Expressway unmanned electric heavy truck intelligent charging and trunk line logistics fusion system

Abstract

The invention relates to the field of charging control, in particular to an expressway unmanned electric heavy truck intelligent charging and trunk line logistics fusion system which comprises a management platform, the input end of the management platform is connected with a logistics input, the output end of the logistics input is connected with a route recommendation, and the output end of the route recommendation is connected with a selection module. The output end of the selection module is connected with a positioning module, the output end of the positioning module is connected with an automatic driving module, and the logistics input module is used for inputting a starting point and an ending point of a logistics travel. According to the method, unmanned energy complementation is realized, the energy complementation efficiency and the operation continuity are improved, stable and reliable intelligent charging technical support is provided for operation of the unmanned electric heavy truck, high-precision prediction of the operation energy consumption of the unmanned electric heavy truck can be realized in a complex road network and a long-distance operation scene, support is provided for energy complementation scheduling and operation path optimization, and the method is suitable for popularization and application. And the safety of cargo transportation is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of charging control, in particular to a highway unmanned electric heavy truck intelligent charging and trunk line logistics fusion system. BACKGROUND

[0002] The highway unmanned electric heavy truck trunk line logistics is a new industry format that realizes intelligent transportation of goods in a closed scene of the highway relying on electric energy as power, L4 level automatic driving technology and vehicle-road cloud collaborative system. The highway unmanned electric heavy truck trunk line logistics not only reconstructs the cost and efficiency model of trunk line logistics, but also promotes the upgrading of the trunk line logistics industry to safety, green and intelligence.

[0003] However, in the process of running the highway unmanned electric heavy truck trunk line logistics, manual plugging is still required when the unmanned electric heavy truck is charged, which is low in efficiency and high in labor cost. There is a lack of automatic parking precise positioning, automatic plugging and charging and unmanned closed loop control technology that can be applied on a large scale, which restricts the continuity of unmanned operation. SUMMARY

[0004] The purpose of the present application is to solve the problems in the background art and provide a highway unmanned electric heavy truck intelligent charging and trunk line logistics fusion system.

[0005] To achieve the above purpose, the technical scheme adopted by the present application is as follows: a highway unmanned electric heavy truck intelligent charging and trunk line logistics fusion system, comprising a management platform, an input end of the management platform is connected with a logistics input, an output end of the logistics input is connected with a route recommendation, an output end of the route recommendation is connected with a selection module, an output end of the selection module is connected with a positioning module, an output end of the positioning module is connected with an automatic driving module, the logistics input is used for inputting the starting point and the ending point of the logistics trip, the route recommendation is used for recommending a plurality of transportation routes according to the input logistics trip, the selection module is used for selecting a suitable route from the recommended plurality of routes, the positioning module is used for positioning the location of the electric heavy truck, the automatic driving module is used for automatically driving the electric heavy truck for logistics transportation, an output end of the automatic driving module is respectively connected with a safety unit and a prediction unit, an output end of the prediction unit is connected with a search module, an output end of the search module is connected with a priority module, an output end of the priority module is connected with a state monitoring, an output end of the state monitoring is connected with a locking module, an output end of the locking module is connected with a guiding module, an output end of the guiding module is connected with a shooting module, an output end of the shooting module is connected with a visual control module, an output end of the visual control module is connected with a plugging module.

[0006] Preferably, the safety unit is used to protect the safety of transported goods, the prediction unit is used to predict the driving distance of the electric heavy truck, the search module is used to search for nearby charging stations and provide routes based on the predicted driving destination of the electric heavy truck, the priority module is used to interrupt the transportation route and execute the route to the charging station, and the output end of the management platform is connected to an energy control module.

[0007] Preferably, the status monitoring is used to monitor the usage status of charging piles within the charging station; the locking module is used to lock the location of unused charging piles; the guiding module is used to guide electric heavy trucks to park at unused charging piles; the shooting module is used to photograph the location of the charging port on the electric heavy truck; the vision control module is used to issue control commands based on the captured images; the plugging / unplugging module is used to plug / unplug the charging gun of the charging pile and the charging port on the electric heavy truck according to the commands; and the energy regulation module is used to regulate the power of multiple charging stations to reduce peak load on the power grid.

[0008] Preferably, the prediction unit includes a power monitoring unit. The output terminal of the power monitoring unit is connected to a power level indicator, and the output terminal of the power monitoring unit is also connected to a power level indicator. The power level indicator is connected to an emergency module. The power monitoring unit is used to monitor the battery power of the electric heavy truck. The power level indicator indicates that the battery power of the electric heavy truck is sufficient, and the power level indicator indicates that the battery power of the electric heavy truck is insufficient. The emergency module is used to provide emergency power when the battery power of the electric heavy truck is insufficient.

[0009] Preferably, the prediction unit further includes a data acquisition module, the output of which is connected to an energy consumption prediction module. The data acquisition module is used to acquire multimodal data such as road slope, traffic flow status, load fluctuation, and ambient temperature. The energy consumption prediction module is used to predict the operating energy consumption and travel distance of the electric heavy truck based on the acquired modal data.

[0010] Preferably, the safety unit includes a cooling module and a temperature detection module. The cooling module is used to cool the battery of the electric heavy truck, and the temperature detection module is used to detect the battery temperature of the electric heavy truck.

[0011] Preferably, the safety unit further includes a flame detection module and a smoke detection module. The flame detection module is used to detect whether there is a flame in the battery compartment of the electric heavy truck, and the smoke detection module is used to detect whether there is smoke in the battery compartment of the electric heavy truck.

[0012] Preferably, the output terminals of the temperature detection module, the flame detection module, and the smoke detection module are connected to a pop-up module. The output terminal of the pop-up module is connected to a cover control. The pop-up module is used to pop the battery to the ground when an abnormality is detected in the battery part of the electric heavy truck. The cover control is used to control the movement of the fireproof shell to cover the popped-up battery for isolation.

[0013] Compared with the prior art, the present invention has the following beneficial effects:

[0014] 1. The system utilizes a search module to locate nearby charging stations and provide routes based on the predicted destination of the electric heavy-duty truck. A priority module interrupts the transport route and executes a route to the charging station. Status monitoring monitors the usage status of charging piles within the charging station. A locking module locks the location of unused charging piles. A guidance module guides the electric heavy-duty truck to park at an unused charging pile. A camera module captures the location of the charging port on the electric heavy-duty truck. A vision control module issues control commands based on the captured images. A plug-in / plug-out module plugs and unplugs the charging gun of the charging pile and the charging port on the electric heavy-duty truck according to the commands. This achieves a closed-loop, unmanned charging process for the unmanned heavy-duty truck, encompassing "autonomous arrival—automatic plug-in / plug-out—intelligent charging—automatic departure," improving charging efficiency and operational continuity, and providing stable and reliable intelligent charging technology support for unmanned heavy-duty truck operation.

[0015] 2. Through the set prediction unit, the battery power of the electric heavy-duty truck is monitored using power monitoring. A qualified power level indicates sufficient battery power, while an unqualified level indicates insufficient battery power. The emergency module provides emergency power when the battery power is insufficient. The data acquisition module collects multimodal data such as road slope, traffic flow status, load fluctuations, and ambient temperature. The energy consumption prediction module predicts the operating energy consumption and travel distance of the electric heavy-duty truck based on the collected modal data. This avoids the electric heavy-duty truck from stalling due to prediction errors during emergency power supply. It also achieves high-precision prediction of the operating energy consumption of unmanned electric heavy-duty trucks in complex road networks and long-distance operation scenarios, supporting energy replenishment scheduling and operational route optimization. This enables coordinated optimization of route planning and energy replenishment scheduling, balancing minimum energy consumption, efficient energy replenishment, charging station capacity availability, and operational time window constraints, achieving optimal balance between operational efficiency and economy in complex operating environments.

[0016] 3. Through the established safety unit, a cooling module is used to cool the battery of the electric heavy-duty truck. A temperature detection module is used to detect the battery temperature of the electric heavy-duty truck, a flame detection module is used to detect whether there is a flame in the battery area of ​​the electric heavy-duty truck, a smoke detection module is used to detect whether there is smoke in the battery area of ​​the electric heavy-duty truck, an ejection module is used to eject the battery to the ground when an abnormality is detected in the battery area of ​​the electric heavy-duty truck, and a cover control is used to control the movement of the fireproof cover to cover the ejected battery for isolation. In this way, the battery is promptly removed from the electric heavy-duty truck when it is burning, and the fireproof cover isolates it to prevent the flame from spreading to the cargo on the vehicle, thereby improving the safety of cargo transportation. Attached Figure Description

[0017] Fig. 1 This is a schematic diagram of a smart charging and trunk logistics integration system for unmanned electric heavy-duty trucks on highways, according to the present invention.

[0018] Fig. 2 This is a schematic diagram of the predictive unit of the intelligent charging and trunk logistics integration system for unmanned electric heavy trucks on highways, as described in this invention.

[0019] Fig. 3 This is a schematic diagram of the safety unit of a smart charging and trunk logistics integration system for unmanned electric heavy-duty trucks on highways, according to the present invention. Detailed Implementation

[0020] The following description is intended to disclose the invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art.

[0021] like Figs. 1-3The system, illustrating an intelligent charging and trunk logistics integration system for unmanned electric heavy-duty trucks on highways, includes a management platform. The platform's input is connected to a logistics input module, and its output is connected to a route recommendation module. The route recommendation module's output is connected to a selection module, and its output is connected to a positioning module. The positioning module's output is connected to an autonomous driving module. The logistics input module is used to input the start and end points of the logistics journey. The route recommendation module recommends multiple transportation routes based on the input logistics journey. The selection module selects a suitable route from the recommended routes. The positioning module locates the electric heavy-duty truck's position. The autonomous driving module autonomously drives the electric heavy-duty truck for logistics transportation. The autonomous driving module's output is connected to a safety unit and a prediction unit. The prediction unit's output is connected to a search module, and its output is connected to a priority module. The priority module's output is connected to a status monitoring module, and its output is connected to a locking module. The locking module's output is connected to a guidance module, and its output is connected to a camera module. The camera module's output is connected to a vision control module, and its output is connected to a plug-in module.

[0022] The safety unit is used to protect the safety of transported goods, the prediction unit is used to predict the driving distance of the electric heavy truck, the search module is used to search for nearby charging stations and provide routes based on the predicted driving destination of the electric heavy truck, the priority module is used to interrupt the transportation route and execute the route to the charging station, and the output end of the management platform is connected to the energy control module.

[0023] The status monitoring module is used to monitor the usage status of charging piles within the charging station. The locking module is used to lock the location of unused charging piles. The guidance module is used to guide electric heavy trucks to park at unused charging piles. The imaging module is used to photograph the location of the charging port on the electric heavy truck. The vision control module is used to issue control commands based on the captured images. The plug-in / plug-out module is used to plug and unplug the charging gun of the charging pile and the charging port on the electric heavy truck according to the commands. The energy regulation module is used to regulate the power of multiple charging stations to reduce the peak load on the power grid. The energy regulation module can perform regulation based on the multi-source collaborative flexible load scheduling and green electricity priority scheduling algorithm of the station group.

[0024] The algorithm steps for the above-mentioned multi-source collaborative flexible load scheduling and green energy priority scheduling of the substation cluster are as follows:

[0025] Step 1: Multi-source data acquisition and preprocessing (algorithm input layer)

[0026] The prerequisite for algorithm execution is to obtain "full-dimensional, high-quality data". Data collection and cleaning must be completed first to avoid invalid data affecting the calculation results.

[0027] Data collection range

[0028] The algorithm needs to simultaneously access three types of core data, and the data update frequency is dynamically adjusted according to the scenario (second-level updates in emergency scenarios, minute-level updates in regular scenarios):

[0029] Grid-side data: real-time electricity price (peak / flat / valley), grid load limit (e.g., maximum allowable load of 200kW within the station), demand response signal (peak shaving / valley filling level), grid voltage / frequency (to determine grid stability);

[0030] Data within the station: charging pile status (idle / charging / faulty), real-time power of a single pile (e.g., 50kW), energy storage system data (remaining SOC, charging and discharging power limits), distributed photovoltaic output (if any, e.g., 30kW), and auxiliary loads within the station (e.g., lighting, air conditioning, approximately 10kW).

[0031] User-side data: charging reservation information (user ID, reservation time period, expected charging amount / duration), vehicle data (battery capacity, current SOC, charging power limit), user priority (regular user / VIP / emergency vehicle).

[0032] Data preprocessing

[0033] The collected raw data is cleaned to resolve issues such as missing data, outliers, and inconsistent formats.

[0034] Missing value handling: If the power data of a charging pile is missing, its average power over the previous 5 minutes will be used as a substitute;

[0035] Outlier removal: If the grid voltage data suddenly drops to 0 at a certain moment (obvious anomaly), remove the data and use the normal data from the previous second;

[0036] Data standardization: unify the format of data with different units (e.g., convert "battery capacity kWh" and "charging power kW" into "values ​​in 1kW") to facilitate subsequent calculations.

[0037] Step 2: Load forecasting calculation (algorithm forecasting layer)

[0038] Based on the preprocessed data, the total load within the station is estimated over a future period (usually 15 minutes to 24 hours) using a prediction algorithm, providing a "forward-looking basis" for scheduling strategies and avoiding poor user experience or grid violations caused by "passive response".

[0039] Core prediction model

[0040] Commonly used models are selected based on the scenario; when the accuracy of a single model is insufficient, "multi-model fusion" is employed.

[0041] Short-term forecasting (15 minutes to 2 hours): LSTM (Long Short-Term Memory) or GRU (Gated Recurrent Unit) are preferred, as they are good at capturing the "short-term fluctuation patterns" of the load (such as real-time changes in user charging behavior).

[0042] For medium- to long-term forecasts (2-24 hours): XGBoost (gradient boosting tree) or LightGBM are preferred. The accuracy can be improved by combining historical data (such as the load of the same period in the past 7 days) and external factors (weather, holidays, and customer traffic in surrounding shopping malls).

[0043] Prediction results output

[0044] Output the "future load curve" and "confidence interval", for example: "The total load in the station is predicted to be 180-190kW in the next hour (18:00-19:00), with the peak occurring around 18:30 (190kW). Peak shaving strategies need to be prepared in advance."

[0045] Step 3: Define scheduling objectives and constraints (algorithm decision layer)

[0046] Clearly define "what goals the algorithm should achieve" and "what limitations it cannot overcome" to avoid conflicts between scheduling strategies and actual needs (such as emergency vehicles being unable to charge due to peak shaving).

[0047] Core scheduling objectives (priority ranking)

[0048] The algorithm needs to dynamically adjust the target priority based on the triggering conditions. Common targets include:

[0049] Power grid safety priority: Ensure that the total load within the station does not exceed the power grid limit and that the voltage / frequency meets the standards (highest priority, such as in case of emergency load limiting by the power grid);

[0050] Cost optimization is the next priority: try to charge more during off-peak hours (to reduce electricity costs) and use less electricity during peak hours (to avoid high electricity prices). If there is energy storage, optimize the timing of charging and discharging (charging during off-peak hours and discharging during peak hours).

[0051] User experience guarantee: Meet users' expected charging time / capacity, reduce the number of power adjustments, and prioritize high-priority users (such as emergency users and VIPs).

[0052] Constraints (unbreakable restrictions)

[0053] The algorithm needs to find the optimal solution within constraints, common constraints include:

[0054] Equipment constraints: The power of the charging pile shall not exceed its hardware limit (e.g., the maximum output of a certain pile is 120kW), and the energy storage charging and discharging power shall not exceed the rated value (e.g., 50kW).

[0055] User constraint: The user's expected charging time is greater than or equal to the actual charging time (e.g., if the user plans to charge in 2 hours, the algorithm must ensure that the charging time is not less than 1.8 hours).

[0056] Safety constraints: Avoid frequent start-stop of charging piles (affecting equipment lifespan); ensure that the energy storage SOC is not lower than 20% (to prevent over-discharge from damaging the battery).

[0057] Step 4: Calculate the optimal scheduling strategy (core layer of the algorithm)

[0058] The "optimization algorithm" finds the optimal solution between the "objective" and the "constraints" to generate the "equipment control scheme" (such as how much power a certain charging pile should be adjusted to, and whether the energy storage should be discharged).

[0059] Commonly used optimization algorithms

[0060] Choose an algorithm based on the problem complexity. Common types include:

[0061] Linear programming (LP): Suitable for simple scenarios (such as only needing to allocate charging pile power, where the objective function and constraints are linear), and has a fast calculation speed (results are available in seconds);

[0062] Mixed Integer Programming (MIP): Suitable for scenarios involving "discrete decisions" (such as whether to start energy storage or whether to connect photovoltaics), and can handle "0-1 variables" (such as energy storage start = 1, not start = 0).

[0063] Particle Swarm Optimization (PSO) or Genetic Algorithm (GA): Suitable for complex nonlinear scenarios (such as the nonlinear relationship between charging pile power and charging time), it can find the global optimal solution under multiple constraints.

[0064] Strategy calculation example (power grid peak shaving scenario)

[0065] Hypothetical scenario: The power grid requires the total load in the station to be ≤170kW from 18:00 to 19:00. The current load in the station is 190kW (10 charging piles, 20kW each, no energy storage). User priority: 2 emergency vehicles (high), 5 VIP vehicles (medium), 3 ordinary vehicles (low).

[0066] Algorithm calculation logic:

[0067] Prioritize high-priority vehicles: keep the 20kW power of the two emergency vehicles unchanged (total 40kW).

[0068] Further optimization with medium priority: reduce the power of 5 VIP vehicles to 18kW (2kW reduction per vehicle, total 90kW);

[0069] Finally, the low priority was adjusted: the power of the three regular vehicles was reduced to 13.3kW (6.7kW per vehicle, for a total of 40kW).

[0070] Total load: 40+90+40=170kW, which meets grid constraints while minimizing the impact on high-priority users.

[0071] Step 5: Policy Execution (Algorithm Output Layer)

[0072] Command issuance and confirmation

[0073] The algorithm sends instructions to the equipment through the charging station's EMS (Energy Management System) and simultaneously activates a "timeout retry mechanism" (if no confirmation is received from the equipment within 3 seconds after the instruction is sent, it will be resent).

[0074] After the device executes the command, it returns the "execution result" to the EMS (such as "Charging pile 1 power has been adjusted to 18kW, current status is normal"). After the algorithm confirms that the command has been implemented, it enters the "real-time monitoring stage".

[0075] Step 6: Real-time monitoring and dynamic adjustment (algorithm feedback layer)

[0076] The algorithm needs to continuously monitor the execution effect. If there is a "deviation between actual state and expectation" (such as load not meeting the standard or equipment failure), a secondary calculation should be triggered immediately to adjust the strategy and avoid scheduling failure.

[0077] Deviation monitoring indicators

[0078] The algorithm compares the "expected value" with the "actual value" in real time, and the core monitoring indicators include:

[0079] Load deviation: The difference between the actual total load in the station and the target load (e.g., target 170kW, actual 175kW, deviation 5kW).

[0080] Equipment status deviation: The difference between the actual power of the charging pile and the commanded power (e.g., commanded 18kW, actual 15kW, deviation 3kW).

[0081] User experience deviation: The difference between the user's actual charging time and the expected charging time (e.g., expected 2 hours, but only 75% charged after 1.5 hours, which is a large deviation).

[0082] Dynamic adjustment logic

[0083] If the deviation exceeds the threshold (e.g., load deviation > 5%, equipment deviation > 10%), the algorithm immediately initiates "secondary optimization":

[0084] Example 1: Load deviation (actual 175kW > target 170kW): The algorithm detects that the power of a VIP vehicle has not been reduced to 18kW as instructed (it is still 20kW), and immediately issues a new instruction to reduce its power to 13kW, while notifying the user that "due to temporary equipment adjustment, the power has been temporarily reduced and is expected to be restored in 10 minutes";

[0085] Example 2: Equipment failure (power outage of one regular vehicle charging station): The algorithm distributes the load demand of the charging station (originally 13.3kW) to the other two regular vehicles (each power increases from 13.3kW to 19.95kW), ensuring that the total load remains at 170kW, while triggering a fault alarm to notify the maintenance personnel.

[0086] The prediction unit includes a power monitoring unit. The output of the power monitoring unit is connected to a power level indicator and a power level indicator. The output of the power monitoring unit is also connected to an emergency module. The power monitoring unit is used to monitor the battery level of the electric heavy truck. A power level indicator indicates that the battery level of the electric heavy truck is sufficient, and a power level indicator indicates that the battery level of the electric heavy truck is insufficient. The emergency module is used to provide emergency power when the battery level of the electric heavy truck is insufficient.

[0087] The prediction unit also includes a data acquisition module. The output of the data acquisition module is connected to an energy consumption prediction module. The data acquisition module is used to collect multimodal data such as road slope, traffic flow status, load fluctuation, and ambient temperature. The energy consumption prediction module is used to predict the operating energy consumption and driving distance of the electric heavy truck based on the collected modal data.

[0088] The safety unit includes a cooling module and a temperature detection module. The cooling module is used to cool down the battery of the electric heavy truck, and the temperature detection module is used to detect the battery temperature of the electric heavy truck.

[0089] The safety unit also includes a flame detection module and a smoke detection module. The flame detection module is used to detect whether there is a flame in the battery compartment of the electric heavy truck, and the smoke detection module is used to detect whether there is smoke in the battery compartment of the electric heavy truck.

[0090] The output terminals of the temperature detection module, the flame detection module, and the smoke detection module are connected to a pop-up module. The output terminal of the pop-up module is connected to a cover control. The pop-up module is used to pop the battery to the ground when an abnormality is detected in the battery part of the electric heavy truck. The cover control is used to control the movement of the fireproof cover to cover the popped-up battery for isolation.

[0091] In summary, the system utilizes a search module to locate nearby charging stations and provide routes based on the predicted destination of the electric heavy-duty truck. A priority module interrupts the transport route and executes the route to the charging station. Status monitoring monitors the usage status of charging piles within the charging station. A locking module locks the location of unused charging piles. A guidance module guides the electric heavy-duty truck to park at an unused charging pile. A camera module captures images of the charging port location on the electric heavy-duty truck. A vision control module issues control commands based on the captured images. A plug-in / plug-out module, based on these commands, plugs / unplugs the charging gun of the charging pile and the charging port on the electric heavy-duty truck. This achieves a closed-loop, unmanned charging process for unmanned heavy-duty trucks, encompassing "autonomous positioning—automatic plugging and unplugging—intelligent charging—automatic departure," improving charging efficiency and operational continuity, and providing stable and reliable intelligent charging technology support for unmanned heavy-duty truck operation. A predictive unit monitors the battery level of the electric heavy-duty truck; a passing level indicates sufficient battery power, while an failing level indicates insufficient battery power. An emergency module provides power when the battery is low, and a data acquisition module collects multimodal data such as road slope, traffic flow, load fluctuations, and ambient temperature. The energy consumption prediction module predicts the operating energy consumption and travel distance of electric heavy-duty trucks based on collected modal data. This prevents trucks from stalling due to prediction errors during emergency power supply and enables high-precision prediction of energy consumption for unmanned electric heavy-duty trucks in complex road networks and long-distance operation scenarios. It supports energy replenishment scheduling and operational route optimization, achieving coordinated optimization of route planning and energy replenishment scheduling while balancing minimum energy consumption, high energy replenishment efficiency, charging station capacity availability, and operational time window constraints. This results in a unified optimal balance of operational efficiency and economy in complex operating environments. Through the established safety unit, it utilizes reduced... The temperature module cools the battery of the electric heavy-duty truck. The temperature detection module detects the battery temperature. The flame detection module detects whether there is a flame in the battery area. The smoke detection module detects whether there is smoke in the battery area. The ejection module ejects the battery to the ground when an abnormality is detected in the battery area. The cover control controls the movement of the fireproof cover to cover the ejected battery for isolation. This allows the battery to be removed from the electric heavy-duty truck in time when it is burning, and the fireproof cover isolates it to prevent the flame from spreading to the cargo on the vehicle, thereby improving the safety of cargo transportation.

[0092] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention. The scope of protection claimed by the appended claims and their equivalents is defined.

Claims

1. A smart charging and trunk logistics integration system for unmanned electric heavy-duty trucks on highways, comprising a management platform, characterized in that: The management platform has an input terminal connected to a logistics entry point, an output terminal connected to a route recommendation point, an output terminal connected to a selection module, an output terminal connected to a positioning module, and an output terminal connected to an autonomous driving module. The logistics entry point is used to input the start and end points of the logistics journey. The route recommendation point is used to recommend multiple transportation routes based on the entered logistics journey. The selection module is used to select a suitable route from the recommended routes. The positioning module is used to locate the position of the electric heavy-duty truck. The autonomous driving module is used to autonomously drive the electric heavy-duty truck for logistics transportation. The output terminals of the autonomous driving module are connected to a safety unit and a prediction unit. The output terminal of the prediction unit is connected to a search module. The output terminal of the search module is connected to a priority module. The output terminal of the priority module is connected to a status monitoring module. The output terminal of the status monitoring module is connected to a locking module. The output terminal of the locking module is connected to a guidance module. The output terminal of the guidance module is connected to a shooting module. The output terminal of the shooting module is connected to a vision control module. The output terminal of the vision control module is connected to a plug-in module.

2. The intelligent charging and trunk logistics integration system for unmanned electric heavy-duty trucks on highways according to claim 1, characterized in that: The safety unit is used to protect the safety of transported goods, the prediction unit is used to predict the driving distance of the electric heavy truck, the search module is used to search for nearby charging stations and provide routes based on the predicted driving destination of the electric heavy truck, the priority module is used to interrupt the transportation route and execute the route to the charging station, and the output end of the management platform is connected to the energy control module.

3. The intelligent charging and trunk logistics integration system for unmanned electric heavy-duty trucks on highways according to claim 2, characterized in that: The status monitoring module is used to monitor the usage status of charging piles within the charging station. The locking module is used to lock the location of unused charging piles. The guiding module is used to guide electric heavy trucks to park at unused charging piles. The shooting module is used to photograph the location of the charging port on the electric heavy truck. The vision control module is used to issue control commands based on the captured images. The plugging / unplugging module is used to plug / unplug the charging gun of the charging pile and the charging port on the electric heavy truck according to the commands. The energy regulation module is used to regulate the power of multiple charging stations to reduce the peak load on the power grid.

4. The intelligent charging and trunk logistics integration system for unmanned electric heavy-duty trucks on highways according to claim 1, characterized in that: The prediction unit includes a power monitoring unit. The output terminal of the power monitoring unit is connected to a power level indicator, and the output terminal of the power monitoring unit is also connected to a power level indicator. The power level indicator is connected to an emergency module. The power monitoring unit is used to monitor the battery power of the electric heavy truck. The power level indicator indicates that the battery power of the electric heavy truck is sufficient, and the power level indicator indicates that the battery power of the electric heavy truck is insufficient. The emergency module is used to provide emergency power when the battery power of the electric heavy truck is insufficient.

5. The intelligent charging and trunk logistics integration system for unmanned electric heavy-duty trucks on highways according to claim 4, characterized in that: The prediction unit also includes a data acquisition module. The output of the data acquisition module is connected to an energy consumption prediction module. The data acquisition module is used to collect multimodal data such as road slope, traffic flow status, load fluctuation, and ambient temperature. The energy consumption prediction module is used to predict the operating energy consumption and driving distance of the electric heavy truck based on the collected modal data.

6. The intelligent charging and trunk logistics integration system for unmanned electric heavy-duty trucks on highways according to claim 1, characterized in that: The safety unit includes a cooling module and a temperature detection module. The cooling module is used to cool the battery of the electric heavy truck, and the temperature detection module is used to detect the battery temperature of the electric heavy truck.

7. The intelligent charging and trunk logistics integration system for unmanned electric heavy-duty trucks on highways according to claim 6, characterized in that: The safety unit also includes a flame detection module and a smoke detection module. The flame detection module is used to detect whether there is a flame in the battery compartment of the electric heavy truck, and the smoke detection module is used to detect whether there is smoke in the battery compartment of the electric heavy truck.

8. The intelligent charging and trunk logistics integration system for unmanned electric heavy-duty trucks on highways according to claim 7, characterized in that: The output terminals of the temperature detection module, the flame detection module, and the smoke detection module are connected to a pop-up module. The output terminal of the pop-up module is connected to a cover control. The pop-up module is used to pop the battery to the ground when an abnormality is detected in the battery part of the electric heavy truck. The cover control is used to control the movement of the fireproof shell to cover the popped-up battery for isolation.

Images