New energy vehicle energy adaptive scheduling method and system based on environment perception

Abstract

The invention relates to the technical field of artificial intelligence, and discloses a new energy vehicle energy adaptive scheduling method and system based on environmental perception. Comprising the following steps: acquiring environmental data of a vehicle in a current driving environment in real time by using a meteorological sensor, a road slope sensor and a traffic flow sensor which are mounted on the new energy vehicle; generating a corresponding future environment change trend of the new energy vehicle on the driving path according to the environment data and the historical environment data; according to the environment data and the environment change trend, generating a vehicle energy management strategy adjustment instruction; and completing adaptive scheduling of the new energy vehicle according to the vehicle energy management strategy adjustment instruction. Through multi-source data fusion, machine learning prediction and scenarized strategy generation, a more intelligent and adaptive energy scheduling system is constructed, the problems of insufficient environmental adaptability and strategy lagging in the prior art are solved, and the method has significant technical progress and practical application value.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a method and system for adaptive energy scheduling of new energy vehicles based on environmental perception. Background Art

[0002] With the increasing prevalence of new energy vehicles, efficiently managing vehicle energy to improve driving range has become a key technical challenge. Traditional energy management strategies for new energy vehicles are typically based on fixed energy consumption models or simple real-time data feedback. For example, they adjust power output based solely on remaining battery power, ignoring the dynamic impact of complex environmental factors (such as weather conditions, road grade, and traffic flow) on energy consumption. While some existing solutions involve collecting environmental data, these approaches focus solely on a single dimension (e.g., considering only traffic congestion or weather impacts). They lack the integration and processing of multi-source environmental data (weather, grade, and traffic) and the ability to predict future trends. This results in an inability for energy scheduling strategies to adapt to both real-time and predicted environmental changes. For example, in the event of unexpected severe weather or long downhill sections, traditional systems are unable to proactively optimize energy consumption allocation or maximize energy recovery efficiency. Furthermore, charging scheduling struggles to dynamically select the optimal charging time and location based on real-time environmental conditions and range predictions, leading to inefficient energy utilization and long charging wait times.

[0003] Therefore, a method and system are urgently needed to solve at least one of the above problems. Summary of the Invention

[0004] This application provides a method and system for adaptive energy scheduling of new energy vehicles based on environmental perception. It uses multiple sensors to collect multi-dimensional environmental data in real time, combines historical data with machine learning to predict future environmental change trends, and dynamically generates energy management strategies and charging plans based on this, thereby achieving coordinated optimization of vehicle energy distribution and charging behavior.

[0005] In a first aspect, the present application provides a method for adaptive energy scheduling of new energy vehicles based on environmental perception, comprising:

[0006] Using weather sensors, road slope sensors, and traffic flow sensors installed on new energy vehicles to collect real-time environmental data from the vehicle's current driving environment, the environmental data includes at least weather conditions, road slope information, and traffic flow data;

[0007] The environmental data and historical environmental data are used to generate a future environmental change trend corresponding to the driving path of the new energy vehicle, wherein the future environmental change trend includes changes in weather conditions, road slope, and traffic flow;

[0008] generating vehicle energy management strategy adjustment instructions based on the environmental data and the environmental change trend, the vehicle energy management strategy adjustment instructions at least including: generating control instructions for reducing energy consumption of new energy vehicles in adverse weather conditions or congested traffic scenarios; generating optimization control instructions for energy recovery systems in long downhill road gradient scenarios;

[0009] Adaptive scheduling of the new energy vehicle is completed according to the vehicle energy management strategy adjustment instruction.

[0010] In some embodiments, in completing the adaptive scheduling of the new energy vehicle according to the vehicle energy management strategy adjustment instruction, the method also includes: generating a vehicle charging plan according to the current remaining power corresponding to the new energy vehicle, the environmental data and the predicted environmental change trend, the vehicle charging plan including the optimal charging time and the recommended charging location; and adaptively scheduling the energy distribution and charging behavior of the new energy vehicle according to the vehicle energy management strategy adjustment instruction and the vehicle charging plan to improve the energy utilization efficiency and endurance of the new energy vehicle.

[0011] In some embodiments, the vehicle charging plan is generated according to the current remaining power corresponding to the new energy vehicle, the environmental data and the predicted environmental change trend, including: constructing a vehicle endurance assessment model based on the current remaining power, weather conditions, road slope, traffic flow data and predicted environmental change trends; combining the endurance assessment model, matching a preset charging facility location database, the charging facility location database at least including charging pile distribution coordinates, available power, real-time electricity prices and queue status; according to the endurance assessment results and the charging facility matching results, with the goal of minimizing charging waiting time and maximizing energy utilization efficiency, determining the best charging time and recommended charging location through an optimization algorithm.

[0012] In some embodiments, the vehicle's energy distribution and charging behavior are adaptively scheduled based on the vehicle energy management strategy adjustment instructions and the vehicle charging plan, including: before detecting that a new energy vehicle enters a congested road section or a severe weather area, the control instructions for reducing energy consumption are executed first, and the motor output power, air-conditioning system power consumption and vehicle-mounted equipment power usage strategy are dynamically adjusted; when the new energy vehicle travels on a long downhill section, the recovery intensity of the energy recovery system is dynamically adjusted according to the real-time slope data, and the remaining power prediction result is synchronously updated; if the predicted remaining power is lower than the preset threshold and is close to the recommended charging location, a charging reminder is triggered and the route to the charging pile is automatically planned to achieve coordinated optimization of energy distribution and charging behavior.

[0013] In some embodiments, the environmental data and historical environmental data are used to generate the future environmental change trend corresponding to the driving path of the new energy vehicle, including: obtaining historical environmental data stored in the cloud through an on-board communication module, the historical environmental data including historical meteorological data, road slope data, traffic flow data and corresponding time-space coordinates; using a long short-term memory network or a random forest algorithm to build an environmental prediction model, inputting the real-time collected environmental data and historical environmental data into the prediction model, and outputting the probability of meteorological condition changes on the driving path in the next 1-5 hours, the road slope distribution curve and the traffic flow congestion index prediction value as the future environmental change trend; wherein, when the prediction model is trained by historical data, time series features and geographic information features are introduced for joint modeling.

[0014] In some embodiments, the vehicle energy management strategy adjustment instructions are generated based on the environmental data and the environmental change trend, including: when the real-time meteorological data or the predicted meteorological data meets the severe weather judgment conditions, or the predicted traffic flow congestion index is ≥ a preset threshold, a motor torque limitation instruction, a battery heating or cooling system power adjustment instruction and a non-essential equipment power limitation instruction are generated to reduce vehicle energy consumption; when the real-time road slope data or the predicted slope data shows that the length of the continuous downhill section is ≥500 meters and the slope is ≥5°, an energy recovery system pre-start instruction is generated, and the recovery current threshold is adjusted in real time according to the slope change.

[0015] In some embodiments, the meteorological sensors, road slope sensors and traffic flow sensors installed on the new energy vehicles are used to collect environmental data in the vehicle's current driving environment in real time, including: sensing traffic flow data through the fusion of millimeter-wave radar and camera, identifying vehicle density and driving speed within 500 meters ahead; obtaining real-time road slope and curvature information through an inertial measurement unit combined with high-precision map data; collecting real-time temperature, humidity, light intensity and rainfall data through a meteorological sensor array, and performing time synchronization and outlier calibration on multi-sensor data to form structured data containing timestamps, geographic locations and environmental parameters as the environmental data.

[0016] In a second aspect, the present application provides an adaptive energy scheduling system for new energy vehicles based on environmental perception, comprising:

[0017] A data acquisition unit, configured to utilize meteorological sensors, road slope sensors, and traffic flow sensors installed on new energy vehicles to collect environmental data in real time under the vehicle's current driving environment, wherein the environmental data includes at least meteorological conditions, road slope information, and traffic flow data;

[0018] a trend generation unit, configured to generate a future environmental change trend corresponding to the driving path of the new energy vehicle based on the environmental data and historical environmental data, wherein the future environmental change trend includes changes in meteorological conditions, road slope, and traffic flow;

[0019] an instruction generation unit, configured to generate vehicle energy management strategy adjustment instructions based on the environmental data and the environmental change trend, the vehicle energy management strategy adjustment instructions at least including: generating control instructions for reducing energy consumption of new energy vehicles in adverse weather conditions or congested traffic scenarios; and generating optimization control instructions for an energy recovery system in long downhill road gradient scenarios;

[0020] A scheduling completion unit is used to complete the adaptive scheduling of the new energy vehicle according to the vehicle energy management strategy adjustment instruction.

[0021] In a third aspect, the present application provides a control module, which includes a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and implement the method provided in any embodiment of the present application when executing the computer program.

[0022] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program. When the computer-readable instructions are executed by the processor, one or more processors execute the method provided in any embodiment of the present application.

[0023] The present invention relates to the field of artificial intelligence technology, and specifically provides a method and system for adaptive energy scheduling of new energy vehicles based on environmental perception. The present invention proposes a method for adaptive energy scheduling of new energy vehicles based on environmental perception, which collects multi-dimensional environmental data in real time through multiple sensors, combines historical data with machine learning to predict future environmental change trends, and dynamically generates energy management strategies and charging plans based on this, thereby achieving coordinated optimization of vehicle energy distribution and charging behavior.

[0024] By utilizing meteorological sensors, road slope sensors, and traffic flow sensors (such as millimeter-wave radars, cameras, and inertial measurement units), the system acquires real-time data on the current driving environment, including meteorological conditions (temperature, rainfall, snow depth, etc.), road slope information (real-time slope, continuous downhill length, etc.), and traffic flow data (vehicle density, congestion index, etc.). It also performs time synchronization and outlier correction on multi-source data.

[0025] Combining real-time environmental data with historical cloud-based environmental data (including time-space coordinates), machine learning models such as long short-term memory (LSTM) networks or random forests predict the probability of changing weather conditions (e.g., rainfall probability), road slope distribution, and traffic congestion index along the route within the next 1-5 hours, providing forward-looking guidance for strategic adjustments. Based on real-time and predicted environmental data, differentiated control commands are generated for different scenarios. For example, in severe weather (rainfall ≥ 5 mm / h) or high congestion index (≥ a preset threshold), energy-saving commands such as motor torque limit and power restriction for non-essential equipment are generated. For long downhill sections (≥ 500 meters in length and ≥ 5° in slope), energy recovery system optimization commands are generated, dynamically adjusting the recovery intensity to improve efficiency (e.g., by 15%-25%). Based on these strategic commands, vehicle power output, energy consumption distribution, and energy recovery are coordinated and optimized, combined with charging plans (optimal charging time and recommended locations) to achieve comprehensive optimization of energy utilization and range.

[0026] By integrating real-time data collection of weather, slope, and traffic flow with future trend forecasts, the system breaks through the limitations of traditional single data dimensions, making energy scheduling strategies more tailored to actual driving scenarios and enhancing their foresight. Differentiated adjustments are made to energy consumption allocation and energy recovery strategies for different scenarios, such as inclement weather, congestion, and long downhill slopes. For example, non-essential power consumption is reduced in congestion and energy recovery is maximized on downhill slopes, directly improving energy efficiency. By combining remaining power, environmental forecasts, and the real-time status of charging facilities (distribution, power, and queue status), charging times and locations are optimized with the goals of minimizing wait times and maximizing efficiency, reducing user anxiety about charging and improving charging resource utilization. Through a closed-loop control system of "real-time perception - predictive analysis - strategy adjustment - execution feedback," refined energy management is achieved, effectively extending vehicle range compared to traditional methods, with significant advantages particularly in complex environments.

[0027] This application builds a more intelligent and adaptive energy scheduling system through multi-source data fusion, machine learning prediction and scenario-based strategy generation, solving the problems of insufficient environmental adaptability and lagging strategies in existing technologies, and has significant technological progress and practical application value.

[0028] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0030] Figure 1 This is a schematic flow chart of the steps of a method for adaptive energy scheduling of new energy vehicles based on environmental perception provided by an embodiment of the present application;

[0031] Figure 2 This is a schematic block diagram of the structure of an adaptive energy scheduling system for new energy vehicles based on environmental perception provided by an embodiment of the present application;

[0032] Figure 3 This is a schematic block diagram of the structure of a control module provided in one embodiment of the present application.

[0033] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0035] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined, or partially merged, so the actual execution order may vary depending on the actual situation.

[0036] It should be understood that, in order to clearly describe the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, terms such as "first" and "second" are used to distinguish between identical or similar items having substantially the same functions and effects. Those skilled in the art will understand that terms such as "first" and "second" do not limit the quantity or order of execution, and that terms such as "first" and "second" do not necessarily define differences.

[0037] It should be understood that the terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0038] It will also be understood that the term "and / or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0039] The following describes some embodiments of the present application in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features therein may be combined with each other.

[0040] With the increasing prevalence of new energy vehicles, efficiently managing vehicle energy to improve driving range has become a key technical challenge. Traditional energy management strategies for new energy vehicles are typically based on fixed energy consumption models or simple real-time data feedback. For example, they adjust power output based solely on remaining battery power, ignoring the dynamic impact of complex environmental factors (such as weather conditions, road grade, and traffic flow) on energy consumption. While some existing solutions involve collecting environmental data, these approaches focus solely on a single dimension (e.g., considering only traffic congestion or weather impacts). They lack the integration and processing of multi-source environmental data (weather, grade, and traffic) and the ability to predict future trends. This results in an inability for energy scheduling strategies to adapt to both real-time and predicted environmental changes. For example, in the event of unexpected severe weather or long downhill sections, traditional systems are unable to proactively optimize energy consumption allocation or maximize energy recovery efficiency. Furthermore, charging scheduling struggles to dynamically select the optimal charging time and location based on real-time environmental conditions and range predictions, leading to inefficient energy utilization and long charging wait times.

[0041] Therefore, a method and system are urgently needed to solve at least one of the above problems.

[0042] To solve the above problems, please refer to Figure 1 , Figure 1 This is a schematic flow chart of a method for adaptive energy scheduling of new energy vehicles based on environmental perception provided by an embodiment of the present application. The execution device of the method is the control module provided by any embodiment of the present application.

[0043] like Figure 1 As shown, the provided method includes steps S101 to S103. The control module can be a handheld terminal, a laptop computer, a wearable device, or a robot, etc., for implementing steps S101 to S104 and their corresponding embodiments.

[0044] Step S101 . Utilize meteorological sensors, road slope sensors, and traffic flow sensors installed on new energy vehicles to collect real-time environmental data of the vehicle's current driving environment. The environmental data includes at least meteorological conditions, road slope information, and traffic flow data.

[0045] Specifically, by utilizing multiple types of sensors onboard new energy vehicles, three core environmental data types, namely meteorological conditions, road slope information, and traffic flow data, are collected in real time to form a multi-dimensional environmental perception system. Specifically, it includes:

[0046] Meteorological conditions: temperature, humidity, wind speed, precipitation (such as rain / snow intensity), light intensity, etc., used to evaluate the impact of weather on energy consumption (such as low temperature leading to decreased battery activity and rainy days increasing driving resistance).

[0047] Road slope information: Obtain real-time slope information through inclination sensors or in combination with high-precision maps (such as ADAS maps), distinguish uphill, downhill, and slope gradients, and is used to optimize power output and energy recovery strategies.

[0048] Traffic flow data: Use vehicle-mounted cameras + image recognition technology (to detect the distance to the vehicle ahead and lane congestion), radar sensors (to detect vehicle density), or access real-time traffic data via the Internet (such as navigation platform APIs) to determine the level of congestion (e.g., smooth, slow, or congested).

[0049] Sensor hardware deployment can include weather sensors integrated into the exterior of the vehicle (e.g., the windshield or roof) to avoid obstruction. A slope sensor (inclinometer) is installed in the center of the vehicle chassis and integrated with an inertial navigation system (INS) to improve slope detection accuracy. Traffic flow detection integrates onboard sensing (camera + millimeter-wave radar) with cloud data (e.g., Baidu Maps and AutoNavi Maps real-time traffic API), ensuring accuracy through data verification mechanisms (e.g., eliminating outliers). Data collection is ensured to be real-time by setting a high-frequency sampling period (e.g., 100ms). Edge computing modules (e.g., onboard ECUs) are used to preprocess raw data (e.g., filtering and denoising) to reduce transmission latency.

[0050] This technology breaks through the limitations of traditional single-source data (e.g., battery charge alone) and comprehensively captures external factors that influence energy consumption, providing real-time, accurate input data for subsequent strategy optimization. High-frequency data collection and edge preprocessing ensure that environmental data is synchronized with vehicle status, preventing strategy failures caused by data lag (e.g., inability to adjust power output in a timely manner during a sudden downpour).

[0051] Step S102: The environmental data and historical environmental data are used to generate a future environmental change trend corresponding to the driving path of the new energy vehicle. The future environmental change trend includes changes in weather conditions, road slopes, and traffic flow.

[0052] Specifically, based on real-time and historical environmental data, data fusion and prediction models are used to generate trends in weather conditions, road slope, and traffic flow along the vehicle's travel path. This involves spatially and temporally matching real-time environmental data with historical databases (e.g., weather patterns in the same region and time period, historical traffic flow distribution, and geographic information on road slopes) to construct a multidimensional feature vector (e.g., timestamp, longitude and latitude, weather indicators, slope, and congestion index).

[0053] Trend prediction includes: Weather forecasting uses short-term weather forecast models (such as LSTM-based time series models) combined with real-time weather data and regional weather station forecasts to predict weather changes (such as rain probability and sudden changes in wind speed) for the next 5-30 minutes. Slope prediction uses high-precision maps to obtain the road slope distribution within 5 kilometers ahead. This is combined with the vehicle's real-time location and speed to generate a slope change curve (such as the length of uphill sections and the starting point of downhill sections). Traffic flow prediction uses machine learning models (such as GNN graph neural networks) to analyze historical congestion data and real-time road conditions to predict the probability and duration of congestion on the road ahead.

[0054] The historical database construction can store historical environmental data by region (such as urban administrative divisions) and time (such as weekdays / weekends, morning and evening rush hours), and use a distributed database (such as HBase) to support fast queries.

[0055] Prediction model deployment can use lightweight models (such as linear regression and random forest) deployed on the on-board ECU to achieve local real-time prediction; complex models (such as LSTM and GNN) are calculated through cloud servers, and vehicles obtain prediction results in real time through 4G / 5G networks, forming a "local + cloud" collaborative prediction architecture.

[0056] By predicting future environmental changes (e.g., a long downhill section 3 kilometers ahead, or heavy rain in 10 minutes), this approach avoids the lag inherent in traditional strategies that rely solely on real-time data, enabling predictive energy scheduling. By integrating real-time perception with historical patterns, this approach improves forecast accuracy (e.g., combining historical traffic data to determine the likelihood of sudden congestion), providing comprehensive trend analysis for complex scenarios (e.g., severe weather combined with congestion).

[0057] Step S103. Generate vehicle energy management strategy adjustment instructions based on the environmental data and the environmental change trend. The vehicle energy management strategy adjustment instructions at least include: generating control instructions for reducing energy consumption of new energy vehicles under severe weather conditions or congested traffic scenarios; generating optimization control instructions for the energy recovery system under long downhill road slope scenarios.

[0058] Specifically, based on real-time environmental data and predicted trends, differentiated energy management instructions are generated for different scenarios. The core includes: low-energy consumption control instructions (bad weather / congested scenarios): Bad weather (such as heavy rain, strong wind): reduce the peak power output of the motor, limit the maximum vehicle speed (such as from 120km / h to 90km / h), and reduce the energy consumption of the air-conditioning system (such as automatically switching to economy mode); Congested scenarios: enable "follow-up energy-saving mode", optimize the acceleration and deceleration strategy through adaptive cruise control (ACC), reduce the energy loss caused by frequent starting and stopping, and dynamically adjust the battery discharge power limit.

[0059] Energy recovery optimization command (long downhill scenario): Identify long downhill sections in advance (e.g., slope > 5% and duration > 1 km), increase the motor back EMF, and improve energy recovery efficiency (e.g., increase the recovery power from 50kW to 80kW). At the same time, coordinate control with the braking system to avoid battery overcharging.

[0060] Charging planning assistance instructions: Combines real-time range predictions (remaining battery power after considering future environmental impacts) with information about nearby charging stations (such as location, charging power, and queue status) to generate optimal charging time and location recommendations (such as the prompt "There is an unoccupied charging station 5 kilometers ahead. It is recommended to charge when the battery is higher after going downhill").

[0061] The scene recognition algorithm improves scene recognition accuracy by establishing a multi-condition rule engine (such as "current precipitation intensity > 5mm / h and wind speed > 10m / s" is judged as severe weather) and combining it with machine learning classification models (such as random forest).

[0062] The command generation strategy uses a model predictive control (MPC) algorithm to optimize the coordinated strategy of power output, energy recovery, and thermal management systems with the goal of maximizing battery life or minimizing energy consumption, and generates specific control parameters (such as the motor torque upper limit and the battery SOC operating range).

[0063] Dedicated strategies are provided for different environmental challenges (such as reducing inefficient energy consumption in congested conditions and maximizing energy recovery on downhill slopes), addressing the inefficiencies of traditional "one-size-fits-all" strategies. By leveraging commands to coordinate powertrain, battery, and thermal management subsystems (for example, simultaneously adjusting power output and battery insulation strategies in inclement weather), optimal global energy allocation is achieved.

[0064] Step S104: Complete the adaptive scheduling of the new energy vehicle according to the vehicle energy management strategy adjustment instruction.

[0065] Specifically, by converting the generated energy management instructions into execution signals of the vehicle's underlying control system, real-time scheduling is achieved through the on-board network (such as CAN / LIN bus), including: power system control: adjusting the motor torque output curve to limit sudden acceleration / deceleration; energy recovery system control: dynamically adjusting the regenerative braking intensity to optimize the motor operating point; auxiliary system control: adjusting the power distribution of loads such as air conditioning and lighting (such as reducing the power consumption of air conditioning compressors in congestion).

[0066] Instruction parsing and distribution includes the control module converting strategy instructions into standardized signals (such as control frames of the CAN bus) and transmitting them to each execution unit (such as the motor controller and battery management system BMS) through the vehicle Ethernet.

[0067] Feedback and closed-loop adjustment include real-time collection of vehicle status data (such as actual energy consumption and battery SOC changes) after execution, comparison with the prediction model, and dynamic correction of strategy parameters through the PID control algorithm to form a "perception-prediction-execution-feedback" closed loop.

[0068] Through underlying hardware control, millisecond-level instruction execution is achieved, ensuring that policy adjustments are synchronized with environmental changes, avoiding energy efficiency losses caused by control delays. Through feedback mechanisms, policy models are continuously iterated (for example, optimizing prediction algorithms based on actual energy consumption data), improving system adaptability and continuously improving energy efficiency over long-term use.

[0069] In some embodiments, in completing the adaptive scheduling of the new energy vehicle according to the vehicle energy management strategy adjustment instruction, the method also includes: generating a vehicle charging plan according to the current remaining power corresponding to the new energy vehicle, the environmental data and the predicted environmental change trend, the vehicle charging plan including the optimal charging time and the recommended charging location; and adaptively scheduling the energy distribution and charging behavior of the new energy vehicle according to the vehicle energy management strategy adjustment instruction and the vehicle charging plan to improve the energy utilization efficiency and endurance of the new energy vehicle.

[0070] During the adaptive scheduling process, the current remaining power, real-time environmental data and future environmental change trends are combined to generate a charging plan that includes the optimal charging time and recommended charging locations, thereby achieving coordinated optimization of energy distribution and charging behavior and solving the inefficiency problem caused by traditional charging planning relying on single power data.

[0071] Data input integration is achieved by collecting the current remaining power (from the battery management system BMS), real-time environmental data (weather, slope, traffic) and environmental change trends output in step S102 (such as the probability of rainfall in the next 2 hours and the distribution of congested roads ahead).

[0072] The charging plan logic defines a "charging urgency threshold" (such as triggering emergency planning when the remaining power is less than 30% and there is a continuous uphill + low temperature scenario on the future road section); and dynamically adjusts the charging priority (such as giving priority to fast charging stations with a current idle rate > 80%) based on real-time traffic data (such as the queue status of charging piles).

[0073] Avoid the risks of premature charging or insufficient range caused by relying solely on remaining battery power. For example, when a long downhill section is predicted, charging can be delayed to utilize energy recovery to increase the remaining power and reduce the number of charging times. By integrating the real-time status of charging stations (such as electricity price and power), charging wait times can be reduced (for example, avoiding the midday charging peak), improving user experience and energy efficiency.

[0074] In some embodiments, the vehicle charging plan is generated according to the current remaining power corresponding to the new energy vehicle, the environmental data and the predicted environmental change trend, including: constructing a vehicle endurance assessment model based on the current remaining power, weather conditions, road slope, traffic flow data and predicted environmental change trends; combining the endurance assessment model, matching a preset charging facility location database, the charging facility location database at least including charging pile distribution coordinates, available power, real-time electricity prices and queue status; according to the endurance assessment results and the charging facility matching results, with the goal of minimizing charging waiting time and maximizing energy utilization efficiency, determining the best charging time and recommended charging location through an optimization algorithm.

[0075] By building a range assessment model, integrating current power, environmental data and predicted trends, energy consumption in different driving scenarios is quantified; combined with the charging facility location database (including charging station coordinates, power, electricity price, and queue status), an optimization algorithm is used to solve the optimal charging plan, with the goal of minimizing charging waiting time and maximizing energy efficiency.

[0076] The battery life evaluation model is constructed by establishing an energy consumption prediction formula: Among them, P drive is related to slope, vehicle speed, and wind resistance, and P air conditioning is affected by temperature / humidity. The weights of each parameter are fitted through historical data.

[0077] The charging facility matching algorithm uses the Dijkstra algorithm to plan the path. The node weights include: remaining power consumption prediction, available power of the charging pile (fast charging with a capacity of 120kW or above is preferred), and real-time electricity prices (with reduced weights during off-peak hours). The algorithm outputs the Pareto optimal solution (e.g., "drive 20 kilometers to station A, wait 5 minutes, and charge for 30 minutes").

[0078] Compared to the traditional simplistic calculation of "range = remaining battery life / average energy consumption," this model dynamically adjusts the energy consumption coefficient based on environmental parameters (e.g., increasing energy consumption by 15% on rainy days), improving prediction accuracy. This model balances charging speed, cost, and waiting time, for example prioritizing high-power charging stations on highways and low-cost, slow-charging stations in urban commuting scenarios, reducing overall costs for users.

[0079] In some embodiments, the vehicle's energy distribution and charging behavior are adaptively scheduled based on the vehicle energy management strategy adjustment instructions and the vehicle charging plan, including: before detecting that a new energy vehicle enters a congested road section or a severe weather area, the control instructions for reducing energy consumption are executed first, and the motor output power, air-conditioning system power consumption and vehicle-mounted equipment power usage strategy are dynamically adjusted; when the new energy vehicle travels on a long downhill section, the recovery intensity of the energy recovery system is dynamically adjusted according to the real-time slope data, and the remaining power prediction result is synchronously updated; if the predicted remaining power is lower than the preset threshold and is close to the recommended charging location, a charging reminder is triggered and the route to the charging pile is automatically planned to achieve coordinated optimization of energy distribution and charging behavior.

[0080] Energy management instructions are executed in stages for different environmental scenarios (congestion, bad weather, long downhill slopes) and linked to the charging plan: Congestion / bad weather: reduce unnecessary energy consumption in advance (such as limiting air conditioning heating power); long downhill slopes: dynamically adjust energy recovery intensity and update battery life forecasts; low battery warning: automatically plan the route to the recommended charging station, realizing the "energy consumption control-energy recovery-charging planning" closed loop.

[0081] Scenario triggering mechanism: Congestion detection: When the vehicle density within 500 meters ahead is greater than 20 vehicles / km and the average speed is less than 20km / h, the "follow-vehicle energy-saving mode" is triggered, increasing the motor response delay from 200ms to 500ms to reduce frequent acceleration; Downhill recovery adjustment: When the slope is ≥5°, the energy recovery intensity increases linearly according to the slope gradient (for example, 5° corresponds to a recovery power of 60kW, 10° corresponds to 80kW), and the battery state of charge is monitored in real time through the BMS to prevent overcharging. Charging linkage logic: When the remaining power prediction value is ≤ the preset threshold (such as 20%) and the recommended charging station is within 3 kilometers of the current route, a charging reminder is pushed through the HMI interface, and the system automatically switches to "power-saving navigation mode" (disabling non-essential entertainment systems).

[0082] Through gradient strategy execution (e.g., gradually reducing power output in congestion rather than abruptly limiting it), the driving experience is maintained while reducing energy consumption (measured reduction of 12% in congested conditions). Real-time data from the energy recovery system (e.g., amount of regenerated energy) is used to inversely modify the range assessment model, forming an iterative optimization process of "prediction-execution-feedback," resulting in continuous improvement in strategy accuracy over long-term use.

[0083] In some embodiments, the environmental data and historical environmental data are used to generate the future environmental change trend corresponding to the driving path of the new energy vehicle, including: obtaining historical environmental data stored in the cloud through an on-board communication module, the historical environmental data including historical meteorological data, road slope data, traffic flow data and corresponding time-space coordinates; using a long short-term memory network or a random forest algorithm to build an environmental prediction model, inputting the real-time collected environmental data and historical environmental data into the prediction model, and outputting the probability of meteorological condition changes on the driving path in the next 1-5 hours, the road slope distribution curve and the traffic flow congestion index prediction value as the future environmental change trend; wherein, when the prediction model is trained by historical data, time series features and geographic information features are introduced for joint modeling.

[0084] Using long short-term memory networks (LSTM) or random forest algorithms, real-time environmental data is integrated with historical cloud data (including spatiotemporal coordinates) to build an environmental prediction model. This outputs the probability of weather changes, slope distribution curves, and traffic congestion index within the next 1-5 hours, addressing the lack of foresight in traditional single real-time data.

[0085] Data feature engineering: Temporal features: hourly (to distinguish between morning and evening peaks), weekday type (weekday / weekend), and holiday labels; spatial features: latitude and longitude grid encoding (for example, dividing a city into 1 km × 1 km grids and storing historical environmental data for each grid); input vectors: real-time data, historical data from the previous three hours, and spatiotemporal features.

[0086] The LSTM model has 128 hidden units in its hidden layer and uses the Adam optimizer with a mean squared error (MSE) loss function. It is trained in the cloud using three years of historical data. The vehicle terminal sends its real-time location to the cloud every five minutes and receives predictions for the next hour (e.g., "Entering a downhill section with an 8° slope in 15 minutes, lasting 2 kilometers").

[0087] Compared to traditional models that rely solely on time series, the inclusion of geographic information (such as the probability of weekend morning rush hour congestion around schools) improves traffic forecast accuracy by 30% and extends weather forecasts (such as localized rainstorms) to 20 minutes in advance. It supports short-term (15-minute) accurate forecasts (such as the starting point of a downhill slope) and long-term (5-hour) trend analysis (such as weather changes during inter-city travel), covering both urban commuting and long-distance driving scenarios.

[0088] In some embodiments, the vehicle energy management strategy adjustment instructions are generated based on the environmental data and the environmental change trend, including: when the real-time meteorological data or the predicted meteorological data meets the severe weather judgment conditions, or the predicted traffic flow congestion index is ≥ a preset threshold, a motor torque limitation instruction, a battery heating or cooling system power adjustment instruction and a non-essential equipment power limitation instruction are generated to reduce vehicle energy consumption; when the real-time road slope data or the predicted slope data shows that the length of the continuous downhill section is ≥500 meters and the slope is ≥5°, an energy recovery system pre-start instruction is generated, and the recovery current threshold is adjusted in real time according to the slope change.

[0089] By setting the severe weather / congestion judgment threshold and downhill section identification conditions, when the real-time / predicted data meets the conditions, targeted control instructions are generated: high-energy consumption scenarios: limit motor torque, adjust battery thermal management power, and shut down non-essential equipment; long downhill scenarios: pre-start the energy recovery system and dynamically adjust the recovery current threshold to match the slope change.

[0090] Definition of judgment conditions: Severe weather: rainfall >10mm / h or temperature <-10°C or wind speed >15m / s; Congestion index: Road speed is calculated based on real-time traffic data. When the average vehicle speed is <15km / h and the duration is >5 minutes, it is judged as congestion; Long downhill: The continuous downhill length is ≥500 meters and the average slope is ≥5° (pre-marked on high-precision maps).

[0091] Command parameter design: Motor torque limit: The upper limit is set to 70% of the rated torque in bad weather and 80% in congestion; Recycling current threshold: The threshold increases by 5A for every 1° increase in slope (for example, 5° corresponds to 50A, 10° corresponds to 75A), and the battery charging power is monitored in real time through the BMS to ensure that it does not exceed the safety upper limit.

[0092] Multi-conditional logic (such as "and / or" combinations) is used to avoid misjudgments (for example, light rain alone does not trigger torque limiting), thereby improving strategy robustness. Dynamic adjustment of recovery intensity in downhill scenarios maximizes energy recovery (actual downhill recovery efficiency increased by 25%), while preventing overcharging through battery safety threshold protection, ensuring system reliability.

[0093] In some embodiments, the meteorological sensors, road slope sensors and traffic flow sensors installed on the new energy vehicles are used to collect environmental data in the vehicle's current driving environment in real time, including: sensing traffic flow data through the fusion of millimeter-wave radar and camera, identifying vehicle density and driving speed within 500 meters ahead; obtaining real-time road slope and curvature information through an inertial measurement unit combined with high-precision map data; collecting real-time temperature, humidity, light intensity and rainfall data through a meteorological sensor array, and performing time synchronization and outlier calibration on multi-sensor data to form structured data containing timestamps, geographic locations and environmental parameters as the environmental data.

[0094] Traffic flow is perceived through the fusion of millimeter-wave radar and cameras, slope and curvature are acquired through the inertial measurement unit (IMU) and high-precision map, and multi-dimensional environmental data is collected by the meteorological sensor array. Time synchronization and outlier calibration are performed to form structured environmental data, solving the problems of high noise and incomplete information from a single sensor.

[0095] Sensor fusion solution: Traffic flow: Cameras identify vehicle type and distance (visual perception), millimeter-wave radar measures relative speed, and the extended Kalman filter (EKF) fuses the two data to output vehicle density and speed distribution within 500 meters ahead; Slope and curvature: The IMU measures the vehicle's pitch angle (accuracy of ±0.5°). Combined with the slope annotation on the high-precision map (resolution 0.1 meter), the real-time slope is calibrated using a weighted average method (e.g., map data accounts for 70% of the weight, and the IMU accounts for 30%); Weather calibration: When the difference between the temperature sensor and the return air temperature of the air conditioning system is greater than 5°C, the sensor is judged to be abnormal, and the average temperature of the cloud area is temporarily used for compensation.

[0096] Data structured processing: Output format: timestamp, latitude and longitude, vehicle speed, rainfall, slope, vehicle density, battery SOC, transmitted to the control module in real time via the CAN bus.

[0097] Multi-sensor fusion reduces the error of a single device (for example, the camera's recognition rate in rainy days is increased from 80% to 95%), and the outlier calibration mechanism avoids strategy misjudgments caused by sensor failures. In addition to basic environmental parameters, new curvature information (used for early deceleration strategies on curves) and vehicle density gradients (distinguishing between slow congestion and stagnant congestion) are added to provide more accurate data support for decision-making in complex scenarios.

[0098] The present invention relates to the field of artificial intelligence technology, and specifically provides a method and system for adaptive energy scheduling of new energy vehicles based on environmental perception. The present invention proposes a method for adaptive energy scheduling of new energy vehicles based on environmental perception, which collects multi-dimensional environmental data in real time through multiple sensors, combines historical data with machine learning to predict future environmental change trends, and dynamically generates energy management strategies and charging plans based on this, thereby achieving coordinated optimization of vehicle energy distribution and charging behavior.

[0099] By utilizing meteorological sensors, road slope sensors, and traffic flow sensors (such as millimeter-wave radars, cameras, and inertial measurement units), the system acquires real-time data on the current driving environment, including meteorological conditions (temperature, rainfall, snow depth, etc.), road slope information (real-time slope, continuous downhill length, etc.), and traffic flow data (vehicle density, congestion index, etc.). It also performs time synchronization and outlier correction on multi-source data.

[0100] Combining real-time environmental data with historical cloud-based environmental data (including time-space coordinates), machine learning models such as long short-term memory (LSTM) networks or random forests predict the probability of changing weather conditions (e.g., rainfall probability), road slope distribution, and traffic congestion index along the route within the next 1-5 hours, providing forward-looking guidance for strategic adjustments. Based on real-time and predicted environmental data, differentiated control commands are generated for different scenarios. For example, in severe weather (rainfall ≥ 5 mm / h) or high congestion index (≥ a preset threshold), energy-saving commands such as motor torque limit and power restriction for non-essential equipment are generated. For long downhill sections (≥ 500 meters in length and ≥ 5° in slope), energy recovery system optimization commands are generated, dynamically adjusting the recovery intensity to improve efficiency (e.g., by 15%-25%). Based on these strategic commands, vehicle power output, energy consumption distribution, and energy recovery are coordinated and optimized, combined with charging plans (optimal charging time and recommended locations) to achieve comprehensive optimization of energy utilization and range.

[0101] By integrating real-time data collection of weather, slope, and traffic flow with future trend forecasts, the system breaks through the limitations of traditional single data dimensions, making energy scheduling strategies more tailored to actual driving scenarios and enhancing their foresight. Differentiated adjustments are made to energy consumption allocation and energy recovery strategies for different scenarios, such as inclement weather, congestion, and long downhill slopes. For example, non-essential power consumption is reduced in congestion and energy recovery is maximized on downhill slopes, directly improving energy efficiency. By combining remaining power, environmental forecasts, and the real-time status of charging facilities (distribution, power, and queue status), charging times and locations are optimized with the goals of minimizing wait times and maximizing efficiency, reducing user anxiety about charging and improving charging resource utilization. Through a closed-loop control system of "real-time perception - predictive analysis - strategy adjustment - execution feedback," refined energy management is achieved, effectively extending vehicle range compared to traditional methods, with significant advantages particularly in complex environments.

[0102] like Figure 2 As shown, an embodiment of the present application also provides an adaptive energy scheduling system 200 for new energy vehicles based on environmental perception. The adaptive energy scheduling system for new energy vehicles based on environmental perception is used to execute the steps of the adaptive energy scheduling method for new energy vehicles based on environmental perception shown in the above embodiments. The adaptive energy scheduling system for new energy vehicles based on environmental perception can be a single server or a server cluster, or the adaptive energy scheduling system for new energy vehicles based on environmental perception can be a terminal, which can be a handheld terminal, a laptop computer, a wearable device, or a robot, etc.

[0103] The new energy vehicle energy adaptive scheduling system 200 based on environmental perception includes:

[0104] The data acquisition unit 201 is used to collect environmental data of the vehicle's current driving environment in real time using meteorological sensors, road slope sensors, and traffic flow sensors installed on the new energy vehicle. The environmental data includes at least meteorological conditions, road slope information, and traffic flow data.

[0105] A trend generation unit 202 is configured to generate a future environmental change trend corresponding to the driving path of the new energy vehicle based on the environmental data and historical environmental data, wherein the future environmental change trend includes changes in weather conditions, road slope, and traffic flow;

[0106] The instruction generation unit 203 is configured to generate vehicle energy management strategy adjustment instructions based on the environmental data and the environmental change trend, wherein the vehicle energy management strategy adjustment instructions at least include: generating control instructions for reducing energy consumption of new energy vehicles in severe weather conditions or congested traffic scenarios; and generating optimization control instructions for energy recovery systems in long downhill road gradient scenarios;

[0107] The scheduling completion unit 204 is configured to complete the adaptive scheduling of the new energy vehicle according to the vehicle energy management strategy adjustment instruction.

[0108] In some embodiments, in completing the adaptive scheduling of the new energy vehicle according to the vehicle energy management strategy adjustment instruction, the method also includes: generating a vehicle charging plan according to the current remaining power corresponding to the new energy vehicle, the environmental data and the predicted environmental change trend, the vehicle charging plan including the optimal charging time and the recommended charging location; and adaptively scheduling the energy distribution and charging behavior of the new energy vehicle according to the vehicle energy management strategy adjustment instruction and the vehicle charging plan to improve the energy utilization efficiency and endurance of the new energy vehicle.

[0109] In some embodiments, the vehicle charging plan is generated according to the current remaining power corresponding to the new energy vehicle, the environmental data and the predicted environmental change trend, including: constructing a vehicle endurance assessment model based on the current remaining power, weather conditions, road slope, traffic flow data and predicted environmental change trends; combining the endurance assessment model, matching a preset charging facility location database, the charging facility location database at least including charging pile distribution coordinates, available power, real-time electricity prices and queue status; according to the endurance assessment results and the charging facility matching results, with the goal of minimizing charging waiting time and maximizing energy utilization efficiency, determining the best charging time and recommended charging location through an optimization algorithm.

[0110] In some embodiments, the vehicle's energy distribution and charging behavior are adaptively scheduled based on the vehicle energy management strategy adjustment instructions and the vehicle charging plan, including: before detecting that a new energy vehicle enters a congested road section or a severe weather area, the control instructions for reducing energy consumption are executed first, and the motor output power, air-conditioning system power consumption and vehicle-mounted equipment power usage strategy are dynamically adjusted; when the new energy vehicle travels on a long downhill section, the recovery intensity of the energy recovery system is dynamically adjusted according to the real-time slope data, and the remaining power prediction result is synchronously updated; if the predicted remaining power is lower than the preset threshold and is close to the recommended charging location, a charging reminder is triggered and the route to the charging pile is automatically planned to achieve coordinated optimization of energy distribution and charging behavior.

[0111] In some embodiments, the environmental data and historical environmental data are used to generate the future environmental change trend corresponding to the driving path of the new energy vehicle, including: obtaining historical environmental data stored in the cloud through an on-board communication module, the historical environmental data including historical meteorological data, road slope data, traffic flow data and corresponding time-space coordinates; using a long short-term memory network or a random forest algorithm to build an environmental prediction model, inputting the real-time collected environmental data and historical environmental data into the prediction model, and outputting the probability of meteorological condition changes on the driving path in the next 1-5 hours, the road slope distribution curve and the traffic flow congestion index prediction value as the future environmental change trend; wherein, when the prediction model is trained by historical data, time series features and geographic information features are introduced for joint modeling.

[0112] In some embodiments, the vehicle energy management strategy adjustment instructions are generated based on the environmental data and the environmental change trend, including: when the real-time meteorological data or the predicted meteorological data meets the severe weather judgment conditions, or the predicted traffic flow congestion index is ≥ a preset threshold, a motor torque limitation instruction, a battery heating or cooling system power adjustment instruction and a non-essential equipment power limitation instruction are generated to reduce vehicle energy consumption; when the real-time road slope data or the predicted slope data shows that the length of the continuous downhill section is ≥500 meters and the slope is ≥5°, an energy recovery system pre-start instruction is generated, and the recovery current threshold is adjusted in real time according to the slope change.

[0113] In some embodiments, the meteorological sensors, road slope sensors and traffic flow sensors installed on the new energy vehicles are used to collect environmental data in the vehicle's current driving environment in real time, including: sensing traffic flow data through the fusion of millimeter-wave radar and camera, identifying vehicle density and driving speed within 500 meters ahead; obtaining real-time road slope and curvature information through an inertial measurement unit combined with high-precision map data; collecting real-time temperature, humidity, light intensity and rainfall data through a meteorological sensor array, and performing time synchronization and outlier calibration on multi-sensor data to form structured data containing timestamps, geographic locations and environmental parameters as the environmental data.

[0114] It should be noted that technical personnel in the relevant field can clearly understand that for the convenience and conciseness of description, the specific working processes of the new energy vehicle energy adaptive scheduling system based on environmental perception and each unit described above can refer to the corresponding processes in the embodiments of the new energy vehicle energy adaptive scheduling method based on environmental perception described in the above embodiments, and will not be repeated here.

[0115] The above-mentioned method for adaptive energy scheduling of new energy vehicles based on environmental perception is implemented in the form of a computer program, which can be run on the above-mentioned device.

[0116] See also Figure 3 , Figure 3 1 is a schematic block diagram of the structure of a control module provided in an embodiment of the present application. The control module includes a processor, a memory and a network interface connected via a device bus, wherein the memory may include a storage medium and an internal memory.

[0117] The storage medium can store an operating device and a computer program. The computer program includes program instructions, which, when executed, can cause a processor to execute any embodiment of the method for adaptive energy scheduling of new energy vehicles based on environmental perception.

[0118] The processor is used to provide computing and control capabilities and support the operation of the entire control module.

[0119] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any one of the new energy vehicle energy adaptive scheduling system methods based on environmental perception.

[0120] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the terminal to which the solution of the present application is applied. The specific control module may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0121] It should be understood that the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0122] In one embodiment, the processor is configured to execute a computer program stored in the memory to implement the following steps:

[0123] Using weather sensors, road slope sensors, and traffic flow sensors installed on new energy vehicles to collect real-time environmental data from the vehicle's current driving environment, the environmental data includes at least weather conditions, road slope information, and traffic flow data;

[0124] The environmental data and historical environmental data are used to generate a future environmental change trend corresponding to the driving path of the new energy vehicle, wherein the future environmental change trend includes changes in weather conditions, road slope, and traffic flow;

[0125] generating vehicle energy management strategy adjustment instructions based on the environmental data and the environmental change trend, the vehicle energy management strategy adjustment instructions at least including: generating control instructions for reducing energy consumption of new energy vehicles in adverse weather conditions or congested traffic scenarios; generating optimization control instructions for energy recovery systems in long downhill road gradient scenarios;

[0126] Adaptive scheduling of the new energy vehicle is completed according to the vehicle energy management strategy adjustment instruction.

[0127] In some embodiments, in completing the adaptive scheduling of the new energy vehicle according to the vehicle energy management strategy adjustment instruction, the method also includes: generating a vehicle charging plan according to the current remaining power corresponding to the new energy vehicle, the environmental data and the predicted environmental change trend, the vehicle charging plan including the optimal charging time and the recommended charging location; and adaptively scheduling the energy distribution and charging behavior of the new energy vehicle according to the vehicle energy management strategy adjustment instruction and the vehicle charging plan to improve the energy utilization efficiency and endurance of the new energy vehicle.

[0128] In some embodiments, the vehicle charging plan is generated according to the current remaining power corresponding to the new energy vehicle, the environmental data and the predicted environmental change trend, including: constructing a vehicle endurance assessment model based on the current remaining power, weather conditions, road slope, traffic flow data and predicted environmental change trends; combining the endurance assessment model, matching a preset charging facility location database, the charging facility location database at least including charging pile distribution coordinates, available power, real-time electricity prices and queue status; according to the endurance assessment results and the charging facility matching results, with the goal of minimizing charging waiting time and maximizing energy utilization efficiency, determining the best charging time and recommended charging location through an optimization algorithm.

[0129] In some embodiments, the vehicle's energy distribution and charging behavior are adaptively scheduled based on the vehicle energy management strategy adjustment instructions and the vehicle charging plan, including: before detecting that a new energy vehicle enters a congested road section or a severe weather area, the control instructions for reducing energy consumption are executed first, and the motor output power, air-conditioning system power consumption and vehicle-mounted equipment power usage strategy are dynamically adjusted; when the new energy vehicle travels on a long downhill section, the recovery intensity of the energy recovery system is dynamically adjusted according to the real-time slope data, and the remaining power prediction result is synchronously updated; if the predicted remaining power is lower than the preset threshold and is close to the recommended charging location, a charging reminder is triggered and the route to the charging pile is automatically planned to achieve coordinated optimization of energy distribution and charging behavior.

[0130] In some embodiments, the environmental data and historical environmental data are used to generate the future environmental change trend corresponding to the driving path of the new energy vehicle, including: obtaining historical environmental data stored in the cloud through an on-board communication module, the historical environmental data including historical meteorological data, road slope data, traffic flow data and corresponding time-space coordinates; using a long short-term memory network or a random forest algorithm to build an environmental prediction model, inputting the real-time collected environmental data and historical environmental data into the prediction model, and outputting the probability of meteorological condition changes on the driving path in the next 1-5 hours, the road slope distribution curve and the traffic flow congestion index prediction value as the future environmental change trend; wherein, when the prediction model is trained by historical data, time series features and geographic information features are introduced for joint modeling.

[0131] In some embodiments, the vehicle energy management strategy adjustment instructions are generated based on the environmental data and the environmental change trend, including: when the real-time meteorological data or the predicted meteorological data meets the severe weather judgment conditions, or the predicted traffic flow congestion index is ≥ a preset threshold, a motor torque limitation instruction, a battery heating or cooling system power adjustment instruction and a non-essential equipment power limitation instruction are generated to reduce vehicle energy consumption; when the real-time road slope data or the predicted slope data shows that the length of the continuous downhill section is ≥500 meters and the slope is ≥5°, an energy recovery system pre-start instruction is generated, and the recovery current threshold is adjusted in real time according to the slope change.

[0132] In some embodiments, the meteorological sensors, road slope sensors and traffic flow sensors installed on the new energy vehicles are used to collect environmental data in the vehicle's current driving environment in real time, including: sensing traffic flow data through the fusion of millimeter-wave radar and camera, identifying vehicle density and driving speed within 500 meters ahead; obtaining real-time road slope and curvature information through an inertial measurement unit combined with high-precision map data; collecting real-time temperature, humidity, light intensity and rainfall data through a meteorological sensor array, and performing time synchronization and outlier calibration on multi-sensor data to form structured data containing timestamps, geographic locations and environmental parameters as the environmental data.

[0133] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the processor described above can refer to the corresponding process in the method embodiments described in the above embodiments, and will not be repeated here.

[0134] A computer-readable storage medium is also provided in an embodiment of the present application, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and the processor executes the program instructions to implement the steps of the environmental perception-based adaptive energy scheduling method for new energy vehicles provided in the above-mentioned embodiments of the present application.

[0135] The computer-readable storage medium may be an internal storage unit of the control module described in the aforementioned embodiment, such as a hard disk or memory of the control module. The computer-readable storage medium may also be an external storage device of the control module, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the control module.

[0136] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present application, and such modifications or substitutions should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. An adaptive energy scheduling system for new energy vehicles based on environmental perception, characterized in that: include: Using weather sensors, road slope sensors, and traffic flow sensors installed on new energy vehicles to collect real-time environmental data from the vehicle's current driving environment, the environmental data includes at least weather conditions, road slope information, and traffic flow data; The environmental data and historical environmental data are used to generate a future environmental change trend corresponding to the driving path of the new energy vehicle, wherein the future environmental change trend includes changes in weather conditions, road slope, and traffic flow; generating vehicle energy management strategy adjustment instructions based on the environmental data and the environmental change trend, the vehicle energy management strategy adjustment instructions at least including: generating control instructions for reducing energy consumption of new energy vehicles in adverse weather conditions or congested traffic scenarios; generating optimization control instructions for energy recovery systems in long downhill road gradient scenarios; Adaptive scheduling of the new energy vehicle is completed according to the vehicle energy management strategy adjustment instruction.

2. The method according to claim 1, characterized in that In completing the adaptive scheduling of the new energy vehicle according to the vehicle energy management strategy adjustment instruction, the method further includes: A vehicle charging plan is generated based on the current remaining power corresponding to the new energy vehicle, the environmental data and the predicted environmental change trend, wherein the vehicle charging plan includes the optimal charging time and recommended charging location; and the energy distribution and charging behavior of the new energy vehicle are adaptively scheduled according to the vehicle energy management strategy adjustment instructions and the vehicle charging plan to improve the energy utilization efficiency and endurance of the new energy vehicle.

3. The method according to claim 2, characterized in that The generating of a vehicle charging plan according to the current remaining power corresponding to the new energy vehicle, the environmental data, and the predicted environmental change trend includes: Constructing a vehicle endurance assessment model based on the current remaining power, weather conditions, road slope, traffic flow data, and predicted environmental change trends; Combined with the endurance assessment model, a preset charging facility location database is matched, wherein the charging facility location database includes at least the charging pile distribution coordinates, available power, real-time electricity price and queue status; Based on the endurance assessment results and the charging facility matching results, with the goal of minimizing charging waiting time and maximizing energy utilization efficiency, the optimal charging time and recommended charging location are determined through an optimization algorithm.

4. The method according to claim 2, characterized in that Adaptively scheduling the energy distribution and charging behavior of the vehicle according to the vehicle energy management strategy adjustment instruction and the vehicle charging plan includes: When a new energy vehicle is detected entering a congested road section or a bad weather area, it will prioritize the execution of energy-saving control instructions, dynamically adjusting the motor output power, air conditioning system power consumption, and vehicle equipment power consumption strategy; When a new energy vehicle is driving on a long downhill section, the energy recovery system's recovery intensity is dynamically adjusted based on real-time slope data, and the remaining power prediction result is simultaneously updated; If the predicted remaining power is lower than the preset threshold and is close to the recommended charging location, a charging reminder is triggered and the route to the charging station is automatically planned to achieve coordinated optimization of energy distribution and charging behavior.

5. The method according to claim 1, wherein The step of generating a future environmental change trend corresponding to the driving path of the new energy vehicle by using the environmental data and historical environmental data includes: Obtain historical environmental data stored in the cloud through the vehicle communication module, wherein the historical environmental data includes historical meteorological data, road slope data, traffic flow data and corresponding time-space coordinates; An environmental prediction model is constructed using a long short-term memory network or a random forest algorithm. Real-time collected environmental data and historical environmental data are input into the prediction model, and the probability of meteorological condition changes, road slope distribution curve, and traffic congestion index prediction on the driving path within the next 1-5 hours are output as the future environmental change trend; When the prediction model is trained with historical data, time series features and geographic information features are introduced for joint modeling.

6. The method according to claim 1, wherein The generating of a vehicle energy management strategy adjustment instruction according to the environmental data and the environmental change trend includes: When real-time or forecasted weather data meets the severe weather conditions, or the predicted traffic congestion index is ≥ a preset threshold, it generates motor torque limit commands, battery heating or cooling system power adjustment commands, and non-essential equipment power limit commands to reduce vehicle energy consumption; When the real-time road slope data or predicted slope data shows that the length of the continuous downhill section is ≥500 meters and the slope is ≥5°, an energy recovery system pre-start instruction is generated, and the recovery current threshold is adjusted in real time according to the slope change.

7. The method according to claim 1, characterized in that The method utilizes the meteorological sensors, road slope sensors, and traffic flow sensors installed on new energy vehicles to collect environmental data in the vehicle's current driving environment in real time, including: By integrating millimeter-wave radar and cameras to perceive traffic flow data, it can identify the vehicle density and driving speed within 500 meters ahead; Acquire real-time road slope and curvature information through inertial measurement units combined with high-precision map data; Real-time temperature, humidity, light intensity and rainfall data are collected through a meteorological sensor array, and time synchronization and outlier correction are performed on multi-sensor data to form structured data containing timestamps, geographic locations and environmental parameters as the environmental data.

8. An adaptive energy dispatching system for new energy vehicles based on environmental perception, characterized by ,, the system comprises: A data acquisition unit, configured to utilize meteorological sensors, road slope sensors, and traffic flow sensors installed on new energy vehicles to collect environmental data in real time under the vehicle's current driving environment, wherein the environmental data includes at least meteorological conditions, road slope information, and traffic flow data; a trend generation unit, configured to generate a future environmental change trend corresponding to the driving path of the new energy vehicle based on the environmental data and historical environmental data, wherein the future environmental change trend includes changes in meteorological conditions, road slope, and traffic flow; an instruction generation unit, configured to generate vehicle energy management strategy adjustment instructions based on the environmental data and the environmental change trend, the vehicle energy management strategy adjustment instructions at least including: generating control instructions for reducing energy consumption of new energy vehicles in adverse weather conditions or congested traffic scenarios; and generating optimization control instructions for an energy recovery system in long downhill road gradient scenarios; A scheduling completion unit is used to complete the adaptive scheduling of the new energy vehicle according to the vehicle energy management strategy adjustment instruction.

9. A control module, characterized in that: The control module includes a memory and a processor; The memory is used to store computer programs; The processor is configured to execute the computer program and implement the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, causes the processor to implement the method according to any one of claims 1 to 7.

Images