Method and device for determining the total mass of a vehicle

Abstract

Method and device for determining the total mass of a vehicle. The present invention relates to a method (100) for determining the total mass of a vehicle, comprising the steps of: - receiving (102) a representative value of a torque applied to the wheels of the vehicle, - receiving (102) a representative value of a longitudinal acceleration of the vehicle, the method of determination (100) being characterized in that it further comprises the steps of: - injecting (110) the representative values ​​of a torque and a longitudinal acceleration into a model for estimating a representative value of a longitudinal force applied to the vehicle, and - determining (112) the total mass of the vehicle as a function of the representative value of the longitudinal force estimated by the estimation model and the representative value of the longitudinal acceleration. (Figure 2)

Description

Title of the invention: Method and device for determining the total mass of a vehicle

[0001] The present invention relates to the field of the automotive industry, and more specifically concerns a method for determining the mass of a vehicle, carried out in the vehicle during its use.

[0002] The overall mass of a vehicle, including its sprung and unsprung mass, is used by the Advanced Driver Assistance Systems (ADAS) implemented in the vehicle. It should be noted that the unsprung mass is the mass of the vehicle components that precisely follow the undulations of the road surface on which the vehicle is traveling, namely the wheels, rims, tires, and shock absorbers, while the sprung mass is the mass of the vehicle components located above the shock absorbers. The unsprung mass is therefore virtually constant throughout the vehicle's operation, whereas the sprung mass depends on the vehicle's load and the number of occupants, and can therefore vary considerably.

[0003] Currently, advanced driver assistance systems use a fixed mass entered into the vehicle's main computer, regardless of the vehicle's load. The vehicle's chassis actuators, particularly the braking and trajectory control devices, therefore do not have the exact total mass of the vehicle. Consequently, the commands that these devices exert on the chassis and wheels deviate from the intended braking or trajectory target, which can impact stability and passenger comfort.

[0004] The precise determination of the total mass of the vehicle is therefore important for designing an optimal self-adaptive control of the vehicle while reducing the energy used by this control, allowing a rapid convergence of the commands towards the set objective.

[0005] Furthermore, precise knowledge of the vehicle's total mass allows for improved route planning, particularly for electric vehicles, whose range is significantly impacted by their mass. In fact, the European Commission mandates that vehicle manufacturers determine the vehicle's total mass in real time.

[0006] Existing solutions for determining the mass of a vehicle during its use utilize measured or estimated data concerning the longitudinal dynamics of the vehicle, in particular its longitudinal acceleration, its speed longitudinal, as well as rolling resistance coefficients. However, the corresponding algorithms require knowledge of all the forces involved in this longitudinal dynamic. Most of these forces, particularly aerodynamic ones, are not directly measurable, necessitating the use of observers, Kalman filters, and / or derivations of equations formalizing this longitudinal dynamic. These derivations assume that the forces are constant and, consequently, that their derivatives are zero, which is not entirely accurate since resistive forces vary depending on the vehicle's speed, wind speed, air density, tire characteristics, and the road surface, among other factors. Therefore, these solutions do not provide the total vehicle mass with sufficient accuracy.

[0007] The present invention aims to remedy at least in part the aforementioned drawbacks by providing a method and a device for determining the total mass of a vehicle, which in particular does not require a calculation of the resistive forces applied to the vehicle.

[0008] To this end, the invention proposes a method for determining the total mass of a vehicle, comprising the following steps: - receiving a representative value of a torque applied to the vehicle's wheels, - receiving a representative value of a longitudinal acceleration of the vehicle, the determination method being characterized in that it further comprises the steps of: - injecting the representative values ​​of a torque and a longitudinal acceleration into a model for estimating a representative value of a longitudinal force applied to the vehicle, and - determination of the total mass of the vehicle as a function of the representative value of the longitudinal force estimated by the estimation model and the representative value of the longitudinal acceleration.

[0009] It is understood that the estimation model provides the representative value of the longitudinal force at the output and that the mass is determined based on a ratio between the representative value of the longitudinal force and the representative value of the longitudinal acceleration. This estimation model does not require measurements of resistive forces; for example, it is based on a neural network, a regression model, or an identification system.

[0010] Thanks to the invention, a precise total mass of the vehicle is obtained, which allows the braking and trajectory control devices to have very good performance in terms of vehicle stability and comfort for the vehicle's passengers.

[0011] In one embodiment of the invention, the estimation model is derived from a supervised learning phase, implemented prior to the execution of the Determination method. This supervised learning phase allows the model to learn the resistive forces involved in the longitudinal dynamics of the vehicle and to deduce them from the vehicle's traction or propulsion force. Once this learning phase is complete, the estimation model therefore does not need to perform any calculations or measurements to account for these resistive forces. Compared to the prior art, the invention thus requires significantly fewer computing resources within the vehicle. Furthermore, this supervised learning phase allows for the correction of uncertainties related to measurements or estimates of the torque applied to the vehicle's wheels and the vehicle's longitudinal acceleration.

[0012] The estimation model is, for example, a neural network with inputs at least the representative value of the torque and the representative value of the longitudinal acceleration, and output the representative value of the longitudinal force. The neural network has, for example, four neural layers, which is sufficient to obtain good accuracy on the representative value of the longitudinal force. Alternatively, the estimation model includes additional input parameters, such as, for example, the lateral acceleration of the vehicle, the wind speed, or the gradient of the road on which the vehicle is traveling. In this variant, the estimation model is refined but requires a longer supervised learning phase and means of determining values ​​corresponding to these additional parameters in the vehicle, such as sensors or observers.

[0013] The determination step includes, for example, the calculation of a total gross mass equal to the ratio between the estimated longitudinal force and the longitudinal acceleration.

[0014] According to an advantageous and optional feature of the invention, the determination step further includes a time smoothing step of the calculated total gross mass.

[0015] Indeed, since the determination of the total mass of the vehicle is carried out in real time, the representative values ​​of the torque applied to the wheels of the vehicle and of the longitudinal acceleration can be distorted by sudden variations in the speed of the vehicle and result in fluctuations in the total gross mass calculated in real time.

[0016] The smoothing step uses, for example, a Kalman filter or a recursive least squares method. It makes it possible to obtain an accurate total mass of the vehicle even during sudden variations in the vehicle's speed.

[0017] According to another advantageous and optional feature of the invention, the method for determining the total mass of a vehicle according to the invention includes a step of inhibiting the determination step when at least one of the following conditions is met: - a slope on which the vehicle is traveling is determined to be greater than a predetermined angle. - the ratio, in absolute value, between the longitudinal acceleration of the vehicle and the lateral acceleration of the vehicle, is determined to be less than a predetermined threshold, and - a vehicle deceleration is determined to be greater than a predetermined braking threshold.

[0018] This inhibition step ensures that certain prerequisites are met before determining the vehicle's total mass. These prerequisites allow the estimation model to be as accurate as possible. Indeed, the estimation model is designed under driving conditions that should closely match those of the vehicle when the total mass determination process is performed. In particular, when the vehicle is traveling on a steep incline, the estimation model may provide the longitudinal force with less accuracy.

[0019] The invention also relates to a device for determining the total mass of a vehicle, comprising: - means for receiving a value representative of a torque applied to the vehicle's wheels, - means of receiving a value representative of the longitudinal acceleration of the vehicle, the determination device being characterized in that it further comprises: - a model for estimating a representative value of a longitudinal force applied to the vehicle, capable of receiving as input the representative values ​​of a torque and a longitudinal acceleration, and - means of determining the total mass of the vehicle as a function of the representative value of the longitudinal force estimated by the estimation model, and of the representative value of the longitudinal acceleration.

[0020] The receiving means are, for example, a communication port connected to a computer bus of the vehicle. The invention makes it possible to use the signals already available on this computer bus, without requiring additional external data.

[0021] In this device for determining the total mass of a vehicle according to the invention, the estimation model is for example a trained neural network having as inputs at least the representative value of the torque and the representative value of the longitudinal acceleration, and as output the representative value of the longitudinal force.

[0022] Furthermore, in this device for determining the total mass of a vehicle according to the invention, the means of determination include, for example, means for calculating a gross total mass equal to the ratio between the estimated longitudinal force and the longitudinal acceleration, and means for time smoothing the gross total mass from the calculation means.

[0023] The invention also relates to a vehicle comprising means for determining the torque applied to the vehicle's wheels, means for determining the vehicle's longitudinal acceleration, and a device for determining the vehicle's total mass according to the invention, capable of receiving data from the means for determining the vehicle's torque and longitudinal acceleration. These means for determining the vehicle's torque and longitudinal acceleration are, for example, sensors or estimators installed in the vehicle.

[0024] The determination device according to the invention and the vehicle according to the invention have advantages similar to those of the determination method according to the invention.

[0025] Other features and advantages of the invention will become apparent from the following description on the one hand, and from several illustrative and non-limiting examples of embodiments given by reference to the accompanying schematic drawings on the other hand, in which:

[0026] [Fig-1] represents a vehicle according to the invention, comprising sensors and / or estimators as well as a device for determining the mass of the vehicle according to the invention, in one embodiment of the invention, and

[0027] [Fig.2] represents steps in a process for determining the mass of the vehicle of [Fig.1] according to the invention, in one embodiment of the invention.

[0028] According to one embodiment of the invention, a vehicle 2 represented in [Fig.1] comprises a set 20 of sensors and / or estimators whose outputs are sent on a computer bus of the vehicle 2, also called CAN bus (for the English "Controller Area Network").

[0029] This assembly 20 may include in particular an estimator of a slope a, in degrees, of the road on which the vehicle 2 travels, a sensor of a longitudinal speed Vx of the vehicle 2, a sensor of a lateral acceleration ay of the vehicle 2, a sensor of a longitudinal acceleration ax of the vehicle 2 and a sensor of a torque Cx applied to the wheels of the vehicle 2.

[0030] The vehicle 2 also includes a device 1 according to the invention for determining the total mass M of the vehicle 2, implementing a method for determining 100 (shown [Fig. 2]) the total mass M of the vehicle 2 according to the invention, using both software and hardware. The determination device 1 is, for example, the main computer of the vehicle 2. It includes, in particular, receiving means 10 of the values ​​provided by the set 20 of sensors and / or estimator on the CAN bus, at least one processor, a random access memory and a read-only memory in which is stored a computer program whose instructions, when executed on the processor, allow the determination process 100 to be implemented.

[0031] The read-only memory includes in particular an estimation model 12 of a representative value of a longitudinal force Fx applied to the vehicle 2, a function of a representative value of a torque Cx applied to the wheels of the vehicle 2 and of a representative value of a longitudinal acceleration ax of the vehicle 2.

[0032] In this embodiment of the invention, the representative value of the torque Cx applied to the wheels of vehicle 2 is given by the torque sensor Cx and is expressed, for example, in Newton-meters. Furthermore, the representative value of a longitudinal acceleration ax of vehicle 2 is given by the longitudinal acceleration sensor ax of vehicle 2 and is expressed, for example, in meters per second squared.

[0033] Estimation model 12 implements a neural network with four neuronal layers. In alternative versions, the neural network has more or fewer than four neuronal layers. The neural network has two inputs, one for receiving the torque Cx applied to the wheels of vehicle 2 and the other for receiving the longitudinal acceleration ax of vehicle 2. It provides as output a value representing a longitudinal force Fx applied to vehicle 2, which is here a longitudinal force Fx applied to vehicle 2 expressed in Newtons.

[0034] The estimation model 12 is obtained from a supervised learning phase carried out on a test bench or by a driving campaign in real conditions, on a test vehicle of the same type as vehicle 2. Once this learning phase has been carried out, the estimation model 12 is fixed and stored in the read-only memory of the determination device 1. The estimation model 12 is of course obtained before the vehicle 2 leaves the factory, and is valid for all vehicles of the same model and the same engine.

[0035] During the supervised learning phase, the test vehicle is subjected to different driving conditions and loaded with varying load levels so as to cover a whole range of total mass values ​​for the test vehicle. The different driving conditions encompass a whole range of longitudinal acceleration values ​​for the test vehicle, and a whole range of torque values ​​applied to the wheels of the test vehicle, which are successively applied as input to the neural network. Each different pair of values ​​for one of these torque values ​​and one of these longitudinal acceleration values ​​constitutes an iteration of the supervised learning phase, during which this pair of values ​​is applied as input to the neural network, associated with a ground truth value for the longitudinal force. The resulting force on the vehicle. Ground truth is obtained by multiplying the applied input longitudinal acceleration value by the total mass of the test vehicle during this iteration. This actual mass can be measured statically on a test bench, or determined based on the vehicle's unladen weight and its load (passenger weight, cargo weight, fuel quantity, etc.).

[0036] During each iteration, the longitudinal acceleration value and the torque value applied to the wheels of the test vehicle, which are used as input to the neural network, are taken from the vehicle's CAN bus. These values ​​are generally noisy measurements because they are instantaneous, and their accuracy depends on the location of the corresponding sensors in the vehicle. The axial acceleration value is optionally filtered to attenuate measurement noise when calculating the longitudinal force to be applied as output to the neural network.

[0037] It should be noted that, through this supervised learning phase, the estimation model 12 eliminates errors related to the estimation or measurement of the torque applied to the wheels of the test vehicle and the longitudinal acceleration of the vehicle, since even if the torque applied to the wheels and the longitudinal acceleration available on the CAN bus are not precise, the longitudinal force necessary to determine the total mass of the vehicle is obtained through learning. This is why, during the supervised learning phase, a precise measurement of the total mass of the vehicle is used to calculate the applied longitudinal force output by the neural network.

[0038] The supervised learning phase therefore plays the role of calibrating the torque and acceleration measurements from the CAN bus.

[0039] Returning to the vehicle 2 represented in Figure 1, the determination device 1 also includes, stored in its read-only memory, a determination module 14 of the total mass M of the vehicle 2, capable of dividing the longitudinal force Fx given at the output of the estimation model 12 by the longitudinal acceleration ax provided by the receiving means 10, and an inhibition module 16 of the use of the estimation model 12 when adequate driving conditions are not met.

[0040] We now describe in relation to [Fig.2], the method of determining 100 of the total mass M according to the invention of vehicle 2, carried out during the use of vehicle 2.

[0041] A first step 102 of the determination method 100 comprises, by means of the receiving means 10, receiving the value of the torque Cx applied to the wheels of the vehicle 2 as transmitted on the CAN bus, receiving the value of the longitudinal acceleration ax of the vehicle 2 as transmitted on the CAN bus, and advantageously receiving the slope a of the road on which the vehicle 2 is traveling, the speed longitudinal Vx of vehicle 2 and lateral acceleration ay of vehicle 2, as transmitted on the CAN bus.

[0042] A second, optional step 104 of the determination method 100 is the verification, by the inhibition module 16, of the vehicle's driving conditions. In this second step 104, the inhibition module 16 verifies, in particular, that the vehicle 2 is not in conditions less favorable to the implementation of the method according to the invention, such as a phase of heavy braking, significant lateral dynamics, or a steep incline, before allowing the determination of the total mass M of the vehicle 2. Alternatively, additional conditions are verified before allowing the determination of the total mass M of the vehicle 2, such as a small variation in engine torque or the non-use of an emergency braking device of the vehicle 2.

[0043] When driving conditions are suitable for determining the total mass M of vehicle 2, the inhibition module 16 sets an indicator S to 1, indicating that the determination of the total mass M of vehicle 2 is authorized; otherwise, the inhibition module 16 sets this indicator S to 0. In other words, the indicator S remains at zero as long as:

[0044] - the slope a on which vehicle 2 travels is greater in absolute value than a predetermined angle, for example set at 5 degrees: I al < 5, and / or - a ratio in absolute value between the longitudinal acceleration ax of vehicle 2 and a lateral acceleration ay of vehicle 2, is less than a predetermined threshold, for example set at 4: <4, and / or N - a deceleration of vehicle 2 is greater than a predetermined braking threshold, for example: | vx( t ) - vx( t- 1) | > 0.015ms 1 in deceleration phase, with t the instant of measurement of the longitudinal velocity Fx.

[0045] The inhibition module 16 then reads, in a third step 106 of the determination process 100, the value of the indicator S, and as long as the indicator S is of zero value (branch N), the inhibition module 16 inhibits, in a step 108, the determination of the total mass M of the vehicle 2. Otherwise, when the value of the indicator S is one (branch Y), the determination process 100 continues with a step 110 of injection of the value of the torque Cx and the longitudinal acceleration a* received during the first step 102, into the input of the estimation model 12, which provides as output a value of a longitudinal force Fx applied to the vehicle 2.

[0046] It should be noted that when the optional second step 104 and third step 106 are not implemented, the first step 102 is followed directly by step 110 of injecting the value of the torque Cx and the longitudinal acceleration ax into the input of the estimation model 12.

[0047] The determination module 14 then determines, during a step 112 of determining the total mass M of the vehicle 2, a total gross mass m(t):

[0048] m(t) = F^x

[0049] Since this gross total mass m(t) fluctuates slightly as a function of time t due to sudden variations in vehicle speed, this determination step 112 may include a time smoothing step 1120 of the gross total mass m(t) so as to obtain the total mass M of the vehicle 2.

[0050] For this, we use, for example, the recursive least squares method applied to the model:

[0051] Fx(t) = m(t)*ax(t) (1)#

[0052] Starting from the initial values ​​m(t = 0) and F(t — 0), with for example = equal to the mass of the vehicle when empty and F(t = 0) = 0.002, F(t) denoting an intermediate variable distinct from the longitudinal force Fx(t) function of time t, the application of recursive least squares allows us to obtain the estimate of the total mass M = m{ t ) by following the following recursive equations (2) and (3):

[0053] =m(t-1) +F(tl)«x(f) (Fx(t) -m(t-ï)ax(t)) (2)#

[0054] O. F(t) = F(t-1)

[0055] The total mass M = m(t) obtained is almost constant after convergence of this filter temporal, and is read into the main computer to be provided to the vehicle's driver assistance systems 2.

[0056] As an example, for a vehicle with a total mass of 2000 kg, the invention allows an estimation of the total mass of the vehicle with an accuracy of 5%, in less than ten seconds, and before the vehicle reaches 10 m.s*. In other words, even at startup with a large variation in speed, the recursive least squares algorithm converges very quickly.

[0057] Alternatively, the determination step 112 does not include a time smoothing step 1120, for example the determination step 112 is implemented only during phases where the speed of the vehicle is quasi-static, so as to obtain a gross total mass m(t) quasi-constant and taken as the total mass M of the vehicle.

[0058] Of course, the invention is not limited to the examples just described, and many modifications can be made to these examples without departing from the scope of the invention. In particular, the features of the different embodiments can be combined to carry out the invention, provided that these embodiments are not incompatible with each other.

Claims

Demands

1. Method for determining (100) a total mass (M) of a vehicle (2), comprising steps of: - receiving (102) a representative value of a torque (Cx) applied to the wheels of the vehicle (2), - receiving (102) a representative value of a longitudinal acceleration of the vehicle (2), the method of determination (100) being characterized in that it further comprises steps of: - injecting (110) the representative values ​​of a torque (Cx) and a longitudinal acceleration (a*) into an estimation model (12) of a representative value of a longitudinal force (Fx) applied to the vehicle (2), and - determining (112) the total mass (M) of the vehicle (2) as a function of the representative value of the longitudinal force (F*) estimated by the estimation model (12) and the representative value of the longitudinal acceleration (a<).

2. Method for determining (100) a total mass (M) of a vehicle (2) according to claim 1, wherein the estimation model (12) is derived from a supervised learning phase, implemented prior to the execution of the determination method (100).

3. Method for determining (100) a total mass (M) of a vehicle (2) according to claim 2, wherein the estimation model (12) is a neural network having as inputs at least the representative value of the torque (Cx) and the representative value of the longitudinal acceleration (a*), and as output the representative value of the longitudinal force (Fx).

4. A method for determining (100) the total mass (M) of a vehicle (2) according to any one of claims 1 to 3, wherein the determination step (112) comprises calculating a gross total mass equal to the ratio between the estimated longitudinal force (Fx) and the longitudinal acceleration

5. Method for determining (100) a total mass (M) of a vehicle (2) according to claim 4, wherein the determination step (112) includes a time-smoothing step (1120) of the calculated gross total mass.

6. A method for determining (100) the total mass (M) of a vehicle (2) according to any one of claims 1 to 5, comprising an inhibition step (108) of the determination step (112) when at least one of the following conditions is met: - a slope on which the vehicle (2) is traveling is determined to be greater than a predetermined angle, - an absolute value ratio between the longitudinal acceleration (ax) of the vehicle (2) and a lateral acceleration (a>) of the vehicle (2) is determined to be less than a predetermined threshold, and - a deceleration of the vehicle (2) is determined to be greater than a predetermined braking threshold.

7. Device for determining (1) a total mass (M) of a vehicle (2), comprising: - means for receiving (10) a representative value of a torque (Cv) applied to the wheels of the vehicle (2), - means for receiving (10) a representative value of a longitudinal acceleration (ax) of the vehicle (2), the device for determining (1) being characterized in that it further comprises: - an estimation model (12) of a representative value of a longitudinal force (Fx) applied to the vehicle (2), capable of receiving as input the representative values ​​of a torque (C'r) and a longitudinal acceleration (ax\ and - means for determining (14) the total mass (M) of the vehicle (2) as a function of the representative value of the longitudinal force (Fx) estimated by the estimation model (12), and of the representative value of the longitudinal acceleration (ax).

8. Device for determining (1) a total mass (M) of a vehicle (2) according to claim 7, wherein the estimation model (12) is a trained neural network having as inputs at least the representative value of the torque (Cr) and the representative value of the longitudinal acceleration (ax\ and as output the representative value of the longitudinal force (F*).

9. Device for determining (1) the total mass (M) of a vehicle (2) according to claim 7 or 8, wherein the determining means comprise means for calculating a gross total mass equal to the ratio between the estimated longitudinal force (Fx) and the longitudinal acceleration (ax), and means of temporal smoothing of the total gross mass from the computing means.

10. Vehicle (2) comprising means for determining (20) a torque (€'x) applied to the wheels of the vehicle (2), means for determining (20) a longitudinal acceleration (ax) of the vehicle (2), and a device for determining (1) a total mass (M) of the vehicle (2) according to any one of claims 7 to 9, capable of receiving data from the means for determining (20) the torque (Cx) and the longitudinal acceleration (ax) of the vehicle (2).

Images