Two-channel result fusion whole vehicle mass estimation method and device

Abstract

The invention relates to the technical field of vehicle auxiliary driving, in particular to a two-channel result fusion whole vehicle mass estimation method and device, and the method comprises the steps: collecting at least one key parameter of a vehicle, so as to judge whether the vehicle meets a preset vehicle mass starting condition or not; if the preset vehicle mass starting condition is met, entering a whole vehicle mass estimation mode, and calculating a first vehicle mass by using a longitudinal dynamic model and calculating a second vehicle mass by using a plurality of parameters under a stable loading working condition; and fusing the first vehicle mass and the second vehicle mass based on the corresponding weight so as to obtain a final mass estimation value of the vehicle according to a fusion result. Therefore, the problem that the vehicle mass estimation precision cannot be effectively guaranteed due to the fact that an existing dual-channel weight estimation method is poor in adaptability, high in algorithm deployment difficulty and high in calculation power requirement due to the fact that related technologies are limited by a specific scene and cannot avoid interference caused by intervention of a nonlinear scene and a vehicle control system is solved.

Description

Technical Field

[0001] This application relates to the field of vehicle driver assistance technology, and in particular to a dual-channel result fusion method and apparatus for estimating vehicle mass. Background Technology

[0002] In the current field of vehicle driver assistance technology, the estimation of vehicle mass often lacks consideration of vehicle control systems, such as anti-lock braking systems, electronic stability control systems, and traction control systems. The intervention of these control systems can have an adverse effect on the estimation of vehicle mass.

[0003] In related technologies, vehicle mass estimation methods can be divided into two categories: dynamics-based methods and machine learning-based methods. Among dynamics-based methods, least squares and Kalman filtering are more commonly used.

[0004] However, among related technologies, recursive least squares (RSS) suffers from bias due to the influence of long-term accumulated old data on the current estimate, and its system time-varying performance is poor. While least squares with a forgetting factor improves the adaptability of time-varying systems by introducing a forgetting factor, it still suffers from the same problems as RSS, such as poor numerical stability and the possibility of the covariance matrix losing positive definiteness due to rounding errors during the update process, leading to algorithm collapse. Standard Kalman filtering is based on linear assumptions, and direct application is prone to errors, while vehicle longitudinal dynamics have nonlinear characteristics. Extended Kalman filtering and unscented Kalman filtering can handle nonlinear problems, but... Expanded Kalman filtering relies on first-order Taylor expansion approximation, which is insufficient in accuracy under strongly nonlinear conditions. Unscented Kalman filtering has high computational complexity and approximation errors in high-dimensional systems, increasing the difficulty of engineering implementation. Among machine learning-based methods, existing studies are mostly limited to scenarios with small changes in vehicle speed and road slope, and have not fully verified the estimation effect under different tire-road friction coefficient conditions. In addition, the comprehensiveness of the dataset and the quality of neural network training directly affect the performance of machine learning methods. Due to the weak theoretical interpretability of neural network models, unpredictable estimation biases may occur. The above problems urgently need to be improved. Summary of the Invention

[0005] This application provides a dual-channel result fusion method and apparatus for vehicle mass estimation, which solves the problems of poor adaptability, high algorithm deployment difficulty and high computing power requirements caused by the interference of nonlinear scenarios and the intervention of the vehicle's own control system due to the limitation of related technologies in specific scenarios. As a result, the existing dual-channel weight estimation methods have high adaptability, high algorithm deployment difficulty and high computing power requirements, which in turn cannot effectively guarantee the accuracy of vehicle mass estimation.

[0006] The first aspect of this application provides a dual-channel result fusion method for vehicle mass estimation, comprising the following steps: collecting at least one key parameter of the vehicle to determine whether the vehicle meets a preset vehicle mass activation condition; if the preset vehicle mass activation condition is met, entering a vehicle mass estimation mode, calculating a first vehicle mass using a longitudinal dynamics model and calculating a second vehicle mass using multiple parameters under a stable loading condition; fusing the first vehicle mass and the second vehicle mass based on corresponding weights to obtain a final mass estimate of the vehicle based on the fusion result.

[0007] Through the aforementioned technical means, this embodiment of the application can acquire key parameters such as wheel speed, torque, and acceleration through sensor signal acquisition; further, it performs initial discrimination of vehicle mass activation conditions, checks basic conditions such as vehicle speed, yaw rate, and sensor effectiveness, and after the initial discrimination conditions are met, it simultaneously starts the branch processes of the model channel and the differential channel to calculate the first vehicle mass using the longitudinal dynamic model and the second vehicle mass using multiple parameters under stable loading conditions, respectively; finally, it integrates the dual-channel results, and outputs the final vehicle mass estimate through dynamic filtering and weighted fusion, thereby improving the estimation stability of the algorithm in complex environments and its adaptability to changes in noise statistical characteristics, and thus improving the estimation accuracy of vehicle mass.

[0008] Optionally, in one embodiment of this application, determining whether the vehicle meets the preset vehicle mass activation conditions includes: collecting at least one key parameter of the vehicle, detecting whether the vehicle speed is within a preset minimum and maximum speed range, detecting whether the vehicle yaw rate is within a preset maximum yaw rate range, detecting whether the axle drive torque is valid, detecting whether the wheel speed signal is valid, detecting whether the engine speed signal is valid, and detecting whether the vehicle's four tire pressure signals are normal; if it is detected that the vehicle speed is within the preset minimum and maximum speed range, the vehicle yaw rate is within the preset maximum yaw rate range, the vehicle's four tire pressure signals are normal, and the axle drive torque, the wheel speed signal, and the engine speed signal are all valid, then it is determined that the preset vehicle mass activation conditions are met.

[0009] Through the above-mentioned technical means, the embodiments of this application can perform coarse discrimination on key parameters such as vehicle speed, yaw rate, axle drive torque, wheel speed signal, engine speed signal, and four tire pressure signal. This can filter out scenarios where key parameters are abnormal or signals are invalid, avoid performing vehicle mass estimation when the initial conditions are not met, reduce invalid calculations, and provide a reliable initial judgment basis for whether to perform mass estimation later, thereby improving the effectiveness and accuracy of subsequent mass estimation.

[0010] Optionally, in one embodiment of this application, the step of calculating the first vehicle mass using a longitudinal dynamics model and the second vehicle mass using multiple parameters under a stable loading condition includes: detecting whether the longitudinal acceleration signal of the vehicle is valid; if the longitudinal acceleration signal is detected to be valid, calculating the first initial vehicle mass based on the longitudinal dynamics model; detecting whether there is no braking intervention during vehicle operation, detecting whether the vehicle acceleration is within a preset first maximum threshold range, detecting whether the rate of change of the drive shaft torque is within a preset second maximum threshold range, and detecting whether the rate of change of the transmission ratio is within a preset third maximum threshold range; if no braking intervention is detected and the values ​​are within the corresponding maximum threshold ranges, outputting the first vehicle mass based on the first initial mass.

[0011] Through the aforementioned technical means, this embodiment of the application can first ensure that the core parameters of the longitudinal dynamics model input meet the calculation premise by detecting the validity of the longitudinal acceleration signal, thus avoiding the deviation in the calculation of the first initial vehicle mass caused by invalid signals. Secondly, by simultaneously detecting no braking intervention (eliminating the interference of braking resistance on the driving force balance equation), acceleration within a first threshold (ensuring that acceleration fluctuations are within the linear range applicable to the model), and the change rate of drive shaft torque and the change rate of gearbox transmission ratio within the corresponding threshold (ensuring the stability of power transmission system parameters and avoiding driving force calculation errors caused by sudden changes in torque or transmission ratio), an ideal working condition with smooth loading is constructed. Finally, under this working condition, the first vehicle mass output based on the first initial mass not only ensures the reliability of the model input through signal validity verification, but also eliminates the influence of nonlinear interference factors such as braking and power fluctuations on the derivation of the dynamics equation through multi-parameter threshold screening, thereby significantly improving the accuracy and stability of vehicle mass calculation and making the calculation results more consistent with the actual vehicle mass state.

[0012] Optionally, in one embodiment of this application, the step of outputting the first vehicle mass based on the first initial mass includes: recording a calculated mass value when the first vehicle mass is between the vehicle's full load mass and minimum curb weight; and calculating the average value of the vehicle mass in the previous period when the number of calculated mass values ​​reaches a set number, so as to obtain the first vehicle mass.

[0013] Through the above-mentioned technical means, the embodiments of this application can filter valid calculated values ​​by limiting the first initial mass between the vehicle's full load mass and minimum curb weight. After the number of valid calculated values ​​reaches a set number, the average value in the previous period is taken as the first vehicle mass, thereby effectively filtering outlier values ​​that deviate from reality. At the same time, by using multi-value averaging to reduce the random error of a single calculation, the accuracy and stability of the vehicle mass calculation results are significantly improved, making them more consistent with the actual mass state of the vehicle.

[0014] Optionally, in one embodiment of this application, the formula for calculating the mass of the first vehicle is expressed as: , in, T w Indicates the wheel-end drive torque. r Indicates the rolling radius of the wheel. C d Indicates the air drag coefficient. A Indicates the windward area. v Indicates longitudinal vehicle speed. f Indicates the rolling resistance coefficient. α Indicates the road slope. δ This represents the rotational mass conversion factor. m Model This represents the vehicle mass calculated using the vehicle model calculation method. g It represents the acceleration due to gravity.

[0015] Optionally, in one embodiment of this application, the step of calculating the first vehicle mass using a longitudinal dynamics model and the second vehicle mass using multiple parameters under a stable loading condition includes: detecting whether the vehicle acceleration is less than a first preset threshold, detecting whether the axle torque change rate is less than a second preset threshold, and checking whether the vehicle braking is engaged; if the vehicle acceleration is less than the first preset threshold, the axle torque change rate is less than the second preset threshold, and the vehicle braking is not engaged, the vehicle is determined to be in a stable driving phase, and the second initial vehicle mass is calculated according to a preset differential mass calculation formula; detecting whether the vehicle acceleration is less than a third preset threshold, detecting whether the drive shaft torque change rate is less than a fourth preset threshold, and detecting whether the transmission ratio change rate is less than a fifth preset threshold; if the values ​​are all less than the corresponding preset thresholds, the second vehicle mass is output based on the second initial vehicle mass.

[0016] Through the aforementioned technical means, the embodiments of this application can achieve layer-by-layer optimization of the accuracy of vehicle mass calculation through phased multi-parameter threshold detection and progressive calculation. Firstly, by detecting that the vehicle acceleration is less than a first preset threshold, the axle torque change rate is less than a second preset threshold, and there is no braking intervention, a basic stable stage (small acceleration fluctuations, stable power output, and no braking interference) is selected. At this point, the second initial vehicle mass is solved based on a preset differential mass calculation formula, which reduces the interference of power and resistance imbalances under non-steady operating conditions on the calculation, ensuring the reliability of the initial value. Furthermore, by detecting that the acceleration is less than a second preset threshold, a more stable stage is selected. Strict third preset thresholds, torque change rate less than the fourth preset threshold, and transmission ratio change rate less than the fifth preset threshold further constrain the vehicle to be in a high-precision stable phase where the power transmission system parameters (torque, transmission ratio) are more stable. At this time, the second vehicle mass is output based on the second initial vehicle mass, which is equivalent to superimposing the low fluctuation constraint of the power transmission parameters on the basic stable conditions. From the derivation level, the influence of minor disturbances such as torque mutation and transmission ratio change on the mass calculation is eliminated. Finally, through the screening and calculation iteration of dual stable working conditions, the calculation accuracy of the second vehicle mass can be significantly improved, making it more consistent with the real mass of the vehicle under actual loading conditions.

[0017] Optionally, in one embodiment of this application, the formula for solving the second initial vehicle mass is expressed as: , in, Ft This represents the driving force of a vehicle during acceleration. Ft_delay This represents the driving force of a vehicle under stable driving conditions. Fw This represents the air resistance of a vehicle during acceleration. Fw_delay This represents the air resistance of a vehicle under stable driving conditions. ax This represents the longitudinal acceleration of a vehicle during acceleration. ax_delay This represents the longitudinal acceleration of a vehicle under stable driving conditions. δ This represents the rotational mass conversion factor. mDiff This represents the vehicle mass obtained through the differential calculation method.

[0018] A second aspect of this application provides a dual-channel result fusion vehicle mass estimation device, comprising: a judgment module, used to collect at least one key parameter of the vehicle to determine whether the vehicle meets a preset vehicle mass activation condition; a calculation module, used to enter a vehicle mass estimation mode if the preset vehicle mass activation condition is met, and calculate a first vehicle mass using a longitudinal dynamics model and a second vehicle mass using multiple parameters under a stable loading condition; and an estimation module, used to fuse the first vehicle mass and the second vehicle mass based on corresponding weights to obtain a final mass estimate of the vehicle based on the fusion result.

[0019] Through the aforementioned technical means, this embodiment of the application can acquire key parameters such as wheel speed, torque, and acceleration through sensor signal acquisition; further, it performs initial discrimination of vehicle mass activation conditions, checks basic conditions such as vehicle speed, yaw rate, and sensor effectiveness, and after the initial discrimination conditions are met, it simultaneously starts the branch processes of the model channel and the differential channel to calculate the first vehicle mass using the longitudinal dynamic model and the second vehicle mass using multiple parameters under stable loading conditions, respectively; finally, it integrates the dual-channel results, and outputs the final vehicle mass estimate through dynamic filtering and weighted fusion, thereby improving the estimation stability of the algorithm in complex environments and its adaptability to changes in noise statistical characteristics, and thus improving the estimation accuracy of vehicle mass.

[0020] Optionally, in one embodiment of this application, the judgment module includes: a first detection unit, used to collect at least one key parameter of the vehicle, detect whether the vehicle speed is within a preset minimum and maximum speed range, detect whether the vehicle yaw rate is within a preset maximum yaw rate range, detect whether the axle drive torque is valid, detect whether the wheel speed signal is valid, detect whether the engine speed signal is valid, and detect whether the vehicle's four tire pressure signals are normal; and a judgment unit, used to determine that the preset vehicle mass opening condition is met when the vehicle speed is within the preset minimum and maximum speed range, the vehicle yaw rate is within the preset maximum yaw rate range, the vehicle's four tire pressure signals are normal, and the axle drive torque, wheel speed signal, and engine speed signal are all valid.

[0021] Through the above-mentioned technical means, the embodiments of this application can perform coarse discrimination on key parameters such as vehicle speed, yaw rate, axle drive torque, wheel speed signal, engine speed signal, and four tire pressure signal. This can filter out scenarios where key parameters are abnormal or signals are invalid, avoid performing vehicle mass estimation when the initial conditions are not met, reduce invalid calculations, and provide a reliable initial judgment basis for whether to perform mass estimation later, thereby improving the effectiveness and accuracy of subsequent mass estimation.

[0022] Optionally, in one embodiment of this application, the calculation module includes: a second detection unit, used to detect whether the longitudinal acceleration signal of the vehicle is valid; a calculation unit, used to calculate a first initial vehicle mass based on a longitudinal dynamics model when the longitudinal acceleration signal is detected to be valid; a third detection unit, used to detect whether there is no braking intervention during vehicle operation, whether the vehicle acceleration is within a preset first maximum threshold range, whether the rate of change of the drive shaft torque is within a preset second maximum threshold range, and whether the rate of change of the transmission ratio is within a preset third maximum threshold range; and an output unit, used to output the first vehicle mass based on the first initial mass when no braking intervention is detected and the acceleration is within the corresponding maximum threshold range.

[0023] Through the aforementioned technical means, this embodiment of the application can first ensure that the core parameters of the longitudinal dynamics model input meet the calculation premise by detecting the validity of the longitudinal acceleration signal, thus avoiding the deviation in the calculation of the first initial vehicle mass caused by invalid signals. Secondly, by simultaneously detecting no braking intervention (eliminating the interference of braking resistance on the driving force balance equation), acceleration within a first threshold (ensuring that acceleration fluctuations are within the linear range applicable to the model), and the change rate of drive shaft torque and the change rate of gearbox transmission ratio within the corresponding threshold (ensuring the stability of power transmission system parameters and avoiding driving force calculation errors caused by sudden changes in torque or transmission ratio), an ideal working condition with smooth loading is constructed. Finally, under this working condition, the first vehicle mass output based on the first initial mass not only ensures the reliability of the model input through signal validity verification, but also eliminates the influence of nonlinear interference factors such as braking and power fluctuations on the derivation of the dynamics equation through multi-parameter threshold screening, thereby significantly improving the accuracy and stability of vehicle mass calculation and making the calculation results more consistent with the actual vehicle mass state.

[0024] Optionally, in one embodiment of this application, the output unit is configured to: record a calculated mass value when the first vehicle mass is between the vehicle's full load mass and minimum curb weight; and calculate the average value of the vehicle mass in the previous period when the number of calculated mass values ​​reaches a set number, so as to obtain the first vehicle mass.

[0025] Through the above-mentioned technical means, the embodiments of this application can filter valid calculated values ​​by limiting the first initial mass between the vehicle's full load mass and minimum curb weight. After the number of valid calculated values ​​reaches a set number, the average value in the previous period is taken as the first vehicle mass, thereby effectively filtering outlier values ​​that deviate from reality. At the same time, by using multi-value averaging to reduce the random error of a single calculation, the accuracy and stability of the vehicle mass calculation results are significantly improved, making them more consistent with the actual mass state of the vehicle.

[0026] Optionally, in one embodiment of this application, the formula for calculating the mass of the first vehicle is expressed as: , in, T w Indicates the wheel-end drive torque. r Indicates the rolling radius of the wheel. C d Indicates the air drag coefficient. A Indicates the windward area. v Indicates longitudinal vehicle speed. f Indicates the rolling resistance coefficient. α Indicates the road slope. δ This represents the rotational mass conversion factor. m Model This represents the vehicle mass calculated using the vehicle model calculation method. g It represents the acceleration due to gravity.

[0027] Optionally, in one embodiment of this application, the calculation module is further configured to: detect whether the vehicle acceleration is less than a first preset threshold, detect whether the axle torque change rate is less than a second preset threshold, and check whether the vehicle braking is engaged; if the vehicle acceleration is less than the first preset threshold, the axle torque change rate is less than the second preset threshold, and the vehicle braking is not engaged, determine that the vehicle is in a stable driving phase, and calculate the second initial vehicle mass according to a preset differential mass calculation formula; detect whether the vehicle acceleration is less than a third preset threshold, detect whether the drive shaft torque change rate is less than a fourth preset threshold, and detect whether the transmission ratio change rate is less than a fifth preset threshold; if the values ​​are all less than the corresponding preset thresholds, output the second vehicle mass based on the second initial vehicle mass.

[0028] Through the aforementioned technical means, the embodiments of this application can achieve layer-by-layer optimization of the accuracy of vehicle mass calculation through phased multi-parameter threshold detection and progressive calculation. Firstly, by detecting that the vehicle acceleration is less than a first preset threshold, the axle torque change rate is less than a second preset threshold, and there is no braking intervention, a basic stable stage (small acceleration fluctuations, stable power output, and no braking interference) is selected. At this point, the second initial vehicle mass is solved based on a preset differential mass calculation formula, which reduces the interference of power and resistance imbalances under non-steady operating conditions on the calculation, ensuring the reliability of the initial value. Furthermore, by detecting that the acceleration is less than a second preset threshold, a more stable stage is selected. Strict third preset thresholds, torque change rate less than the fourth preset threshold, and transmission ratio change rate less than the fifth preset threshold further constrain the vehicle to be in a high-precision stable phase where the power transmission system parameters (torque, transmission ratio) are more stable. At this time, the second vehicle mass is output based on the second initial vehicle mass, which is equivalent to superimposing the low fluctuation constraint of the power transmission parameters on the basic stable conditions. From the derivation level, the influence of minor disturbances such as torque mutation and transmission ratio change on the mass calculation is eliminated. Finally, through the screening and calculation iteration of dual stable working conditions, the calculation accuracy of the second vehicle mass can be significantly improved, making it more consistent with the real mass of the vehicle under actual loading conditions.

[0029] Optionally, in one embodiment of this application, the formula for solving the second initial vehicle mass is expressed as: , in, Ft This represents the driving force of a vehicle during acceleration. Ft_delay This represents the driving force of a vehicle under stable driving conditions. Fw This represents the air resistance of a vehicle during acceleration. Fw_delay This represents the air resistance of a vehicle under stable driving conditions. ax This represents the longitudinal acceleration of a vehicle during acceleration. ax_delay This represents the longitudinal acceleration of a vehicle under stable driving conditions. δ This represents the rotational mass conversion factor. mDiff This represents the vehicle mass obtained through the differential calculation method.

[0030] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the dual-channel result fusion vehicle quality estimation method as described in the above embodiments.

[0031] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the dual-channel result fusion vehicle mass estimation method described above.

[0032] A fifth aspect of this application provides a computer program product that stores a computer program that, when executed by a processor, implements the dual-channel result fusion vehicle quality estimation method described above.

[0033] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0034] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart of a dual-channel result fusion method for estimating vehicle mass according to an embodiment of this application; Figure 2 This is a schematic diagram of the computational framework for estimating vehicle mass in a model lane according to a specific embodiment of this application; Figure 3 This is a schematic diagram of the framework for post-processing of quality estimation according to a specific embodiment of this application; Figure 4 This is a schematic diagram of a differential lane vehicle mass estimation calculation framework according to a specific embodiment of this application; Figure 5 This is a schematic diagram of a dual-channel quality estimation integration framework according to a specific embodiment of this application; Figure 6 This is a flowchart of a dual-channel result fusion vehicle mass estimation method according to a specific embodiment of this application; Figure 7 This is a schematic diagram of the structure of a dual-channel result fusion vehicle mass estimation device according to an embodiment of this application; Figure 8 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0035] The embodiments of this application are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as representing a limitation of this application.

[0036] The following description, with reference to the accompanying drawings, describes a dual-channel result fusion method and apparatus for estimating vehicle mass according to embodiments of this application. To address the issues mentioned in the background technology center, where existing vehicle mass estimation methods suffer from poor adaptability, high algorithm deployment difficulty, and high computational requirements due to limitations imposed by specific scenarios and the inability to avoid interference from nonlinear scenarios and the vehicle's own control system, thus failing to effectively guarantee the accuracy of vehicle mass estimation, this application provides a dual-channel result fusion method for vehicle mass estimation. This method first acquires sensor signals to obtain key parameters such as wheel speed, torque, and acceleration. It then performs initial discrimination of vehicle mass estimation activation conditions, checking basic conditions such as vehicle speed, yaw rate, and sensor validity; if these conditions are not met, the estimation terminates. After satisfying the initial discrimination conditions, the branching processes of the model channel and the differential channel are simultaneously initiated. The model channel first performs mass estimation activation condition discrimination, then calculates the vehicle mass based on the longitudinal dynamics model, and finally filters valid data through a post-processing module. The differential channel preloads parameters such as resistance and gradient under stable operating conditions, then performs estimation activation condition discrimination, subsequently calculates the vehicle mass, and filters data through post-processing. Finally, the dual-channel results are integrated, and dynamic filtering and weighted fusion are used to output the final vehicle mass estimate. This solves the problems that existing vehicle mass estimation methods suffer from poor adaptability, high algorithm deployment difficulty, and high computing power requirements due to limitations in specific scenarios and the inability to avoid interference from nonlinear scenarios and the vehicle's own control system. Consequently, they cannot effectively guarantee the accuracy of vehicle mass estimation.

[0037] Specifically, Figure 1 This is a flowchart illustrating a dual-channel result fusion method for estimating vehicle mass provided in an embodiment of this application.

[0038] like Figure 1 As shown, the dual-channel result fusion method for estimating vehicle mass includes the following steps: In step S101, at least one key parameter of the vehicle is collected to determine whether the vehicle meets the preset vehicle mass opening conditions.

[0039] Among them, at least one key parameter of the vehicle includes, but is not limited to, wheel speed, torque, acceleration, etc., without specific limitations.

[0040] In actual implementation, the embodiments of this application can use sensors to collect signals of the key parameters of the vehicle to obtain key parameters such as wheel speed, torque, and acceleration. After obtaining at least one key parameter, an initial judgment of the vehicle mass activation condition is made. For example, the vehicle speed, yaw rate, and sensor validity can be checked to represent the preset vehicle mass activation condition. If the preset vehicle mass activation condition is met, the vehicle mass can be estimated; otherwise, the estimation is terminated.

[0041] Optionally, in one embodiment of this application, determining whether the vehicle meets the preset vehicle mass activation conditions includes: collecting at least one key parameter of the vehicle, detecting whether the vehicle speed is within a preset minimum and maximum speed range, detecting whether the vehicle yaw rate is within a preset maximum yaw rate range, detecting whether the axle drive torque is valid, detecting whether the wheel speed signal is valid, detecting whether the engine speed signal is valid, and detecting whether the tire pressure signals of the four tires are normal; if the vehicle speed is within a preset minimum and maximum speed range, the vehicle yaw rate is within a preset maximum yaw rate range, the tire pressure signals of the four tires are normal, and the axle drive torque, wheel speed signal, and engine speed signal are all valid, then the preset vehicle mass activation conditions are determined to be met.

[0042] Specifically, in this embodiment of the application, after collecting at least one key parameter of the vehicle, a coarse determination of the vehicle mass estimation activation conditions can be performed: For example, it can be checked whether the vehicle speed is within the preset minimum and maximum speed range; whether the vehicle yaw rate is within the preset maximum yaw rate range; whether the axle drive torque is valid; whether the wheel speed signal is valid; whether the engine speed signal is valid; and whether the tire pressure signals of the four tires are normal. If all parameters are within the preset range and the relevant signals are valid, the coarse judgment of mass estimation is completed, and the initial judgment conditions for mass estimation are met. At this time, it is necessary to further determine whether to perform mass estimation based on subsequent conditions; otherwise, if the initial judgment conditions are not met, mass estimation is not performed.

[0043] Through the above-mentioned technical means, the embodiments of this application can perform coarse discrimination on key parameters such as vehicle speed, yaw rate, axle drive torque, wheel speed signal, engine speed signal, and four tire pressure signal. This can filter out scenarios where key parameters are abnormal or signals are invalid, avoid performing vehicle mass estimation when the initial conditions are not met, reduce invalid calculations, and provide a reliable initial judgment basis for whether to perform mass estimation later, thereby improving the effectiveness and accuracy of subsequent mass estimation.

[0044] In step S102, if the preset vehicle mass activation conditions are met, the vehicle mass estimation mode is entered, and the mass of the first vehicle is calculated using the longitudinal dynamics model and the mass of the second vehicle is calculated using multiple parameters under the stable loading condition.

[0045] In actual execution, once the initial discrimination conditions are met, the branch processes of the model channel and the differential channel can be started simultaneously: the model channel first performs mass estimation activation condition discrimination, then calculates the vehicle mass based on the longitudinal dynamics model, and finally filters valid data through the post-processing module; the differential channel first preloads parameters such as resistance and slope under stable operating conditions, then performs estimation activation condition discrimination, then calculates the vehicle mass and filters data through post-processing; finally, the dual-channel results are integrated, and the final vehicle mass estimate is output through dynamic filtering and weighted fusion.

[0046] Optionally, in one embodiment of this application, the first vehicle mass is calculated using a longitudinal dynamics model and the second vehicle mass is calculated using multiple parameters under a stable loading condition, including: detecting whether the longitudinal acceleration signal of the vehicle is valid; if the longitudinal acceleration signal is detected to be valid, calculating the first initial vehicle mass based on the longitudinal dynamics model; detecting whether there is no braking intervention during vehicle operation, detecting whether the vehicle acceleration is within a preset first maximum threshold range, detecting whether the rate of change of the drive shaft torque is within a preset second maximum threshold range, and detecting whether the rate of change of the transmission ratio is within a preset third maximum threshold range; if no braking intervention is detected and the values ​​are within the corresponding maximum threshold ranges, outputting the first vehicle mass based on the first initial mass.

[0047] like Figure 2 As shown, Figure 2 The calculation process of the model lane vehicle mass estimation method is demonstrated as follows: 1) Estimation process of vehicle mass model: ① Rough determination of vehicle mass estimation start conditions: Check if the vehicle speed is within the preset minimum and maximum speed range; check if the vehicle yaw rate is within the preset maximum yaw rate range; check if the axle drive torque is valid; check if the wheel speed signal is valid; check if the engine speed signal is valid; check if the tire pressure signals of all four tires are normal. If all parameters are within the preset range and the relevant signals are valid, the coarse judgment of mass estimation is completed, and the initial judgment conditions for mass estimation are met. At this point, further judgment needs to be made based on subsequent conditions to determine whether to execute mass estimation; otherwise, if the initial judgment conditions are not met, mass estimation is not executed.

[0048] ② Determination of the opening conditions for the vehicle mass estimation model channel: Check if the vehicle's longitudinal acceleration signal is valid; if the vehicle's longitudinal acceleration signal is valid, calculate the vehicle's mass according to the following formula (1):

[0049] The above formula can be further expressed as:

[0050] Vehicle weight can be expressed as follows:

[0051] in, T w Indicates the wheel-end drive torque. r Indicates the rolling radius of the wheel. C d Indicates the air drag coefficient. A Indicates the windward area. v Indicates longitudinal vehicle speed. f Indicates the rolling resistance coefficient. α Indicates the road slope. δ This represents the rotational mass conversion factor. m Model This represents the vehicle mass calculated using the vehicle model calculation method. g It represents the acceleration due to gravity.

[0052] In the embodiments of this application, equation (3) can be used as a calculation formula to represent the mass of the first vehicle.

[0053] ③ Vehicle model quality estimation output condition discrimination: Check whether there is no braking intervention during vehicle operation; check whether the vehicle's acceleration is within the set maximum threshold range; check whether the rate of change of drive shaft torque is within the set maximum threshold range; check whether the rate of change of transmission ratio is within the set maximum threshold range. If all the above conditions are met, it can be determined that the vehicle accelerates smoothly, the transmission shifts smoothly and there is no braking interference. The vehicle mass calculated by equation (1) is then input into the post-processing module for vehicle mass estimation for the final step of processing before output.

[0054] Through the above-mentioned technical means, the embodiments of this application can first ensure that the core parameter (acceleration) input to the longitudinal dynamics model meets the calculation premise by detecting the validity of the longitudinal acceleration signal, and avoid the deviation in the first initial vehicle mass calculation caused by invalid signals (because there is a quantitative relationship between mass, driving force, drag, and acceleration in the longitudinal dynamics model, invalid acceleration will directly destroy the calculation). F=maFirst, the system establishes a fundamental principle for force balance derivation. Second, it simultaneously detects the absence of braking intervention (eliminating the interference of braking resistance on the driving force balance equation), acceleration within a first threshold (ensuring acceleration fluctuations are within the linear range applicable to the model), and the rate of change of drive shaft torque and gearbox transmission ratio within corresponding thresholds (ensuring stable power transmission system parameters and avoiding driving force calculation errors caused by sudden changes in torque or transmission ratio). This constructs an ideal loading condition. Finally, based on the first vehicle mass output under this condition, the reliability of the model input is ensured through signal validity verification, and the influence of nonlinear interference factors such as braking and power fluctuations on the derivation of the dynamic equations is eliminated through multi-parameter threshold screening. This significantly improves the accuracy and stability of vehicle mass calculation, making the calculation results more consistent with the actual vehicle mass state.

[0055] Furthermore, in one embodiment of this application, outputting the first vehicle mass based on the first initial mass includes: recording a calculated mass value when the first vehicle mass is between the vehicle's full load mass and minimum curb weight; and calculating the average value of the vehicle mass in the previous period when the number of calculated mass values ​​reaches a set number, so as to obtain the first vehicle mass.

[0056] In this embodiment of the application, after completing step ③ of the vehicle model mass estimation output condition judgment, the calculated vehicle mass can be input into the vehicle mass post-processing model for post-processing of mass estimation, such as... Figure 3 As shown, the post-processing procedure for quality estimation can be specifically set as follows: ④ Post-processing of quality estimation: Valid values ​​of the mass estimate are filtered. When the calculated vehicle mass is between the vehicle's full load mass and minimum curb weight, it is considered that the calculated vehicle mass is within a reasonable range, and the calculated vehicle mass value is recorded. When the number of recorded valid mass values ​​reaches a set threshold, the average value of the vehicle mass in the previous period is calculated.

[0057] ⑤ Iterative solution: Repeat steps ①-④ to update and output the quality estimate obtained by the model quality estimation method.

[0058] Through the above-mentioned technical means, the embodiments of this application can filter valid calculated values ​​by limiting the first initial mass between the vehicle's full load mass and minimum curb weight. After the number of valid calculated values ​​reaches a set number, the average value in the previous period is taken as the first vehicle mass, thereby effectively filtering outlier values ​​that deviate from reality. At the same time, by using multi-value averaging to reduce the random error of a single calculation, the accuracy and stability of the vehicle mass calculation results are significantly improved, making them more consistent with the actual mass state of the vehicle.

[0059] Optionally, in one embodiment of this application, the first vehicle mass is calculated using a longitudinal dynamics model, and the second vehicle mass is calculated using multiple parameters under a stable loading condition. This includes: detecting whether the vehicle acceleration is less than a first preset threshold, detecting whether the axle torque change rate is less than a second preset threshold, and checking whether the vehicle braking is engaged; if the vehicle acceleration is less than the first preset threshold, the axle torque change rate is less than the second preset threshold, and the vehicle braking is not engaged, the vehicle is determined to be in a stable driving phase, and the second initial vehicle mass is calculated according to a preset differential mass calculation formula; detecting whether the vehicle acceleration is less than a third preset threshold, detecting whether the drive shaft torque change rate is less than a fourth preset threshold, and detecting whether the transmission ratio change rate is less than a fifth preset threshold; if the values ​​are all less than the corresponding preset thresholds, the second vehicle mass is output based on the second initial vehicle mass.

[0060] Among them, regarding the calculation of the second vehicle's mass using multiple parameters under stable loading conditions, such as... Figure 4 As shown, the specific settings are as follows: 2) Vehicle mass differential estimation process (i.e., branching process of the differential channel): ① Rough determination of vehicle mass estimation start conditions: The coarse discrimination conditions are the same as those for model quality methods, and will not be repeated here.

[0061] ②Preloading of the vehicle mass estimation differential channel: The system checks whether the vehicle acceleration is less than a set threshold. This threshold is relatively small, requiring the vehicle to not accelerate or accelerate only slightly. It also checks whether the axle torque change rate is less than a set threshold and whether the vehicle brakes are engaged. If the parameters are within the preset range and the vehicle brakes are not engaged, it indicates that the vehicle is in a stable driving phase. The drive axle torque during this stable driving phase is recorded and delayed. This delayed torque is used to calculate the vehicle's delayed driving force. This delayed driving force, along with air resistance and road gradient, is output to the model mass calculation module for calculating the vehicle's mass during acceleration.

[0062] ③ Calculation of vehicle mass estimation differential channel: Once the vehicle's stable driving time reaches a set threshold, the vehicle differential mass estimation proceeds to the next stage. When the vehicle's acceleration exceeds the set threshold and there is significant acceleration, step ② is no longer executed, and the vehicle differential mass estimation preloading is complete. The difference between the road gradient in the preloading module and the current road gradient is checked to ensure it is less than the set threshold. If the condition is met, the vehicle mass is calculated using the differential mass calculation formula.

[0063] Optionally, in one embodiment of this application, the formula for solving the second initial vehicle mass is expressed as: , in, FtThis represents the driving force of a vehicle during acceleration. Ft_delay This indicates the driving force of a vehicle under stable driving conditions. Fw This represents the air resistance of a vehicle during acceleration. Fw_delay This represents the air resistance of a vehicle under stable driving conditions. ax This represents the longitudinal acceleration of a vehicle during acceleration. ax_delay This represents the longitudinal acceleration of a vehicle under stable driving conditions. δ This represents the rotational mass conversion factor. mDiff This represents the vehicle mass obtained through the differential calculation method.

[0064] ④ Vehicle model quality estimation output condition judgment: Check if the vehicle acceleration is less than a set threshold; check if the torque change rate is less than a set threshold; check if the transmission ratio change rate is less than a set threshold. If the above conditions are met, output the vehicle mass calculated by equation (4) to ⑤ for post-processing of mass estimation.

[0065] ⑤ Quality estimation post-processing module: The post-processing workflow is the same as that of the model quality method, so it will not be repeated here.

[0066] ⑥ Iterative solution: Repeat steps ①-⑤ to update and output the mass estimate obtained by the vehicle mass difference estimation method.

[0067] Through the aforementioned technical means, the embodiments of this application can achieve layer-by-layer optimization of the accuracy of vehicle mass calculation through phased multi-parameter threshold detection and progressive calculation. First, by detecting that the vehicle acceleration is less than a first preset threshold, the axle torque change rate is less than a second preset threshold, and there is no braking intervention, a basic stable stage with stable vehicle driving status (small acceleration fluctuations, stable power output, and no braking interference) is selected. At this time, the second initial vehicle mass is solved based on the preset differential mass calculation formula, which can reduce the interference of power and resistance imbalance on the calculation under non-steady conditions and ensure the reliability of the initial value. Furthermore, by detecting that the acceleration is less than a more stringent threshold, the accuracy of vehicle mass calculation can be further optimized. The third preset threshold, the torque change rate being less than the fourth preset threshold, and the transmission ratio change rate being less than the fifth preset threshold further constrain the vehicle to be in a high-precision stable phase where the power transmission system parameters (torque and transmission ratio) are more stable. At this time, the second vehicle mass is output based on the second initial vehicle mass, which is equivalent to superimposing the low fluctuation constraint of the power transmission parameters on the basic stable conditions. From the derivation level, the influence of minor disturbances such as torque mutation and transmission ratio change on the mass calculation is eliminated. Finally, through the screening and calculation iteration of the dual stable working conditions, the calculation accuracy of the second vehicle mass can be significantly improved, making it more consistent with the real mass of the vehicle under actual loading conditions.

[0068] In step S103, the first vehicle mass and the second vehicle mass are fused based on their corresponding weights to obtain the final vehicle mass estimate based on the fusion result.

[0069] In actual implementation, the embodiments of this application can set up a weighted fusion of dual-channel vehicle mass estimation, specifically, as follows: Figure 5 As shown in the embodiment of this application, the vehicle mass obtained from the model channel and the differential channel can be fused, as shown in the following formula:

[0070] in, w It can be selected based on the magnitude of the vehicle's longitudinal acceleration.

[0071] The longitudinal acceleration of a vehicle is categorized into four levels: low, medium, high, and very high. The longitudinal acceleration ranges from 0 to 3 m / s². 2 The longitudinal acceleration is low, and the dependence on the differential channel is low. w Set to 0.2; longitudinal acceleration is between 3 and 6 m / s². 2 In the longitudinal acceleration representation, the dependence on the differential channel increases, at which point... w Set to 0.4; longitudinal acceleration is between 6 and 9 m / s². 2 When the longitudinal acceleration is high, the vehicle mass calculated by the differential channel is dominant, and w is set to 0.6; when the longitudinal acceleration is greater than 9 m / s², the longitudinal acceleration is high. 2 ,at this time w Set it to 0.8.

[0072] Regarding signal filtering in the aforementioned dual-channel quality estimation, a pre-packaged first-order low-pass filter (LPF) module can be used. This low-pass filter requires only a single multiplication and addition operation, eliminating the need for complex matrix operations or iterative solutions. It is particularly suitable for embedded systems in automotive electronic control units, saving debugging costs. When the sampling time is fixed, the filtering capability of the signal is adjusted by regulating the cutoff frequency. The specific formula for the first-order low-pass filter is as follows: (6) in, f Indicates the cutoff frequency. t Indicates the sampling time.

[0073] Through the above-mentioned technical means, the embodiments of this application can obtain the final mass estimate by representing the mass of the first vehicle and the mass of the second vehicle with corresponding weights and fusing them. This can combine the advantages of the two mass calculation methods, balance the calculation characteristics under different working conditions, effectively reduce the deviation or limitations that may exist in a single calculation method, thereby improving the accuracy and robustness of the final mass estimate of the vehicle and making it more consistent with the actual mass state of the vehicle.

[0074] In summary, this application addresses the problem of insufficient accuracy and limited adaptability of single-channel estimation under complex operating conditions in vehicle mass estimation. It proposes a dual-channel result fusion method for vehicle mass estimation, achieving accurate and robust mass estimation through the dynamic fusion of a precise estimation channel (model channel) based on the longitudinal dynamics model and a differential estimation channel (differential channel) based on the longitudinal force-acceleration trend. Specifically, the model channel constructs a precise calculation framework based on the vehicle's longitudinal dynamics model; the differential channel constructs a simplified model based on the parameter difference between steady-state and acceleration conditions, calculating the mass change trend through the ratio of the delayed torque signal to the real-time acceleration.

[0075] Based on this, a dual-channel collaborative logic is designed: the model channel, based on Newton's second law, filters the effective calculation range through constraints such as no braking intervention and smooth acceleration, and uses a signal filtering module to smooth the output results; the differential channel tracks the dynamic changes in mass to represent the core objective, distinguishing between the steady and acceleration phases by setting acceleration thresholds. During the steady phase, parameters such as road resistance and gradient are preloaded; during the acceleration phase, vehicle mass is calculated based on the preloaded data. Both channels share the basic conditions for sensor signal validity judgment and vehicle speed range detection, but each has its own independent trigger threshold.

[0076] Furthermore, this embodiment of the application can fuse the dual-channel vehicle mass estimation results through dynamic weighting coefficients. The weights are adaptively adjusted according to the complexity of the operating conditions, and the fused results are corrected in real time using closed-loop feedback from wheel speed and acceleration sensors, forming a closed-loop logic of "dual-channel parallel computing - dynamic weight fusion - feedback correction". This method reduces the mass estimation error under complex operating conditions, improves the anti-interference capability against braking, steering and other disturbances, and reduces the running time of the algorithm on the vehicle electronic control unit, meeting the real-time and accuracy requirements of the vehicle chassis control system for mass estimation.

[0077] The beneficial technical effects of the above embodiments can be summarized as follows: (1) Improved estimation accuracy: The dual-channel mass estimation method can effectively avoid the limitation of a single method to specific scenarios. By combining dynamic filtering fusion strategy, the estimation accuracy of vehicle mass is improved.

[0078] (2) Enhanced adaptability: For nonlinear scenarios and interference caused by the intervention of various vehicle control systems, the corresponding quality estimation channel can be selected through condition discrimination, which can improve the estimation stability of the algorithm in complex environments and its adaptability to changes in noise statistical characteristics.

[0079] (3) High engineering feasibility: It can simplify the nonlinear processing flow of vehicle systems, avoid the iterative process in dynamic estimation methods, and its interpretability is higher than that of machine learning-based estimation methods. The algorithm is easy to deploy in the vehicle electronic control unit and has a shorter running time, which meets the real-time control requirements.

[0080] Furthermore, in order to enable those skilled in the art to more clearly understand this application, the following specific embodiment will be used to exemplarily illustrate the dual-channel result fusion vehicle mass estimation method of this application.

[0081] In this embodiment, the specific process of the dual-channel result fusion vehicle mass estimation method can be set as follows: Step S601: Sensor signal acquisition; First, sensor signals are acquired to obtain several important parameters such as wheel speed and torque; Step S602: Initial determination of vehicle mass start conditions, check the basic conditions such as vehicle speed, yaw rate and sensor effectiveness. If not met, the estimation is terminated. After the initial determination conditions are met, the branch process of the model channel and the difference channel is started at the same time. Then steps S603 and S606 can be executed at the same time. Step S603: Perform the absolute mechanism quality estimation start condition discrimination of the model channel; this step corresponds to the coarse discrimination of the vehicle quality estimation start condition of the model method in the above embodiment, and the specific execution process will not be described here. Step S604: Perform absolute mass estimation of vehicle mass calculation for the model channel; this step corresponds to the vehicle mass estimation of the model method in the above embodiment, and the specific execution process will not be described here. Step S605: Perform post-processing for quality estimation of the model channels; Step S606: Perform relative mechanism quality estimation preloading for the differential channel; this step corresponds to the vehicle quality estimation differential channel preloading content in the above embodiments, and will not be repeated here; Step S607: Perform relative mechanism quality estimation of differential channels to determine the activation condition; Step S608: Perform relative mass estimation of vehicle mass calculation using the differential channel; this step corresponds to the vehicle mass estimation differential channel calculation process in the above embodiments, and will not be repeated here. Step S609: Perform post-processing for quality estimation of the differential channels; Step S610: Integrate the post-processing results of the quality estimation of the model channel obtained in step S605 with the post-processing results of the quality estimation of the differential channel obtained in step S609 into a dual-channel quality estimation. Step S611: Finally, the estimated vehicle mass value is obtained.

[0082] The dual-channel result fusion vehicle mass estimation method proposed in this application can be applied to the process of vehicle assisted driving. It can accurately estimate the vehicle mass to coordinate and optimize the chassis control strategy, improve the execution effect of functions such as anti-lock braking, traction control, and vehicle attitude control, and ensure the vehicle driving stability and ride comfort during assisted driving.

[0083] The dual-channel result fusion method for vehicle mass estimation proposed in this application first acquires sensor signals to obtain key parameters such as wheel speed, torque, and acceleration. It then performs initial discrimination of vehicle mass estimation conditions, checking basic conditions such as vehicle speed, yaw rate, and sensor validity; estimation terminates if these conditions are not met. Once the initial discrimination conditions are met, the branching processes of the model channel and the differential channel are simultaneously initiated. The model channel first discriminates the mass estimation conditions, then calculates the vehicle mass based on the longitudinal dynamics model, and finally filters valid data through a post-processing module. The differential channel preloads parameters such as resistance and gradient under stable operating conditions, then discriminates the estimation conditions, calculates the vehicle mass, and filters data through post-processing. Finally, the dual-channel results are integrated, and the final vehicle mass estimate is output through dynamic filtering and weighted fusion. This solves the problems of existing vehicle mass estimation methods, which are limited by specific scenarios and cannot avoid interference from nonlinear scenarios and the vehicle's own control system, resulting in poor adaptability, high algorithm deployment difficulty, and high computational requirements, ultimately failing to effectively guarantee vehicle mass estimation accuracy.

[0084] Next, refer to the appendix. Figure 7 This application describes a dual-channel result fusion vehicle quality estimation apparatus based on embodiments thereof.

[0085] Figure 7 This is a block diagram of a dual-channel result fusion vehicle quality estimation device according to an embodiment of this application.

[0086] like Figure 7 As shown, the dual-channel result fusion vehicle mass estimation device 10 includes: a judgment module 100, a calculation module 200, and an estimation module 300.

[0087] The judgment module 100 is used to collect at least one key parameter of the vehicle to determine whether the vehicle meets the preset vehicle quality opening conditions.

[0088] The calculation module 200 is used to enter the vehicle mass estimation mode if the preset vehicle mass activation conditions are met, and to calculate the mass of the first vehicle using the longitudinal dynamics model and the mass of the second vehicle using multiple parameters under the loading steady condition.

[0089] The estimation module 300 is used to fuse the first vehicle mass and the second vehicle mass based on corresponding weights to obtain the final mass estimate of the vehicle based on the fusion result.

[0090] Optionally, in one embodiment of this application, the judgment module 100 includes: a first detection unit and a judgment unit; wherein, the first detection unit is used to collect at least one key parameter of the vehicle, detect whether the vehicle speed is within a preset minimum and maximum speed range, detect whether the vehicle yaw rate is within a preset maximum yaw rate range, detect whether the axle drive torque is valid, detect whether the wheel speed signal is valid, detect whether the engine speed signal is valid, and detect whether the vehicle's four tire pressure signals are normal; the judgment unit is used to determine that the preset vehicle mass opening conditions are met when the vehicle speed is within a preset minimum and maximum speed range, the vehicle yaw rate is within a preset maximum yaw rate range, the vehicle's four tire pressure signals are normal, and the axle drive torque, wheel speed signal, and engine speed signal are all valid.

[0091] Optionally, in one embodiment of this application, the calculation module 200 includes: a second detection unit, a calculation unit, a third detection unit, and an output unit; wherein, the second detection unit is used to detect whether the longitudinal acceleration signal of the vehicle is valid; the calculation unit is used to calculate the first initial vehicle mass based on the longitudinal dynamics model when the longitudinal acceleration signal is detected to be valid; the third detection unit is used to detect whether there is no braking intervention during vehicle driving, whether the vehicle acceleration is within a preset first maximum threshold range, whether the rate of change of the drive shaft torque is within a preset second maximum threshold range, and whether the rate of change of the transmission ratio is within a preset third maximum threshold range; the output unit is used to output the first vehicle mass based on the first initial mass when no braking intervention is detected and the acceleration is within the corresponding maximum threshold range.

[0092] Optionally, in one embodiment of this application, the output unit is configured to: record a calculated mass value when the first vehicle mass is between the vehicle's full load mass and minimum curb weight; and calculate the average value of the vehicle mass in the previous period when the number of calculated mass values ​​reaches a set number, so as to obtain the first vehicle mass.

[0093] Optionally, in one embodiment of this application, the formula for calculating the mass of the first vehicle is expressed as: , in, T w Indicates the wheel-end drive torque. r Indicates the rolling radius of the wheel. C d Indicates the air drag coefficient. A Indicates the windward area.v Indicates longitudinal vehicle speed. f Indicates the rolling resistance coefficient. α Indicates the road slope. δ This represents the rotational mass conversion factor. m Model This represents the vehicle mass calculated using the vehicle model calculation method. g It represents the acceleration due to gravity.

[0094] Optionally, in one embodiment of this application, the calculation module 200 is further configured to: detect whether the vehicle acceleration is less than a first preset threshold, detect whether the axle torque change rate is less than a second preset threshold, and check whether the vehicle braking is engaged; if the vehicle acceleration is less than the first preset threshold, the axle torque change rate is less than the second preset threshold, and the vehicle braking is not engaged, determine that the vehicle is in a stable driving phase, and calculate the second initial vehicle mass according to a preset differential mass calculation formula; detect whether the vehicle acceleration is less than a third preset threshold, detect whether the drive shaft torque change rate is less than a fourth preset threshold, and detect whether the transmission ratio change rate is less than a fifth preset threshold; if the values ​​are all less than the corresponding preset thresholds, output the second vehicle mass based on the second initial vehicle mass.

[0095] Optionally, in one embodiment of this application, the formula for solving the second initial vehicle mass is expressed as: , in, Ft This represents the driving force of a vehicle during acceleration. Ft_delay This represents the driving force of a vehicle under stable driving conditions. Fw This represents the air resistance of a vehicle during acceleration. Fw_delay This represents the air resistance of a vehicle under stable driving conditions. ax This represents the longitudinal acceleration of a vehicle during acceleration. ax_delay This represents the longitudinal acceleration of a vehicle under stable driving conditions. δ This represents the rotational mass conversion factor. mDiff This represents the vehicle mass obtained through the differential calculation method.

[0096] Furthermore, the hardware configuration of this application embodiment can be set as follows: ① Drive system: It can be equipped with four-wheel speed sensors to obtain vehicle speed signals; and four-wheel torque sensors to obtain four-wheel torque signals and calculate the vehicle's driving force.

[0097] ② Braking system: It can be equipped with a brake pressure sensor and a brake pedal displacement sensor to detect the braking intervention status in real time and determine whether there is braking interference.

[0098] ③ Equipped with a six-axis inertial measurement unit, it is used to acquire the acceleration and angular velocity of the vehicle in the horizontal, vertical and lateral directions in real time, monitor the longitudinal acceleration of the vehicle and the yaw motion state during turning, and use it to determine the applicability of the working conditions for mass estimation.

[0099] ④ Equipped with a high-performance electronic control unit, it has the ability to acquire multi-sensor data synchronously, run filtering algorithms in real time, and perform iterative calculations. It supports parallel processing and result fusion output in both modes of quality estimation.

[0100] It should be noted that the foregoing explanation of the embodiment of the dual-channel result fusion vehicle quality estimation method also applies to the dual-channel result fusion vehicle quality estimation device of this embodiment, and will not be repeated here.

[0101] The dual-channel result fusion vehicle mass estimation device proposed in this application first acquires sensor signals to obtain key parameters such as wheel speed, torque, and acceleration. It then performs initial discrimination of vehicle mass estimation conditions, checking basic conditions such as vehicle speed, yaw rate, and sensor validity; if these conditions are not met, the estimation terminates. After meeting the initial discrimination conditions, the branching processes of the model channel and the differential channel are simultaneously initiated. The model channel first discriminates the mass estimation conditions, then calculates the vehicle mass based on the longitudinal dynamics model, and finally filters valid data through a post-processing module. The differential channel preloads parameters such as resistance and gradient under stable operating conditions, then discriminates the estimation conditions, calculates the vehicle mass, and filters data through post-processing. Finally, the dual-channel results are integrated, and the final vehicle mass estimate is output through dynamic filtering and weighted fusion. This solves the problems of existing vehicle mass estimation methods, which are limited by specific scenarios and cannot avoid interference from nonlinear scenarios and the vehicle's own control system, resulting in poor adaptability, high algorithm deployment difficulty, and high computational requirements, thus failing to effectively guarantee the accuracy of vehicle mass estimation.

[0102] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include: The memory 801, the processor 802, and the computer program stored on the memory 801 and capable of running on the processor 802.

[0103] When the processor 802 executes the program, it implements the dual-channel result fusion vehicle quality estimation method provided in the above embodiments.

[0104] Furthermore, electronic devices also include: Communication interface 803 is used for communication between memory 801 and processor 802.

[0105] The memory 801 is used to store computer programs that can run on the processor 802.

[0106] The memory 801 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0107] If the memory 801, processor 802, and communication interface 803 are implemented independently, then the communication interface 803, memory 801, and processor 802 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be represented as an address bus, data bus, control bus, etc. This representation is for ease of representation. Figure 8 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0108] Optionally, in a specific implementation, if the memory 801, processor 802, and communication interface 803 are integrated on a single chip, then the memory 801, processor 802, and communication interface 803 can communicate with each other through an internal interface.

[0109] The processor 802 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0110] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described dual-channel result fusion vehicle mass estimation method.

[0111] This application also provides a computer program product storing a computer program that, when executed by a processor, implements the above-described dual-channel result fusion vehicle quality estimation method.

[0112] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0113] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0114] Any process or method description in the flowchart or otherwise herein can be understood to represent a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0115] The logic and / or steps represented in the flowchart or otherwise described herein, for example, may be represented as a sequenced list of executable instructions for implementing logical functions, and may be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, meaning that the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0116] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or more of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0117] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it includes one or a combination of the steps of the method embodiments.

[0118] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and is intended for independent product sale or use, it can also be stored in a computer-readable storage medium.

[0119] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A dual-channel result fusion whole vehicle mass estimation method, characterized in that, The method comprises the following steps: collecting at least one key parameter of the vehicle to determine whether the vehicle meets a preset vehicle mass starting condition; if the preset vehicle mass starting condition is met, entering a vehicle mass estimation mode, calculating a first vehicle mass by using a longitudinal dynamics model and calculating a second vehicle mass by using a plurality of parameters under a loaded steady state condition; fusing the first vehicle mass and the second vehicle mass based on corresponding weights to obtain a final mass estimation value of the vehicle according to a fusion result.

2. The method of claim 1, wherein, The determination of whether the vehicle meets the preset vehicle mass starting condition comprises: collecting at least one key parameter of the vehicle to detect whether the vehicle speed is within a preset minimum speed and maximum speed range, whether the vehicle yaw rate is within a preset maximum yaw rate range, whether the axle driving torque is effective, whether the wheel speed signal is effective, whether the engine speed signal is effective and whether the vehicle four-wheel tire pressure signal is normal; if the vehicle speed is within the preset minimum speed and maximum speed range, the vehicle yaw rate is within the preset maximum yaw rate range, the vehicle four-wheel tire pressure signal is normal and the axle driving torque, the wheel speed signal and the engine speed signal are all effective, it is determined that the preset vehicle mass starting condition is met.

3. The method of claim 1, wherein, The calculation of the first vehicle mass by using the longitudinal dynamics model and the calculation of the second vehicle mass by using the plurality of parameters under the loaded steady state condition comprise: detecting whether the longitudinal acceleration signal of the vehicle is effective; if the longitudinal acceleration signal is detected to be effective, calculating a first initial vehicle mass based on the longitudinal dynamics model; detecting whether there is no brake intervention during vehicle driving, whether the vehicle acceleration is within a preset first maximum threshold range, whether the driving axle torque change rate is within a preset second maximum threshold range and whether the transmission ratio change rate is within a preset third maximum threshold range; if no brake intervention and the corresponding maximum threshold ranges are detected, outputting the first vehicle mass based on the first initial mass.

4. The method of claim 3, wherein, The output of the first vehicle mass based on the first initial mass comprises: when the first vehicle mass is between the full load mass and the minimum ready mass of the vehicle, recording a mass calculation value; when the number of the mass calculation values reaches a set number, calculating an average value of the vehicle mass in a previous period to obtain the first vehicle mass.

5. The method of claim 3, wherein, The calculation formula of the first vehicle mass is represented as: ， wherein, T w represents a wheel end driving torque, r represents a wheel rolling radius, C d represents an air resistance coefficient, A represents a windward area, v represents a longitudinal vehicle speed, f represents a rolling resistance coefficient, α represents a road slope, δ represents a rotational mass conversion coefficient, m Model represents a vehicle mass calculated by a vehicle model calculation method, g represents a gravitational acceleration.

6. The method of claim 1, wherein, The calculation of the first vehicle mass by using the longitudinal dynamics model and the calculation of the second vehicle mass by using the plurality of parameters under the loaded steady state condition comprise: detecting whether the vehicle acceleration is less than a first preset threshold, detecting whether the axle torque change rate is less than a second preset threshold and checking whether the vehicle brake is intervened; In a case where it is detected that the vehicle acceleration is less than the first preset threshold, the axle torque change rate is less than the second preset threshold, and the vehicle brake is not intervened, it is determined that the vehicle is in a steady driving stage, and a second initial vehicle mass is solved according to a preset differential mass calculation formula; detecting whether the vehicle acceleration is less than a third preset threshold, detecting whether the torque change rate of the drive axle is less than a fourth preset threshold, and detecting whether the transmission ratio change rate is less than a fifth preset threshold; In a case where it is detected that the vehicle acceleration is less than the first preset threshold, the axle torque change rate is less than the second preset threshold, and the vehicle brake is not intervened, it is determined that the vehicle is in a steady driving stage, and a second initial vehicle mass is solved according to a preset differential mass calculation formula; 7. The method of claim 6, wherein, The solving formula of the second initial vehicle mass is represented as: ， wherein Ft represents a running driving force of the vehicle in the accelerating running state, Ft_delay represents a running driving force of the vehicle in the steady running state, Fw represents an air resistance of the vehicle in the accelerating running state, Fw_delay represents an air resistance of the vehicle in the steady running state, ax represents a longitudinal acceleration of the vehicle in the accelerating running state, ax_delay represents a longitudinal acceleration of the vehicle in the steady running state, δ represents a rotational mass conversion coefficient, mDiff represents a vehicle mass obtained by a difference calculation method.

8. An electronic device, comprising: comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the dual-channel result fusion whole vehicle mass estimation method according to any one of claims 1-7.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the dual-channel result fusion whole vehicle mass estimation method according to any one of claims 1-7.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed to implement the dual-channel result fusion whole vehicle mass estimation method according to any one of claims 1-7.

Images