A new energy vehicle endurance management method and system based on tire pressure-temperature self-aware intelligent tire

Abstract

The application discloses a new energy vehicle endurance management method and system based on tire pressure-temperature self-sensing intelligent tires, and is applied to the technical field of data processing.The application aims at new energy vehicle endurance optimization and constructs an intelligent tire and whole vehicle cooperative management system.Tire pressure and temperature data are collected through a conductive wet mixing rubber distributed sensor, combined with vehicle load, road conditions and other multi-source information, and pretreated through noise reduction and calibration to make a standardized data set.The endurance strategy is determined based on working condition complexity and ECU computing power, a monitoring window and a transmission frequency are set, and data is imported into the ECU through a parallel mechanism.The multi-modal feature fusion algorithm is used to optimize power control parameters, dynamically adapt motor power and braking recovery strategies, generate optimal vehicle speed recommendations, and balance endurance maximization and driving safety.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and system for managing the range of new energy vehicles based on tire pressure-temperature self-sensing intelligent tires. Background Technology

[0002] In existing new energy vehicle range management technologies, tires, as a core driving component, have their tire pressure, temperature, and rolling resistance coefficient directly affecting range energy consumption. However, traditional range management solutions have the following shortcomings: The lack of integrated perception and correlation analysis of tire pressure, temperature and rolling resistance, relying more on single parameters or non-real-time data, and failing to make full use of tire dynamic working status feedback to optimize range; The data collection dimension is limited, and it does not effectively integrate multi-source vehicle-related data such as vehicle load, road conditions, and motor power. Furthermore, the sensor signals are susceptible to interference, and the transmitted data is biased, affecting the accuracy of the range strategy. The range strategy was not formulated in accordance with actual operating conditions such as the complexity of driving conditions and the computing power resources of the vehicle ECU. Parameters such as monitoring window and data transmission frequency were fixed and could not be dynamically adapted to different scenarios. The optimization of power control parameters has not established a mapping relationship between multimodal data and range strategy. The adjustment of motor power and regenerative braking strategy is not coordinated enough with tire working characteristics and vehicle configuration, making it difficult to achieve a balance between maximizing range and driving safety. Summary of the Invention

[0003] To solve the above-mentioned technical problems, the present invention provides the following technical solution: A method for managing the range of new energy vehicles based on a tire pressure-temperature self-sensing intelligent tire includes: collecting multi-source core sensor data and vehicle-wide associated data, including real-time tire pressure monitoring data and temperature distribution data collected by distributed sensors composed of conductive wet-mixed rubber compounds, vehicle load parameters, navigation road condition information, motor output power records, regenerative braking strategy parameters, and raw sensor data transmitted by the tire's built-in RFID chip / wireless module; setting optimal tire pressure range, temperature warning threshold, and rolling resistance coefficient calculation weights based on the goal of maximizing the range of new energy vehicles, power system safety thresholds, and tire operating characteristics; processing the multi-source core sensor data and vehicle-wide associated data, completing sensor signal noise reduction, RFID / wireless module data transmission calibration, time-series data alignment, and tire pressure-temperature-rolling resistance correlation feature extraction, creating a standardized range management dataset, reading the tire pressure and temperature feature dimensions, driving time-series data volume, and parameter modal type information of the dataset, and sorting the data according to the degree of correlation between the data and range energy consumption and tire operating status; and combining the data with... Based on the complexity of driving conditions, the computing power resources of the onboard ECU, the characteristics of energy consumption optimization algorithms, and the response characteristics of distributed sensors, a range coordination management strategy is determined. The monitoring window size and the number of dynamic adjustments are set according to the tire pressure and temperature characteristics and the amount of driving time-series data, matching the sensor data transmission frequency. The dataset is split according to the target range management strategy, forming control batches containing tire pressure and temperature characteristic data, rolling resistance coefficient estimation data, raw sensor data, and energy consumption optimization label information. Data is transmitted in an orderly manner based on the monitoring window size and the number of dynamic adjustments. Data of the same type and consistent with energy consumption optimization are synchronously imported into the ECU processing unit through a parallel processing mechanism. A multimodal feature fusion algorithm is used to learn the mapping relationship between tire pressure and temperature characteristics, rolling resistance coefficient, and range management strategy. Power control parameters are optimized according to a weighted fusion logic of tire pressure data, temperature data, road condition information, and load parameters. Combined with tire model, vehicle power configuration, and driving scenario, motor output power and regenerative braking strategy parameters are dynamically adapted to generate a target vehicle speed recommendation command.

[0004] Another aspect of this application is a new energy vehicle range management system based on tire pressure-temperature self-sensing intelligent tires, the system being used to execute executable instructions to implement the above-described new energy vehicle range management method based on tire pressure-temperature self-sensing intelligent tires.

[0005] According to another aspect of this application, an electronic device includes: a first processor; and a memory for storing executable instructions of the first processor; wherein the first processor is configured to execute the above-described method for managing the range of a new energy vehicle based on a tire pressure-temperature self-sensing intelligent tire by executing the executable instructions.

[0006] According to another aspect of this application, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a second processor, implements the above-described method for managing the range of a new energy vehicle based on a tire pressure-temperature self-sensing intelligent tire.

[0007] Its beneficial effects are as follows: This invention provides a new energy vehicle range management method and system based on a tire pressure-temperature self-sensing intelligent tire. It constructs a collaborative management system between the intelligent tire and the entire vehicle. Tire pressure and temperature data are collected through distributed sensors in conductive wet-mixed rubber compounds. This data is then integrated with multi-source information such as vehicle load and road conditions, and preprocessed through noise reduction and calibration to generate a standardized dataset. A range strategy is determined by considering factors such as operating condition complexity and ECU computing power. A monitoring window and transmission frequency are set, and data is imported into the ECU through a parallel mechanism. A multi-modal feature fusion algorithm is used to optimize power control parameters, dynamically adapting motor power and regenerative braking strategies to generate optimal vehicle speed recommendations, achieving a balance between range and safety.

[0008] This invention achieves multi-source data fusion and precise processing, solving the problems of single data dimension and large interference in traditional solutions, and improving the accuracy of range strategy formulation. The dynamically adaptable range strategy matches different operating conditions and hardware resources, avoiding poor adaptability caused by fixed parameters, and balancing data processing timeliness and range optimization accuracy. The application of a multi-modal feature fusion algorithm achieves deep adaptation of power parameters and driving scenarios, improving driving range while ensuring driving safety. The parallel transmission mechanism improves data transmission and processing efficiency, ensuring real-time adjustment of power parameters and further optimizing range performance. Attached Figure Description

[0009] Figure 1 A flowchart illustrating a method for managing the range of a new energy vehicle based on a tire pressure-temperature self-sensing intelligent tire, provided as an embodiment of the present invention; Figure 2 This is a schematic diagram of a new energy vehicle range management system based on a tire pressure-temperature self-sensing intelligent tire, provided as an embodiment of the present invention. Detailed Implementation

[0010] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention. Figure 1 This application describes a method and system for managing the range of new energy vehicles based on tire pressure-temperature self-sensing smart tires, according to exemplary embodiments thereof.

[0011] In this application embodiment, a method for managing the range of new energy vehicles based on tire pressure-temperature self-sensing intelligent tires is described, such as... Figure 1 As shown: S101 collects multi-source core sensor data and vehicle-related data.

[0012] In one embodiment, a distributed sensor based on conductive wet-mixed rubber compound is used to achieve real-time capture of tire pressure and temperature data. The sensors are evenly distributed in the tire liner and key stress areas of the tire carcass to ensure comprehensive and accurate data acquisition. The distributed sensor senses the resistance fluctuations of the conductive wet-mixed rubber compound caused by changes in tire pressure and converts them into quantifiable tire pressure data. For example, in a constant-speed driving scenario on an urban road, the sensor continuously monitors at a sampling frequency of 10Hz. When the tire pressure drops from the standard value of 2.5 bar to 2.3 bar, the rubber compound resistance changes by 3% simultaneously. The sensor converts this resistance signal into the corresponding tire pressure value and records it, ensuring that every 0.01 bar change in tire pressure is accurately captured.

[0013] Based on the thermosensitive properties of conductive wet-mixed rubber compounds, sensors detect temperature differences in different areas of the tire in real time. For example, after a vehicle has been driving continuously on the highway for one hour, the temperature in the center area of ​​the tire tread rises to 65°C, the sidewall area to 52°C, and the shoulder area to 58°C. Distributed sensors capture the temperature signals of each area, and after internal signal conversion, a complete tire temperature distribution dataset is formed. The acquisition frequency is dynamically adjusted according to the driving time, increasing to 15Hz during high-speed driving.

[0014] By connecting to the CAN bus of the new energy vehicle's overall control system, core operating parameters related to range management are synchronously acquired, ensuring the real-time nature and relevance of data acquisition. Core data reflecting the vehicle's load status is directly read from the overall control system, including the total load value fed back by the onboard weight sensor and the front-to-rear axle load distribution ratio. For example, when the vehicle is unloaded, the total load is 1.8 tons, and the front-to-rear axle load ratio is 4:6; when carrying 3 passengers and 50kg of luggage, the total load increases to 2.1 tons, and the front-to-rear axle load ratio adjusts to 4.2:5.8. The system collects this type of load change data in real time, with a collection interval of 1 second.

[0015] The system connects to the vehicle navigation system to obtain real-time traffic information such as road type, road gradient, curve curvature, speed limit, and driving distance. For example, if the navigation system identifies the current driving segment as a congested urban area with a 0° road gradient, no curves, and a speed limit of 60 km / h, and the next 5 kilometers is a free-flowing highway with a speed limit of 120 km / h, the system will collect this traffic information completely and synchronize it to the dataset. The traffic information update frequency is consistent with the navigation system, refreshing every 3 seconds.

[0016] The system extracts real-time motor output power data from the vehicle's powertrain control system, including instantaneous power, average power, and power change trends. For example, during vehicle acceleration, the motor output power rapidly increases from 0kW to 80kW, stabilizes at 30kW during constant speed driving, and drops below 10kW during deceleration. The system records this power change data at a frequency of 5Hz, forming a motor output power time-series curve. The system also collects braking trigger signals, braking intensity, and corresponding energy recovery power parameters from the vehicle's braking system. For example, when the driver lightly presses the brake pedal, the braking intensity is 0.3g, corresponding to an energy recovery power of 25kW; during emergency braking, the braking intensity is 0.8g, and the energy recovery power increases to 40kW. The system simultaneously collects the braking trigger time, braking intensity level, and recovery power data, with a response time of no more than 0.1 seconds.

[0017] By utilizing the tire's built-in RFID chip or wireless module, raw sensor signals captured by distributed sensors are transmitted contactlessly to the vehicle's receiving unit, ensuring the stability and integrity of data transmission. The tire's built-in RFID chip establishes a wireless communication link with the vehicle's RFID reader, storing unprocessed data such as raw resistance and voltage signals collected by the distributed sensors. For example, every 30 seconds, 1500 sets of raw tire pressure signals and 1500 sets of raw temperature signals collected during that period are packaged and transmitted, covering a transmission distance of 0-5 meters, ensuring uninterrupted signal transmission during vehicle operation. Upon successful reception, the vehicle's receiving unit sends back an acknowledgment signal, and the chip clears the transmitted data upon receiving the acknowledgment. When RFID transmission is interfered with, it automatically switches to a wireless module (such as Bluetooth BLE 5.0) for data transmission. The module encapsulates the raw sensor data in a frame format, with each frame containing a data type identifier, a collection timestamp, and the raw signal value. For example, in complex electromagnetic environments, the wireless module transmits data at a rate of 200ms / frame. Each frame contains 8 bytes of raw tire pressure signal and 8 bytes of raw temperature signal. The vehicle-mounted receiving unit ensures data integrity by verifying the frame header and frame footer, and the loss rate is controlled within 0.1%.

[0018] S102 sets the optimal tire pressure range, temperature warning threshold, and rolling resistance coefficient calculation weights based on the goal of maximizing the range of new energy vehicles, the safety threshold of the power system, and the tire working characteristics.

[0019] In one implementation, with the goal of maximizing the range of new energy vehicles as the core guideline, and combining the hard threshold for safe operation of the power system with the tire's own structure and material properties, three types of key information are systematically integrated: core parameters of tire pressure control, temperature warning boundary conditions, and rolling resistance coefficient calculation weights.

[0020] The core parameters for tire pressure control need to balance driving range efficiency and tire load-bearing capacity. For compact new energy passenger cars, the basic tire pressure range is set to 2.3 bar to 2.8 bar. This range reduces tire rolling resistance to improve driving range while preventing excessive tire sidewall deformation caused by low tire pressure. Temperature warning boundary conditions must match the tire's high-temperature resistance limit, with a normal operating temperature upper limit of 70°C. Exceeding this temperature can easily degrade tire rubber performance, affecting driving safety. The weighting of the rolling resistance coefficient calculation must be correlated with the degree of influence of tire pressure and temperature on rolling resistance. Initially, the tire pressure weight is set to 0.6 and the temperature weight to 0.4, as tire pressure changes have a more direct impact on rolling resistance. The correlation requirements for each parameter are clearly defined: when the tire pressure is below 2.3 bar, the temperature weight in the rolling resistance coefficient calculation automatically increases to 0.5; when the temperature exceeds 65°C, the tire pressure fine-tuning mechanism is triggered first to ensure parameter linkage and adaptation.

[0021] The parameter setting logic is designed based on the synergistic needs of range optimization and tire safety, clearly defining the setting standards for core and related parameters. Core parameters include the optimal tire pressure range, temperature warning threshold, and rolling resistance coefficient calculation weight. Related parameters include tire model adaptation parameters and powertrain response threshold information. Based on the core needs of range optimization and tire safety coordination, a clear parameter setting logic is designed, distinguishing between core and related parameters and clarifying their respective standards. Among the core parameters, the optimal tire pressure range is refined according to tire size: 2.4 bar to 2.6 bar for 195 / 65R15 tires and 2.5 bar to 2.7 bar for 225 / 50R18 tires, ensuring that tires of different sizes can maintain a low rolling resistance state. The temperature warning threshold is set in three levels: Level 1 warning threshold 65℃, Level 2 warning threshold 68℃, and Level 3 warning threshold 70℃, corresponding to different safety response levels. The rolling resistance coefficient calculation weights are set according to the basic scenario: 0.55 for tire pressure and 0.45 for temperature when driving on urban roads, and 0.65 for tire pressure and 0.35 for temperature when driving on highways. Among the associated parameters, tire model adaptation parameters include the load factor and elastic modulus of different tires; for example, the load factor of a 195 / 65R15 tire is set to 615 kg / tire, and the load factor of a 225 / 50R18 tire is set to 750 kg / tire. The power system response threshold information is set to a minimum step size of 5 kW for motor output power adjustment and 3 kW for regenerative braking power adjustment, ensuring that parameter adjustments match the power system response capability.

[0022] To ensure a balance between range optimization and driving safety, the system incorporates dynamic fine-tuning of tire pressure ranges, tiered temperature threshold warnings, and real-time adaptation of rolling resistance coefficient weights, taking into account the range stability requirements under various driving conditions such as urban congestion, highways, and mountain slopes. Specifically, the dynamic fine-tuning rules for tire pressure ranges are as follows: In urban congestion, with frequent starts and stops, tire pressure is dynamically adjusted every 5 minutes at ±0.05 bar, maintaining it near the midpoint of the optimal range; on highways at constant speeds, tire pressure remains stable, only fine-tuning by 0.03 bar to 0.05 bar when the temperature change exceeds 5°C; and on mountain slopes, tire pressure is increased by 0.05 bar to 0.1 bar uphill to enhance load-bearing capacity, and then returns to the optimal range downhill. The temperature threshold grading warning rules are as follows: When a Level 1 warning is triggered, the system only pushes a notification message to the driver; when a Level 2 warning is triggered, the system automatically reduces the motor output power by 10% to 20% to reduce tire load; when a Level 3 warning is triggered, a forced cooling reminder is activated and the maximum vehicle speed is limited to 60 km / h. The rolling resistance coefficient weight real-time adaptation rules are as follows: When the tire pressure deviates from the optimal range by ±0.1 bar, the tire pressure weight in the rolling resistance coefficient increases or decreases by 0.05; when the temperature deviates from the normal operating temperature by ±5℃, the temperature weight increases or decreases by 0.03; when the vehicle load changes by more than 300 kg, both the tire pressure weight and the temperature weight are adjusted by 0.02 to ensure that the weights are adapted to the actual driving conditions.

[0023] The system systematically integrates and standardizes parameter setting requirements, range and safety coordination needs, and parameter optimization rules to generate basic range management data that includes four core dimensions: parameter type, setting specifications, correlation logic, and optimization strategy. This enables structured and standardized storage and management of the data, providing accurate, reliable, and directly accessible data support for subsequent full-process range management.

[0024] The core of the parameter type dimension is to distinguish between core parameters and related parameters, and to clearly define the data attributes of each parameter to ensure the accuracy and adaptability of parameter calls. Core parameters directly determine the range optimization effect and the bottom line of driving safety, including three categories: optimal tire pressure range, temperature warning threshold, and rolling resistance coefficient calculation weight. Among them, the optimal tire pressure range and temperature warning threshold are range-type data, while the rolling resistance coefficient calculation weight is numerical data. Supporting core parameters are those that adapt to different vehicle configurations and operating scenarios, including tire model adaptation parameters (such as load factor and elastic modulus, both of which are numerical) and powertrain response threshold information (such as the minimum step size for motor output power adjustment and the minimum step size for regenerative braking power adjustment, both of which are numerical). By clearly classifying and labeling data attributes, type confusion or adaptation errors are avoided during subsequent parameter calls, laying the foundation for parameter calculation and strategy formulation.

[0025] For each parameter category, specifications are defined, detailing its specific values, ranges, and corresponding applicable scenarios to ensure accurate application across different situations. Breaking it down by tire model, the optimal range for the 195 / 65R15 tire is 2.4bar-2.6bar, suitable for urban commuting in compact family electric vehicles; the optimal range for the 225 / 50R18 tire is 2.5bar-2.7bar, suitable for mixed high-speed and urban driving scenarios in mid-to-high-end electric vehicles; and the basic universal range is 2.3bar-2.8bar, covering the basic driving needs of most family electric sedans. A three-level warning system is adopted: Level 1 warning threshold 65℃ (suitable for urban congestion and low-speed driving scenarios, alerting drivers to tire condition); Level 2 warning threshold 68℃ (suitable for highway constant-speed driving scenarios, initiating light protective measures); and Level 3 warning threshold 70℃ (suitable for long-distance uphill driving and high-temperature environments, initiating strong protective measures), all matching the high-temperature resistance limits of tire rubber.

[0026] Based on driving conditions, the tire pressure weight is set to 0.55 and temperature weight to 0.45 for urban driving (suitable for scenarios with frequent start-stop cycles and large tire pressure fluctuations); for highway driving, the tire pressure weight is set to 0.65 and temperature weight to 0.35 (suitable for scenarios with constant speed driving and more significant temperature effects); and for mountainous slope driving, the tire pressure weight is set to 0.6 and temperature weight to 0.4 (suitable for scenarios with large load fluctuations and where tire pressure and temperature jointly affect rolling resistance). The load factor of 195 / 65R15 tires is set to 615 kg / tire and the elastic modulus to 2.5 GPa; the load factor of 225 / 50R18 tires is set to 750 kg / tire and the elastic modulus to 2.8 GPa. The minimum step size for adjusting motor output power is 5 kW, and the minimum step size for adjusting regenerative braking power is 3 kW, adapting to the response capabilities of most new energy vehicle power systems.

[0027] The logical linkage clearly defines the rules governing the interaction between core parameters and between core parameters and related parameters, ensuring the synergy and consistency of parameter adjustments. When tire pressure is below 2.3 bar (the lower limit of the baseline range), the temperature weight in the rolling resistance coefficient calculation automatically increases from the baseline value of 0.4 to 0.5, strengthening the influence of temperature on rolling resistance. When the temperature exceeds 65℃ (the first-level warning threshold), the tire pressure fine-tuning mechanism is triggered first, adjusting the pressure to the median of the optimal range at a rate of +0.03 bar every 5 minutes to prevent tire performance degradation due to temperature increases. For every 0.001 increase in the rolling resistance coefficient, the lower limit of the optimal tire pressure range increases by 0.05 bar, balancing the impact of increased rolling resistance on driving range. When tire models are changed, the optimal tire pressure range is adjusted proportionally to the load factor. For example, if the load factor is increased from 615 kg / tire to 750 kg / tire (an increase of 22%), the lower limit of the optimal tire pressure range is simultaneously increased from 2.4 bar to 2.5 bar (an increase of 4.2%). When the power system response threshold is adjusted, the rolling resistance coefficient weight is adjusted accordingly. For example, if the motor output power adjustment step size is reduced from 5 kW to 3 kW, the tire pressure weight is increased by 0.05 to ensure that the parameter adjustment accuracy matches the power system response capability.

[0028] For each parameter type, the optimization strategy details the adjustment conditions, adjustment range, and execution process under different operating conditions to ensure that the parameters dynamically adapt to actual driving conditions. In urban congestion, where vehicles frequently start and stop, the trigger condition is a tire pressure deviation of ±0.05 bar from the median of the optimal range, with an adjustment range of ±0.05 bar every 5 minutes, and the execution process is "data monitoring -- deviation judgment -- automatic fine-tuning -- effect feedback". On highways at constant speeds, the trigger condition is a temperature change exceeding 5°C, with an adjustment range of 0.03-0.05 bar, and the execution process is "temperature monitoring -- threshold judgment -- precise fine-tuning -- stable maintenance". In mountainous terrain, the trigger condition for uphill driving is a load increase exceeding 300 kg, with an adjustment range of 0.05-0.1 bar; the trigger condition for downhill driving is a load decrease exceeding 200 kg, with an adjustment range of 0.05-0.1 bar, and the execution process is "load monitoring -- slope identification -- directional adjustment -- real-time calibration".

[0029] When a Level 1 warning (65℃) is triggered, the execution process is "temperature monitoring -- threshold trigger -- instrument prompt -- continuous monitoring", only a prompt message is pushed to the driver; when a Level 2 warning (68℃) is triggered, the execution process is "temperature monitoring -- threshold trigger -- automatically reduce motor output power by 10%-20% -- reduce tire load -- continuous monitoring -- intervention is canceled when temperature drops"; when a Level 3 warning (70℃) is triggered, the execution process is "temperature monitoring -- threshold trigger -- activate forced cooling reminder -- limit maximum vehicle speed to 60km / h -- continuous monitoring -- limit is lifted when temperature is below 65℃". When tire pressure deviates from the optimal range by ±0.1 bar, the trigger condition is that the tire pressure deviates stably for three consecutive monitoring cycles (each cycle is 10 seconds). The adjustment range is a 0.05 increase or decrease in the tire pressure weight, and the execution process is "tire pressure monitoring -- deviation judgment -- weight adjustment -- rolling resistance coefficient recalculation". When the temperature deviates from the normal operating temperature by ±5℃, the trigger condition is that the temperature change rate exceeds 2℃ / minute. The adjustment range is a 0.03 increase or decrease in the temperature weight, and the execution process is "temperature monitoring -- rate judgment -- weight adjustment -- rolling resistance coefficient recalculation". When the vehicle load changes by more than 300 kg, the trigger condition is a sudden change in the load sensor data. The adjustment range is a 0.02 increase or decrease in both the tire pressure weight and the temperature weight, and the execution process is "load monitoring -- sudden change judgment -- weight coordination adjustment -- rolling resistance coefficient recalculation".

[0030] Through detailed analysis and integration of the four dimensions, a complete basic data document for range management was finally formed. This document not only echoes the parameter setting logic based on the goal of maximizing range, the safety threshold of the power system, and the working characteristics of the tires mentioned earlier, but also provides clear and operable data basis for subsequent data preprocessing, strategy formulation, parameter optimization, and other links, ensuring the consistency and accuracy of the entire range management process.

[0031] S103 processes multi-source core sensor data and vehicle-related data, including sensor signal noise reduction, RFID / wireless module data transmission calibration, time-series data alignment, tire pressure-temperature-rolling resistance correlation feature extraction, and creates a standardized range management dataset. It reads the tire pressure and temperature feature dimensions, driving time-series data volume, and parameter mode type information of the dataset and sorts them according to the degree of correlation between the data and range energy consumption and tire working status.

[0032] In one embodiment, an adaptive noise cancellation algorithm is used to process the environmental interference noise in the tire pressure and temperature signals collected by the distributed sensor of the conductive wet-process rubber compound, ensuring signal purity. The algorithm takes the raw electrical signal collected by the sensor as input, distinguishes between the frequency characteristics and noise characteristics of the signal, sets a noise frequency threshold of 20Hz to 100Hz, and filters out interference signals within this frequency band. For example, when a vehicle is driving on a bumpy road, the tire pressure signal collected by the sensor is mixed with high-frequency vibration noise, and the raw signal exhibits irregular fluctuations. After processing by the adaptive noise cancellation algorithm, the noise signal is effectively filtered out, and the output tire pressure signal is smooth and accurately reflects the actual tire pressure changes, such as a steady drop from 2.5 bar to 2.45 bar without noise interference. For the temperature signal, the same algorithm filters out instantaneous noise generated by external airflow and road friction, ensuring that the temperature data stably tracks the actual temperature change trend of the tire.

[0033] Considering the potential data deviations caused by distance and electromagnetic interference during data transmission from RFID chips or wireless modules, data calibration is performed based on a pre-defined calibration benchmark and error compensation model. First, a calibration benchmark library is established to store standard data samples under different transmission distances and electromagnetic environments. The error compensation model determines compensation coefficients by learning the deviation patterns between actual and transmitted data from the samples. For example, when the distance between the RFID chip and the vehicle-mounted receiver is 3 meters, the transmitted tire pressure data might be 0.08 bar lower than the actual value, and the temperature data 2°C higher. The calibration model uses the corresponding compensation coefficients for this scenario to increase the transmitted tire pressure data by 0.08 bar and decrease the temperature data by 2°C, thus achieving data calibration. For data transmitted by the wireless module, if electromagnetic interference causes a set of temperature data to be 68°C, while adjacent transmitted data from the same period are all around 55°C, the calibration model determines this data as an outlier. Based on the trend of the preceding and following time-series data, it corrects the temperature to 56°C to ensure data consistency.

[0034] Because the data from multiple sources are collected at different frequencies, tire pressure, temperature, vehicle load, and road conditions need to be time-aligned according to a unified timeline to ensure consistency in the time dimension of the data. A unified timestamp precision of milliseconds is set, and a global timeline is established with the vehicle's start time as the origin. For tire pressure and temperature data collected at a frequency of 10Hz, a data point is recorded every 100 milliseconds. For vehicle load data collected at a 1-second interval and road condition data refreshed every 3 seconds, interpolation is performed to complete the data along the timeline, ensuring that all types of data have corresponding values ​​at the same time point. For example, at a time point 10 seconds after startup, the tire pressure data is 2.5 bar, the temperature data is 52℃, the vehicle load data is interpolated to 2.0 tons, and the road condition data is "smooth urban road," achieving accurate alignment of all data at this time point and laying the foundation for subsequent correlation analysis.

[0035] Based on calibrated and aligned tire pressure and temperature data, combined with vehicle load parameters, multivariate regression analysis was used to extract the correlation features between these three factors and the tire rolling resistance coefficient, clarifying the influence of each parameter on rolling resistance. A multivariate regression model was constructed using tire pressure, temperature, and load data as input variables and rolling resistance coefficient as the output variable. During model training, a large amount of measured data was used as samples to iteratively optimize model parameters, determine the model's weight coefficients and bias terms, and terminate training when the model's prediction error was less than 3%. For example, when the tire pressure was 2.5 bar, the temperature was 55°C, and the load was 2.0 tons, the rolling resistance coefficient calculated by the model was 0.008; when the tire pressure dropped to 2.3 bar, the temperature rose to 60°C, and the load remained unchanged, the rolling resistance coefficient increased to 0.010. The model extracted correlation features showing a negative correlation between tire pressure and rolling resistance coefficient and a positive correlation between temperature and rolling resistance coefficient, and output the correlation strength values ​​of these features for subsequent data sorting.

[0036] After integrating the various processed data, a standardized range management dataset is created using a unified data format and field definitions to ensure the data is structured and directly usable for subsequent processing. The dataset includes fields such as data identifier, timestamp, tire pressure data, temperature data, vehicle load data, navigation traffic data, motor output power data, regenerative braking strategy parameters, and rolling resistance correlation feature data. The data is stored in a unified numerical format, and traffic data is converted into corresponding coded values ​​according to scenarios such as urban congestion, urban smooth traffic, highways, and mountain slopes. For example, a data record might have an identifier of 001, a timestamp of 15 seconds after startup, tire pressure of 2.48 bar, temperature of 53°C, load of 2.0 tons, a traffic code of urban smooth traffic, motor output power of 35 kW, regenerative braking power of 0 kW, and rolling resistance correlation feature value of 0.009. All data is arranged in order by field, forming standardized data records. Multiple records are combined to constitute a complete standardized range management dataset.

[0037] The core information of the standardized dataset is extracted, including tire pressure and temperature feature dimensions, driving time-series data volume, and parameter modality types. The dataset is then sorted according to the correlation between the data and driving range, energy consumption, and tire operating status. The tire pressure and temperature feature dimensions are statistically analyzed based on the attribute categories of the collected tire pressure and temperature data, such as tire pressure value, temperature value, tire pressure change rate, and temperature change rate, totaling four feature dimensions. The driving time-series data volume represents the total number of time points included in the dataset; for example, after one hour of vehicle driving, the dataset contains 3600 time-series data records. Parameter modality types are categorized into three types: sensor data, vehicle operation data, and road condition data. During sorting, a correlation score standard is used: tire pressure, temperature, and rolling resistance are scored at 9 points; vehicle load, motor output power, and regenerative braking strategy parameters are scored at 7 points; and navigation road condition data is scored at 5 points. The data is sorted from highest to lowest score, with high-correlation data retained first for easy access to core data when formulating subsequent driving range strategies.

[0038] S104, combining the driving condition complexity of the dataset, the computing power resources of the vehicle ECU, the characteristics of energy consumption optimization algorithms and the response characteristics of distributed sensors, determines the range coordination management strategy, sets the monitoring window size and the number of dynamic adjustments based on the tire pressure and temperature characteristics and the amount of driving time series data, and matches the sensor data transmission frequency.

[0039] In one implementation, four core elements are comprehensively analyzed: driving condition complexity, on-board ECU computing power resources, energy consumption optimization algorithm characteristics, and distributed sensor response characteristics. These elements are then systematically integrated with the core direction of the range coordination management strategy, the monitoring window setting logic, the dynamic adjustment trigger conditions, and the data transmission frequency matching principle to clarify the relationship between each element and parameter and the strategy adaptation scenarios.

[0040] Driving condition complexity is categorized into three levels based on road type, traffic density, and gradient variation: high-level complexity for congested urban roads, low-level complexity for highways with uniform speeds, and medium-level complexity for mountainous sloping roads. Onboard ECU computing power resources are divided into high, medium, and low tiers based on data processing capabilities: high-end ECUs have high computing power, capable of processing eight channels of high-dimensional data simultaneously, while economy ECUs have low computing power, supporting only four channels of basic data processing. Energy consumption optimization algorithms are categorized into fast convergence and precise iterative algorithms. Fast convergence algorithms are suitable for scenarios with high real-time requirements, while precise iterative algorithms are suitable for scenarios with high accuracy requirements for range optimization. Distributed sensor response characteristics are categorized into fast, medium, and slow tiers based on response speed: ≤0.1 seconds for fast response, ≤0.3 seconds for medium response, and ≤0.5 seconds for slow response.

[0041] Taking urban traffic congestion as a typical example, this scenario involves dense traffic flow and frequent starts, stops, accelerations, and decelerations, classifying the driving conditions as highly complex. Tire pressure fluctuates frequently, and temperature rises rapidly due to friction and load changes, demanding extremely high real-time and dynamic adjustment capabilities for range optimization. If the onboard ECU has high-performance computing capabilities (capable of processing 8 channels of high-dimensional data simultaneously), the energy consumption optimization algorithm is a fast-convergence type (suitable for scenarios with high real-time requirements), and the distributed sensors are fast-response type (response time ≤ 0.1 seconds, accurately capturing instantaneous changes in tire pressure and temperature), then the core direction of the range collaborative management strategy is specifically set as high-frequency dynamic adjustment to ensure the strategy can adapt to rapid changes in road conditions and tire status in a timely manner.

[0042] Considering the highly dynamic nature of tire conditions in urban congestion scenarios, the monitoring window is set with a small window and high-frequency updates, with an initial window size of 8 seconds (below the baseline of 10 seconds). The core purpose of this setting is to increase data sampling density, completing the full collection and status assessment of tire pressure, temperature, and related data every 8 seconds. This avoids missing key status changes due to an excessively large window (such as small fluctuations in tire pressure of 0.03-0.05 bar caused by frequent starts and stops, or rapid temperature increases of 3-5°C in a short period of time), ensuring that subsequent adjustment strategies can accurately respond to the dynamic conditions of the tires.

[0043] The dynamic adjustment trigger conditions are clearly defined as a tire pressure change ≥0.05 bar or a temperature change ≥3℃. This threshold is set based on the actual operating characteristics of urban congestion scenarios: In urban congestion, vehicles frequently accelerate and decelerate, causing small but frequent fluctuations in tire pressure. When the fluctuation reaches 0.05 bar, the tire rolling resistance coefficient will change significantly (an increase of approximately 0.001-0.002). If the power parameters are not adjusted in time, it will lead to a 5%-8% increase in driving range energy consumption. Therefore, this is used as the tire pressure trigger threshold. Frequent braking and starting will increase tire friction and cause the temperature to rise rapidly. When the temperature rises ≥3℃, the rubber elastic modulus will change, and the tire grip and rolling resistance characteristics will change simultaneously. If the original power parameters are maintained, it may affect driving safety and driving range efficiency. Therefore, this is used as the temperature trigger threshold. As long as either condition is met, the system will immediately start the parameter adjustment process to ensure the timeliness of the strategy response.

[0044] The data transmission frequency matching principle is set to high-frequency transmission, specifically 18Hz (within the high end of the 5Hz-20Hz adaptation range). This frequency selection is deeply adapted to scenario requirements and hardware capabilities. In urban congestion scenarios, sensors collect data at a frequency of 10Hz-15Hz. The 18Hz transmission frequency ensures that the collected raw and feature data are transmitted to the ECU without delay, avoiding adjustment lag caused by data accumulation. Combined with the computing power advantage of high-end ECUs (which can efficiently process high-frequency transmitted data), there is no need to worry about computing power overload caused by excessively high transmission frequencies. At the same time, fast convergence algorithms can quickly iterate and calculate based on high-frequency data to output optimized power parameters.

[0045] The correlation requirements for each parameter in this scenario are further refined to ensure coordinated matching of all aspects of the strategy. The complexity of the operating conditions is negatively correlated with the monitoring window size and positively correlated with the adjustment trigger frequency: urban congestion is a high-level complexity scenario, therefore the monitoring window is reduced (from the basic 10 seconds to 8 seconds), and the adjustment trigger frequency is increased (evaluating whether the trigger conditions are met every 8 seconds, far higher than the 15 seconds / evaluation in low-speed scenarios). ECU computing power is positively correlated with data transmission frequency: high-end ECUs' multi-channel parallel processing capabilities support high-frequency transmission of 18Hz; if the ECU computing power is reduced to mid-range, the transmission frequency will be simultaneously reduced to 12Hz-15Hz to avoid untimely data processing.

[0046] Supported by high-frequency data, the fast-convergence algorithm sets the number of iterations for each adjustment to 8 (within the mid-to-high range of 3-15 adjustments), enabling rapid convergence to the optimal parameters while avoiding response delays caused by excessive iteration. A fast-response sensor (≤0.1 seconds) accurately captures instantaneous data, providing a reliable data source for the 18Hz high-frequency transmission. If the sensor response speed drops to a medium speed (≤0.3 seconds), the transmission frequency will be adjusted to 12Hz-16Hz to ensure that the transmitted data matches the sensor's acquisition capabilities. Through the above parameter settings and associated logic, a closed-loop management system of "high-frequency acquisition - fast transmission - timely adjustment" is achieved in urban congestion scenarios. This satisfies the real-time requirements for range optimization in this scenario while leveraging the synergy of hardware computing power and algorithm characteristics to ensure a balance between strategy execution efficiency and driving safety.

[0047] Based on the dual requirements of accurate range optimization and timely data processing, the logic for setting the monitoring window size, number of dynamic adjustments, and data transmission frequency was planned. The initial benchmarks, threshold ranges, and core related factors for each parameter were clearly defined to ensure scientific and reasonable parameter settings. The initial benchmark for the monitoring window size was set to 10 seconds, with the core correlation being the complexity of the tire pressure and temperature feature dimensions. High complexity is defined when the feature dimensions include tire pressure values, temperature values, tire pressure change rate, and temperature change rate; low complexity is defined when only tire pressure and temperature values ​​are included. The upper and lower limits for the number of dynamic adjustments were set to a lower limit of 3 and an upper limit of 15, with the core correlation being the scale of the driving time-series data. Data volumes ≤1000 are considered small-scale, and ≥5000 are considered large-scale. The data transmission frequency was set to an adaptation range of 5Hz to 20Hz, with the core correlation being the sensor response characteristics and ECU computing resources.

[0048] For example, when the tire pressure and temperature feature dimension is highly complex, the amount of driving time-series data is 3000 (medium scale), the sensor has a medium-speed response, and the ECU has medium-level computing power, the initial baseline of the monitoring window is maintained at 10 seconds, the number of dynamic adjustments is set to 8, and the data transmission frequency is set to 12Hz. If the feature dimension becomes low complexity, the initial baseline of the monitoring window is adjusted to 15 seconds; if the amount of time-series data increases to 6000 (large scale), the upper limit of the number of dynamic adjustments is increased to 15 according to the rules; if the ECU has high computing power, the data transmission frequency can be increased to 18Hz to ensure a balance between data processing timeliness and range optimization accuracy.

[0049] Based on the real-time changes in tire pressure and temperature data, the dynamic switching requirements of driving conditions, and the ECU's computational load balancing requirements, dynamic optimization rules were formulated for monitoring window size, dynamic adjustment frequency, and data transmission frequency to achieve precise adaptation of parameters to actual operating conditions. The dynamic adaptation rule for monitoring window size is as follows: when the tire pressure and temperature feature dimension has high complexity, the window is reduced by 20%; when it has low complexity, the window is expanded by 30%. For example, the initial window is 10 seconds, adjusted to 8 seconds in high-complexity scenarios, and adjusted to 13 seconds in low-complexity scenarios, ensuring more intensive data sampling in complex scenarios and reducing processing load in simple scenarios.

[0050] The dynamic adjustment frequency is increased and decreased in a tiered manner as follows: for every 1,000 additional driving time-series data entries, the number of adjustments increases by 2; for every 1,000 fewer entries, the number of adjustments decreases by 2, with a minimum of 3 and a maximum of 15 adjustments. For example, when the data volume increases from 2,000 to 3,000 entries, the number of adjustments increases from 6 to 8; when the data volume decreases from 4,000 to 2,000 entries, the number of adjustments decreases from 10 to 6, adapting to the different processing requirements caused by changes in data volume.

[0051] The real-time transmission frequency matching rule is as follows: for every upgrade in sensor response speed, the transmission frequency increases by 4Hz; for every reduction in ECU computing power, the transmission frequency decreases by 3Hz. For example, if a sensor upgrades from medium-speed to fast-speed response, the transmission frequency increases from 12Hz to 16Hz; if an ECU reduces its computing power from high-speed to medium-speed, the transmission frequency decreases from 18Hz to 15Hz. This ensures that the transmission frequency matches the sensor's response capability and the ECU's processing capability, avoiding data accumulation or resource waste.

[0052] The core directions, parameter setting standards, and optimization rules of the above strategies are comprehensively integrated to form a structured implementation guideline that includes strategy adaptation conditions, monitoring window configuration specifications, dynamic adjustment processes, and data transmission frequency requirements, providing clear guidance for actual implementation. The strategy adaptation conditions clearly define the strategy types corresponding to different combinations of operating condition complexity, ECU computing power, algorithm characteristics, and sensor response characteristics. For example, "high-level operating condition complexity + high-end ECU computing power + fast convergence algorithm + fast sensor response" corresponds to a high-frequency dynamic adjustment strategy. The monitoring window configuration specifications detail the initial window size, adjustment range, and adaptation scenarios for different feature dimension complexities. For example, for low-complexity feature dimensions, the initial window is 15 seconds with an adjustment range of ±3 seconds, suitable for highway constant speed scenarios.

[0053] The dynamic adjustment process clearly defines the conditions for triggering adjustments, parameter calculations, and the entire process of execution feedback. For example, when the tire pressure change is ≥0.05 bar, the adjustment process is triggered, the number of adjustments is calculated based on the data volume, and the adjustment effect is fed back to the system after execution. The data transmission frequency requirements clearly define the frequency range and adjustment logic under different sensor response speeds and ECU computing power combinations. For example, a fast-response sensor paired with a high-performance ECU has a transmission frequency range of 16Hz to 20Hz, dynamically fine-tuned according to the complexity of operating conditions.

[0054] For example, the implementation details for urban congestion scenarios specify that the adaptation conditions are: high-level operating complexity, high-end ECU computing power, fast convergence algorithm, and fast sensor response; the initial size of the monitoring window is 8 seconds, and this size is maintained when the feature dimension remains unchanged; the number of dynamic adjustments is initially 8 times, and increases or decreases by 2 times for every 1,000 or 1,000 data entries; the transmission frequency is 18Hz, and it remains stable when the sensor response speed does not change, ensuring that the strategy execution is systematic, precise, and controllable.

[0055] S105 splits the dataset according to the target range management strategy, forming control batches containing tire pressure and temperature characteristic data, rolling resistance coefficient estimation data, sensor raw data, and energy consumption optimization label information. Data is transmitted in an orderly manner based on the monitoring window size and the number of dynamic adjustments. Data of the same type and consistent with the energy consumption optimization are synchronously imported into the ECU processing unit through a parallel processing mechanism.

[0056] In one implementation, a dataset splitting technique is used to process a standardized range management dataset according to the target range management strategy, generating management batches containing tire pressure and temperature characteristic data, rolling resistance coefficient estimation data, raw sensor data, and energy consumption optimization label information. A strategy-matching-based dataset splitting technique is employed, guided by the target range management strategy, to classify and split the standardized range management dataset, generating independent management batches containing tire pressure and temperature characteristic data, rolling resistance coefficient estimation data, raw sensor data, and energy consumption optimization label information, ensuring that each batch of data is specifically adapted to subsequent processing needs.

[0057] The splitting process is based on data type and its relevance to range optimization, dividing batches according to strategy requirements. For example, when the target range management strategy is a high-frequency dynamic adjustment strategy for urban congestion scenarios, the standardized dataset is split into multiple small control batches. Each batch contains tire pressure and temperature characteristic data within 1 minute (e.g., a change sequence from 2.5 bar to 2.45 bar), corresponding rolling resistance coefficient estimation data (e.g., dynamic values ​​from 0.008 to 0.009), raw sensor electrical signal data, and energy consumption optimization labels for "high-frequency adjustment." If the strategy is a precise optimization strategy for highway constant speed scenarios, then large control batches are generated, with each batch containing a complete data sequence within 5 minutes, ensuring data continuity and integrity to meet the needs of precise iterative optimization.

[0058] The generated control batches are systematically integrated with the preset monitoring window size standard, dynamic adjustment frequency threshold and data transmission timing rules. By establishing an association mapping model, the transmission parameter requirements corresponding to each control batch are clarified, so as to achieve accurate matching between control batches and transmission needs.

[0059] The association mapping model takes batch data volume, data update frequency, and data importance as input, and outputs corresponding monitoring window adaptation standards, adjustment frequency thresholds, and transmission timing rules. For example, a certain control batch contains 2 minutes of high-frequency data in an urban congestion scenario, with a data volume of 2000 records and an update frequency of 10Hz. The association mapping model determines that its suitable monitoring window size is 8 seconds, the dynamic adjustment frequency threshold is 8 times, and the transmission timing rule is "core data first, then auxiliary data." Another control batch contains 5 minutes of low-frequency data on highways, with a data volume of 3000 records and an update frequency of 5Hz. The model matches its monitoring window size to 15 seconds, the dynamic adjustment frequency threshold to 5 times, and the transmission timing rule to "continuous transmission in chronological order," ensuring accurate adaptation between batch data and transmission resources.

[0060] Based on the monitoring window size and the number of dynamic adjustments, data transmission parameters are set, with controlled batches as the basic transmission unit. Transmission timing rules serve as the execution standard, and transmission categories are divided according to data association attributes, enabling refined control over the transmission order, frequency, and priority. The transmission order is divided into core data and auxiliary data categories based on data association attributes. Core data, including tire pressure and temperature characteristic data and rolling resistance coefficient estimation data, is transmitted first; auxiliary data, including raw sensor data and energy consumption optimization label information, is transmitted later. The transmission frequency is linked to the monitoring window size. When the monitoring window is 8 seconds, the transmission frequency is set to one controlled batch every 8 seconds; when the monitoring window is 15 seconds, the transmission frequency is adjusted to one batch every 15 seconds. The transmission priority is set according to the data's impact on range optimization, with tire pressure and temperature characteristic data having the highest priority, followed by rolling resistance coefficient estimation data, and raw sensor data and energy consumption optimization label information having the lowest priority. For example, in urban congestion scenarios, control batches are transmitted in the order of "tire pressure and temperature characteristic data - rolling resistance coefficient estimation data - sensor raw data - energy consumption optimization tag information", with one batch transmitted every 8 seconds to ensure that core data is quickly delivered to the ECU and meet the high-frequency adjustment requirements; in highway scenarios, batches are transmitted continuously in chronological order, with one batch transmitted every 15 seconds to balance transmission efficiency and resource consumption.

[0061] Based on the correlation strength between data and energy consumption optimization, and combined with the aggregation requirements for similar data, the controlled batch data is classified. Aggregation rules, parallel transmission channels, and ECU import interfaces for highly correlated data of the same type are clarified. Through a multi-channel parallel processing mechanism, data is synchronously imported into the ECU processing unit, improving data processing efficiency. Data is categorized into four main types: tire pressure and temperature, rolling resistance coefficient, sensor raw data, and tag information. The aggregation rules for similar data types are set as "timestamp alignment and consistent data dimensions." Parallel transmission channels are configured according to data type: tire pressure and temperature data uses channel 1, rolling resistance coefficient data uses channel 2, sensor raw data uses channel 3, and tag information data uses channel 4. Each channel transmits independently without interference. The ECU import interface corresponds one-to-one with the transmission channels: channel 1 corresponds to the ECU's core data interface, and channels 2 to 4 correspond to ordinary data interfaces. For example, in the management batch of urban congestion scenarios, tire pressure and temperature characteristic data are aggregated into a continuous time-stamped sequence and transmitted to the ECU core interface through channel 1; rolling resistance coefficient estimation data are aggregated according to the same time stamp and transmitted synchronously through channel 2; sensor raw data and tag information data are transmitted in parallel through channels 3 and 4 respectively. The four types of data arrive at the ECU at the same time and are synchronously imported into the processing unit, with the transmission delay controlled within 0.2 seconds, which greatly improves data processing efficiency.

[0062] S106 learns the mapping relationship between tire pressure and temperature characteristics, rolling resistance coefficient and range management strategy through a multimodal feature fusion algorithm. It optimizes power control parameters according to the weighted fusion logic of tire pressure data, temperature data, road condition information and load parameters. Combined with tire model, vehicle power configuration and driving scenario, it dynamically adapts motor output power and brake recovery strategy parameters to generate target speed recommendation instructions.

[0063] In one implementation, based on the learning logic of a multimodal feature fusion algorithm and combined with the adaptation requirements of range management strategies, a mapping and correlation standard for tire pressure and temperature features, rolling resistance coefficient, and strategy objectives is established. Multi-source data on tire pressure, temperature, road conditions, and load are processed for feature weight classification, dimensional homogeneity classification, and correlation strength anchoring, ultimately forming a refined feature fusion list containing feature importance identifiers, data dimension labels, and strategy mapping coefficients. Feature weight classification is divided into three levels based on the degree of data impact on range optimization: Level 1 represents core impact features, Level 2 represents important impact features, and Level 3 represents auxiliary impact features. For example, in urban congestion scenarios, tire pressure features have Level 1 weight, temperature features have Level 1 weight, road conditions features have Level 2 weight, and load features have Level 2 weight; in highway scenarios, tire pressure features have Level 1 weight, rolling resistance coefficient has Level 1 weight, road conditions features have Level 3 weight, and load features have Level 3 weight. Dimension homogeneity classification divides data into mechanical and environmental categories according to physical attributes; tire pressure, load, and rolling resistance coefficient are classified as mechanical, while temperature and road conditions are classified as environmental. The correlation strength is determined by calculating the correlation coefficient between the data and the remaining energy consumption. A correlation coefficient ≥ 0.8 indicates a strong correlation, ≥ 0.5 and < 0.8 indicates a moderate correlation, and < 0.5 indicates a weak correlation.

[0064] The generated refined feature fusion list clearly identifies the weight level of each data point by feature importance markers, labels the data dimensions to indicate their categories, and strategy mapping coefficients quantify the correlation between the data and the range strategy. For example, in urban congestion scenarios, the tire pressure feature is identified as Level 1 in importance, labeled as mechanical, with a strategy mapping coefficient of 0.85; the road condition feature is identified as Level 2 in importance, labeled as environmental, with a strategy mapping coefficient of 0.62, providing a clear basis for subsequent parameter optimization.

[0065] Based on the consistency threshold of the correlation between data and range optimization, a smart adaptation mechanism for power parameter optimization is constructed by integrating weighted fusion rules for fusion parameters with the coordination requirements of vehicle control. This mechanism clarifies the weighted fusion threshold for multi-source data, the parameter adjustment timing calibration protocol, and formulates scenario-specific differentiated optimization specifications to ensure precise matching between power parameter optimization and vehicle control needs. The correlation consistency threshold is set to 0.7. When the correlation between multi-source data and range optimization is ≥0.7, weighted fusion calculation is initiated. The weighted fusion threshold is set according to the scenario: 0.65 for urban congestion scenarios, 0.75 for highway scenarios, and 0.70 for mountain slope scenarios. The parameter adjustment timing calibration protocol clarifies the time synchronization rules for data fusion and parameter adjustment, setting the calibration period to 0.5 seconds to ensure real-time synchronization between data fusion results and parameter adjustment actions.

[0066] The scenario-based and differentiated optimization specifications are designed with specific optimization logic for different driving scenarios. For example, in urban congestion scenarios, the optimization specifications focus on the rapid adjustment of motor output power, with a response delay of no more than 0.3 seconds; in highway scenarios, the specifications focus on the precise adaptation of regenerative braking power, with an error controlled within 5%; in mountainous slope scenarios, the specifications focus on the coordinated adjustment of motor power and regenerative braking strategy to ensure sufficient power uphill and efficient energy recovery downhill.

[0067] By combining a refined feature fusion list with differentiated optimization specifications, a three-in-one power control optimization architecture integrating feature learning, parameter optimization, and scenario adaptation is constructed. A tire-vehicle collaborative adaptation and verification module is embedded, and a dynamic parameter adjustment mechanism and scenario switching adaptation rules are set to achieve deep integration of feature learning, parameter optimization, and scenario adaptation. The feature learning layer receives data from the refined feature fusion list and learns the correlation patterns and mapping relationships between data through a multimodal feature fusion algorithm. Based on the learning results, the parameter optimization layer adjusts core parameters such as motor output power and regenerative braking strategy according to differentiated optimization specifications. The scenario adaptation layer adapts the optimized parameters to the current driving scenario to ensure that the parameters meet actual driving needs.

[0068] A tire-vehicle collaborative adaptation and verification module is embedded in the core architecture to verify the optimized parameters and determine whether they meet the tire's operating characteristics and the vehicle's powertrain safety thresholds. A dynamic parameter adjustment mechanism sets adjustment step sizes and trigger conditions: the motor output power adjustment step size is 5kW, and the regenerative braking power adjustment step size is 3kW. Parameter adjustment is triggered when tire pressure changes by ≥0.05 bar or temperature changes by ≥3℃. Scene switching adaptation rules clearly define the parameter transition logic during scene transitions. For example, when switching from an urban congestion scenario to a highway scenario, parameters are gradually adjusted to the target value at a rate of 0.2 seconds per level to avoid sudden parameter changes affecting driving stability.

[0069] The system monitors the parameter adaptation accuracy, strategy response speed, and range improvement effect in real time during the optimization process. It introduces a dynamic feedback mechanism for driving scenarios and continuously optimizes the control process by dynamically adjusting parameter weights, optimizing strategy adaptation logic, and vehicle speed recommendation thresholds, thereby generating accurate power control parameters and target vehicle speed recommendation results data.

[0070] Parameter adaptation accuracy monitoring is achieved by comparing the deviation between the optimized parameters and actual driving requirements. The deviation threshold is set at 8%. When the deviation exceeds the threshold, weight adjustment is initiated. Strategy response speed monitoring records the time from data input to parameter adjustment completion. The response speed threshold is 0.3 seconds in urban congestion scenarios and 0.5 seconds in highway scenarios. If the timeout occurs, the strategy adaptation logic is optimized. Range improvement is achieved by calculating the increase in range in real time. When the increase is less than 30% of the expected value, the recommended vehicle speed threshold is adjusted.

[0071] The dynamic feedback mechanism for driving scenarios collects real-time data on the current scenario and dynamically adjusts relevant parameters. For example, when a vehicle transitions from an urban congestion scenario to a highway scenario, the feedback mechanism detects the change in road conditions and adjusts the weighting of tire pressure characteristics from 0.35 to 0.45, increases the weighting of rolling resistance coefficient from 0.25 to 0.35, switches the optimization strategy adaptation logic from "rapid response" to "precise stability," and adjusts the recommended vehicle speed threshold from 50km / h to 90km / h. Through dynamic feedback adjustments, the mechanism ultimately generates power control parameters adapted to the current scenario, such as stabilizing the motor output power at 45kW, setting the regenerative braking power at 30kW, and recommending a target vehicle speed of 90km / h, achieving a balance between maximizing range and driving safety.

[0072] like Figure 2 As shown, a new energy vehicle range management system based on tire pressure-temperature self-sensing intelligent tires is disclosed. The system includes: The multi-source data acquisition module 201 is used to receive real-time tire pressure monitoring data and temperature distribution data collected by distributed sensors composed of conductive wet-mixed rubber compounds, as well as vehicle load parameters, navigation road condition information, motor output power records, brake recovery strategy parameters, and raw sensor data transmitted by tire-embedded RFID chips / wireless modules, to complete the core data acquisition for range management. The threshold and weight setting module 202 is used to set the optimal tire pressure range, temperature warning threshold and rolling resistance coefficient calculation weight based on the goal of maximizing the range of new energy vehicles, the safety threshold of the power system and the working characteristics of the tires, and to provide the benchmark parameters for range optimization. The data preprocessing and dataset creation module 203 is used to perform sensor signal noise reduction, RFID / wireless module transmission data calibration, time series data alignment and tire pressure-temperature-rolling resistance correlation feature extraction on multi-source core sensor and vehicle-related data, create a standardized range management dataset, read key information of the dataset and sort it according to the degree of correlation. The range coordination management strategy formulation module 204 is used to determine the range coordination management strategy by combining the driving condition complexity of the dataset, the computing power resources of the vehicle ECU, the characteristics of energy consumption optimization algorithms and the response characteristics of distributed sensors, and to set the monitoring window size, the number of dynamic adjustments and match the sensor data transmission frequency according to relevant parameters. The data splitting and parallel transmission module 205 is used to split the standardized range control dataset according to the target range management strategy, forming control batches containing various feature data, estimated data and tag information. The data is transmitted in an orderly manner based on the monitoring window size and the number of dynamic adjustments. The parallel processing mechanism synchronously imports the same type of highly correlated data into the ECU processing unit. The power parameter optimization and vehicle speed recommendation module 206 is used to learn the mapping relationship between tire pressure and temperature characteristics, rolling resistance coefficient and range management strategy through multimodal feature fusion algorithm, optimize power control parameters according to weighted fusion logic, and dynamically adapt motor output power and regenerative braking strategy parameters in combination with tire model, vehicle power configuration and driving scenario to generate target vehicle speed recommendation instructions.

[0073] A computing device includes a memory for storing computer program instructions and a processor for executing the computer program instructions, wherein when the computer program instructions are executed by the processor, the device is triggered to execute any of the new energy vehicle range management methods based on tire pressure-temperature self-sensing smart tires.

[0074] The methods and / or embodiments in this application can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowchart. When the computer program is executed by a processing unit, it performs the functions defined in the methods of this application.

[0075] It should be noted that the computer-readable medium described in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0076] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0077] It will be apparent to those skilled in the art that this application is not limited to the details of the exemplary embodiments described above, and that this application can be implemented in other specific forms without departing from the spirit or essential characteristics of this application. Therefore, the embodiments should be regarded as exemplary and non-limiting in all respects, and the scope of this application is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within this application.

Claims

1. A method for range management of new energy vehicles based on tire pressure-temperature self-sensing intelligent tires, characterized in that, include: Collect multi-source core sensor data and vehicle-related data, including real-time tire pressure monitoring data and temperature distribution data collected by distributed sensors composed of conductive wet-mixed rubber compounds, vehicle load parameters, navigation road condition information, motor output power records, brake recovery strategy parameters, and raw sensor data transmitted by tire-embedded RFID chips / wireless modules. The optimal tire pressure range, temperature warning threshold, and rolling resistance coefficient calculation weights are set based on the goal of maximizing the range of new energy vehicles, the safety threshold of the power system, and the tire working characteristics. The data from multi-source core sensors and the vehicle are processed to perform sensor signal noise reduction, RFID / wireless module transmission data calibration, time-series data alignment, tire pressure-temperature-rolling resistance correlation feature extraction, and to create a standardized range management dataset. The dataset is read to determine the tire pressure and temperature feature dimensions, driving time-series data volume, and parameter mode type information, and sorted according to the degree of correlation between the data and range energy consumption and tire working status. By combining the driving condition complexity of the dataset, the computing power resources of the vehicle ECU, the characteristics of energy consumption optimization algorithms and the response characteristics of distributed sensors, a range coordination management strategy is determined. The monitoring window size and the number of dynamic adjustments are set according to the tire pressure and temperature characteristics and the amount of driving time series data, and the sensor data transmission frequency is matched. Data sets are split according to the target range management strategy to form control batches containing tire pressure and temperature characteristic data, rolling resistance coefficient estimation data, sensor raw data and energy consumption optimization label information. Data is transmitted in an orderly manner based on the monitoring window size and the number of dynamic adjustments. Data of the same type and consistent with the energy consumption optimization are synchronously imported into the ECU processing unit through a parallel processing mechanism. By learning the mapping relationship between tire pressure and temperature characteristics, rolling resistance coefficient and range management strategy through a multimodal feature fusion algorithm, the power control parameters are optimized according to the weighted fusion logic of tire pressure data, temperature data, road condition information and load parameters. Combined with tire model, vehicle power configuration and driving scenario, the motor output power and braking recovery strategy parameters are dynamically adapted to generate target speed recommendation instructions.

2. The method for managing the range of new energy vehicles based on tire pressure-temperature self-sensing intelligent tires according to claim 1, characterized in that, Based on the goal of maximizing the driving range of new energy vehicles, the safety threshold of the power system, and the tire working characteristics, the optimal tire pressure range, temperature warning threshold, and rolling resistance coefficient calculation weights are set, including: Based on the goal of maximizing the range of new energy vehicles, the safety threshold of the power system, and the working characteristics of tires, the core parameters of tire pressure control, the boundary conditions of temperature warning, and the weight information of rolling resistance coefficient calculation are integrated to clarify the setting range and correlation requirements of each parameter. The parameter setting logic is designed based on the synergistic requirements of range optimization and tire safety, and the setting standards of core parameters and related parameters are clarified. The core parameters include the optimal tire pressure range, temperature warning threshold, and rolling resistance coefficient calculation weight, while the related parameters include tire model adaptation parameters and power system response threshold information. Based on the range stability requirements under different driving conditions, parameter optimization rules are set up, including dynamic fine-tuning of tire pressure range, graded warning of temperature threshold, and real-time adaptation of rolling resistance coefficient weight, to ensure a balance between range optimization and driving safety. The system processes parameter setting requirements, range and safety coordination needs, and parameter optimization rules to generate basic range management data that includes parameter types, setting specifications, correlation logic, and optimization strategies.

3. The method for managing the range of new energy vehicles based on tire pressure-temperature self-sensing intelligent tires according to claim 1, characterized in that, By considering the complexity of driving conditions in the dataset, the computing power resources of the onboard ECU, the characteristics of energy consumption optimization algorithms, and the response characteristics of distributed sensors, a range coordination management strategy is determined. Based on the tire pressure and temperature characteristics and the amount of driving time-series data, the monitoring window size and the number of dynamic adjustments are set, and the sensor data transmission frequency is matched, including: Based on the complexity of driving conditions, computing power resources of vehicle ECU, characteristics of energy consumption optimization algorithms and response characteristics of distributed sensors, the core direction of range cooperative management strategy, the logic of monitoring window setting, dynamic adjustment of trigger conditions and data transmission frequency matching principle are integrated to clarify the strategy adaptation scenarios and the requirements of each parameter association. Based on the requirements of accuracy in range optimization and timeliness in data processing, the parameter setting logic is planned, clarifying the initial benchmark for the size of the monitoring window, the upper and lower thresholds for the number of dynamic adjustments, the adaptability range of data transmission frequency, and the complexity of the core associated tire pressure and temperature feature dimensions and the scale of driving time series data. Based on the real-time variation characteristics of tire pressure and temperature data, the dynamic switching requirements of driving conditions, and the ECU computing power load balancing requirements, optimization rules are set to dynamically adapt the monitoring window size to the tire pressure and temperature characteristic dimensions, increase or decrease the number of adjustments in a stepwise manner according to the amount of driving time-series data, and match the transmission frequency with the sensor response characteristics in real time. The core strategy direction, parameter setting standards, and optimization rules are integrated and processed to generate detailed implementation rules for endurance collaborative management, which include strategy adaptation conditions, monitoring window configuration specifications, dynamic adjustment processes, and data transmission frequency requirements.

4. The method for managing the range of new energy vehicles based on tire pressure-temperature self-sensing intelligent tires according to claim 3, characterized in that, Data sets are split according to the target range management strategy, forming control batches containing tire pressure and temperature characteristic data, rolling resistance coefficient estimation data, raw sensor data, and energy consumption optimization label information. Data is transmitted in an orderly manner based on the monitoring window size and the number of dynamic adjustments. Data of the same type and consistent with energy consumption optimization are synchronously imported into the ECU processing unit through a parallel processing mechanism, including: The standardized range control dataset is processed according to the target range management strategy using dataset splitting technology to generate control batches containing tire pressure and temperature characteristic data, rolling resistance coefficient estimation data, sensor raw data and energy consumption optimization label information. Data integration and processing are performed on the control batch and monitoring window size standards, dynamic adjustment frequency thresholds and data transmission timing rules to establish a precise matching relationship between control batches and transmission requirements; Based on the monitoring window size and the number of dynamic adjustments, data transmission parameters are set, with the controlled batch as the transmission unit, the transmission timing rules as the execution standard, and the data association attributes as the classification basis, so as to achieve precise control over the data transmission order, transmission frequency, and transmission priority. Based on the correlation strength between data and energy consumption optimization and the requirements for aggregating similar data, the batch data under control is classified and adapted for parallel processing. The aggregation rules, parallel transmission channels and ECU import interfaces for similar highly correlated data are clarified, and the data is synchronously imported into the ECU processing unit through a parallel processing mechanism.

5. The method for managing the range of new energy vehicles based on tire pressure-temperature self-sensing intelligent tires according to claim 4, characterized in that, The mapping relationship between tire pressure and temperature characteristics, rolling resistance coefficient, and range management strategy is learned through a multimodal feature fusion algorithm. Power control parameters are optimized using a weighted fusion logic based on tire pressure data, temperature data, road condition information, and load parameters. Combined with tire model, vehicle power configuration, and driving scenario, motor output power and regenerative braking strategy parameters are dynamically adapted to generate target speed recommendation instructions, including: Based on the learning logic of the multimodal feature fusion algorithm and the adaptation requirements of the range management strategy, the mapping association standard of tire pressure and temperature features, rolling resistance coefficient and strategy target is coupled. Feature weight classification, dimension homogeneity classification and association strength anchoring are performed on multi-source data of tire pressure / temperature / road condition / load, and a refined feature fusion list including feature importance identifier, data dimension label and strategy mapping coefficient is generated. Based on the consistency threshold of the correlation between data and range optimization, the weighted fusion rules of the fusion parameters and the coordination requirements of vehicle control are integrated to design an intelligent adaptation mechanism for power parameter optimization, clarify the weighted fusion threshold of multi-source data and the parameter adjustment timing calibration protocol, and formulate scenario-based differentiated optimization specifications; By combining a refined feature fusion list and differentiated optimization specifications, a three-in-one power control optimization architecture integrating feature learning, parameter optimization, and scenario adaptation is built. A tire-vehicle collaborative adaptation verification module is embedded, and a dynamic parameter adjustment mechanism and scenario switching adaptation rules are set. The system monitors the parameter adaptation accuracy, strategy response speed, and range improvement effect in real time during the optimization process. It introduces a dynamic feedback mechanism for driving scenarios and optimizes the control process by dynamically adjusting parameter weights, optimizing strategy adaptation logic, and optimizing vehicle speed recommendation thresholds to generate power control parameters and target vehicle speed recommendation results data.

6. A new energy vehicle range management system based on a tire pressure-temperature self-sensing intelligent tire, characterized in that, The system is used to execute executable instructions to perform the new energy vehicle range management method based on tire pressure-temperature self-sensing intelligent tires as described in any one of claims 1 to 5.

7. An electronic device, characterized in that, include: First processor; and memory for storing executable instructions of the first processor; The first processor is configured to execute the new energy vehicle range management method based on tire pressure-temperature self-sensing intelligent tires as described in any one of claims 1 to 5 by executing the executable instructions.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the second processor, it implements the new energy vehicle range management method based on tire pressure-temperature self-sensing intelligent tires as described in any one of claims 1 to 5.

Images