical charging behavior data, and output a prediction result based on the above feature inputs to indicate the urgency of the charging demand, including urgent, relatively urgent, and general.

5. The real-time planning system for charging paths of mobile charging vehicles for engineering vehicles according to claim 3 is characterized in that: Calculating the optimal path includes: Get information about road conditions, including congestion levels, accident reports, and road closures; Access map data, including road networks, intersections, and charging station locations; Based on the real-time traffic conditions, the algorithm is used to search for paths, and the traffic condition function h(n) is defined as: Traffic condition function h(n) = straight-line distance (x, y) * traffic condition factor (n, g) Where: straight-line distance (x, y) is the straight-line distance from node x to target node y; The traffic factor (n, g) is a data factor based on real-time traffic conditions and is adjusted according to the real-time traffic conditions; 1) When the road section is unobstructed, the road condition factor is close to 1; 2) The more congested the road is, the road condition factor is much greater than 1; Set the starting point s and the target point g; Based on the map grid, the s coordinate is (0,0) and the g coordinate is (x,y); Get real-time traffic information: On the straight road from the starting point s to the target g, a certain section of the path is congested due to an accident, so the traffic factor is 2, and the rest of the road is in good condition, so the traffic factor is 1; Calculate the size of the traffic function h(n) of any node and obtain the value of the time cost of the node; Initialize the list of nodes to be calculated, openlist, and the list of selected nodes, closedlist; Add the starting point s to the initialized list of nodes to be calculated, openlist. The specific formula is: f(s)=g(s)+h(s) Among them, g(s) is the actual time cost from the starting point to the current node; h(s) is the estimated time cost from the current node to the target node; f(s) is the sum of the above two; Loop through the open list to select the node n with the smallest f(s), process its neighboring node n′, update g(n′) and f(n′), and if the neighboring node n′ is not in the closed list and f(n′) is smaller, update it and add it to the open list; Repeat the above steps until the target point g is found; Calculate the total cost of the complete path; Generate and output multiple routes with the shortest time under current traffic conditions.

6. The real-time planning system for charging paths of mobile charging vehicles for engineering vehicles according to claim 5 is characterized in that: The total cost of the complete path includes: Traverse each node on the path and integrate the costs between adjacent nodes; Assuming the path consists of a node sequence P = {s, n1, n2, ..., g}, the total cost C can be calculated as: Where: cost_to_move_from_n i-1 _to_n i is from node n i-1 Move to node n i cost.

7. The real-time planning system for charging paths of mobile charging vehicles for engineering vehicles according to claim 6 is characterized in that: The path planning module includes: Obtain real-time data through multiple channels, including vehicle location data, road condition data and traffic flow; Integrate and analyze historical traffic data, charging demand data, and weather data to build a predictive model; Clean the collected data, remove noise and outliers, and perform standardization; Use machine learning algorithms to learn historical traffic data and real-time traffic data to predict traffic congestion and road closure information in the future; Obtain the optimal path for the output of the data processing module; Integrate the results of road condition prediction and charging demand prediction into the path planning algorithm to correct and calculate the optimal path that meets charging needs while avoiding sections where congestion may occur; Send the planned path instructions to the mobile charging vehicle and the charging engineering vehicle to guide them to the target location for charging; Real-time detection of vehicle driving conditions and road condition changes through on-board equipment; Obtain charging task completion status and feedback, collect vehicle driving data and traffic congestion during traffic hours, and evaluate route planning results; Continuously optimize the prediction model and path planning algorithm based on feedback data.

8. The real-time charging path planning system for a mobile charging vehicle for engineering vehicles according to claim 7 is characterized in that: The establishment of the prediction model comprises: Obtain raw data from the database and perform feature extraction, including time, location, weather conditions, historical traffic flow, and historical congestion index, and generate training sets, validation sets, and test sets; According to the data characteristics, construct new features, including time period features, weather impact index, and remove irrelevant or redundant features; Based on traffic congestion prediction, set up a machine learning algorithm model, and train and test the model's performance through a training set; Adjust model parameters, improve features, or try different algorithms based on the evaluation results; Finally, the trained machine learning algorithm model is deployed in the path planning module; The new features include setting up morning and evening peak congestion, traffic congestion at irregular time periods, and seasonal climate changes.

9. A method for real-time planning of charging paths for mobile charging vehicles for engineering vehicles, using the real-time planning system for charging paths for mobile charging vehicles for engineering vehicles as described in claim 8, characterized in that: The following steps are involved: S1, data collection: obtain the location, status and environmental data of engineering vehicles and mobile charging vehicles in real time through GPS, sensors and wireless communication units; S2, data processing: pre-process the collected data, evaluate the urgency of charging demand, calculate the optimal path, and optimize the scheduling of multi-vehicle charging tasks; S3, route planning: intelligently plan the route through the prediction model, and adjust the charging route of the mobile charging vehicle in real time based on the real-time road conditions and charging demand; S4, control and dispatch: send the planned path instructions to the mobile charging vehicle and the engineering vehicle to be charged, and guide them to go to the target location for charging; S5, user interaction: providing real-time traffic conditions, charging station information, route planning results, and charging progress display and query, and receiving user feedback; S6, database management: stores and manages various types of data in the system, including engineering vehicle information, charging vehicle information, real-time road condition data, charging station information, and historical scheduling data.

10. The method for real-time planning of charging paths for mobile charging vehicles for engineering vehicles according to claim 9, characterized in that: Step S3 includes: S31, collects a large amount of raw data, including road congestion, traffic accidents, construction information, weather changes, and generates a large number of road condition training sets; S32, building a prediction model, using historical data and machine learning algorithms to build a prediction model, integrating time, weather, and holiday factors to predict changes in road conditions and charging demand distribution in the future; S33, based on the prediction model and real-time data, a path planning algorithm is used to plan the optimal path for the mobile charging vehicle; S34, monitoring the road condition changes of the driving route in real time, adjusting the driving route, and replanning the route; S35, collect actual data during the charging process, evaluate the effect of path planning, and optimize the prediction model and path planning algorithm based on user feedback and actual results.

Images