Clamping force estimation method, device and vehicle

Abstract

The application discloses a clamping force estimation method and device and a vehicle, and relates to the technical field of automobile brake control. The method comprises the following steps: acquiring current caliper position information; inputting the current caliper position information into a clamping force estimation model to obtain the clamping force corresponding to the current caliper position information. In this way, the clamping force can be obtained by inputting the current caliper position information of the caliper friction plate into the clamping force estimation model, thereby avoiding the problem that the clamping force can be obtained only by using an expensive and high-installation clamping force sensor in the prior art. Even in the case that the technical cost and the production cost are both low, the electronic mechanical brake system can still realize precise control over the vehicle.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automobile brake control, in particular to a clamping force estimation method and device and vehicle. BACKGROUND

[0002] With the popularity of vehicle intelligence and electrification, the electromechanical brake system (EMB) has become an important research direction in the field of automobile brake control technology, replacing the electro-hydraulic brake system, due to its high linearity, four-wheel independent control, and low noise, etc. In the process of completing the brake through the electromechanical brake system, the brake force at the wheel end of the vehicle needs to be known, which is closely related to the different clamping forces applied to the caliper friction plate.

[0003] In related technologies, the size of the clamping force can be measured by a clamping force sensor in theory. However, since the clamping force sensor is expensive and has very high installation requirements, it is actually difficult to install the clamping force sensor into the electromechanical brake system, so the size of the clamping force cannot be accurately measured, which will affect the accurate control of the electromechanical brake system on the vehicle. SUMMARY

[0004] The present application provides a clamping force estimation method and device and vehicle, which can realize accurate control of the electromechanical brake system on the vehicle at a low technical cost and production cost.

[0005] The present application discloses the following technical solutions:

[0006] In a first aspect, the present application provides a clamping force estimation method, which comprises:

[0007] obtaining current caliper position information;

[0008] inputting the current caliper position information into a clamping force estimation model to obtain a clamping force corresponding to the current caliper position information.

[0009] Optionally, the clamping force estimation model is constructed by the following method:

[0010] obtaining a caliper initial position;

[0011] In the stroke increasing direction, the positive torque information corresponding to the current positive position information is obtained every preset distance, the positive position information being the caliper initial position, and the sum of the number of times and the product of the preset distance; in the stroke decreasing direction, the negative torque information corresponding to the current negative position information is obtained every preset distance, the negative position information being the caliper initial position, and the difference between the number of times and the product of the preset distance.

[0012] obtaining clamping force information corresponding to positive torque information and negative torque information, the positive torque information and the negative torque information being torque information of equal distance and opposite directions from the initial position of the caliper;

[0013] training a neural network model with the positive torque information and the negative torque information as inputs and the clamping force information as output, to obtain a clamping force estimation model.

[0014] Optionally, the obtaining of the clamping force information corresponding to the positive torque information and the negative torque information comprises:

[0015] averaging the positive torque information and the negative torque information to obtain average torque information;

[0016] obtaining the clamping force information corresponding to the positive torque information and the negative torque information by dividing the product of the average torque information and the transmission ratio by the equivalent radius of the transmission structure ball screw.

[0017] Optionally, the obtaining of the clamping force information corresponding to the positive torque information and the negative torque information comprises:

[0018] averaging the positive torque information and the negative torque information to obtain average torque information;

[0019] obtaining comprehensive torque information according to the average torque information and static friction equivalent torque information, the static friction equivalent torque information being related to motor output revolutions;

[0020] obtaining comprehensive clamping force information corresponding to the comprehensive torque information;

[0021] The training of the neural network model with the positive torque information and the negative torque information as inputs and the clamping force information as output comprises:

[0022] training the neural network model with the comprehensive torque information as input and the comprehensive clamping force information as output.

[0023] Optionally, the training of the neural network model with the comprehensive torque information as input and the comprehensive clamping force information as output comprises:

[0024] training the neural network model with the comprehensive torque information as input and the comprehensive clamping force information as output if the size of the comprehensive clamping force information is less than or equal to a preset threshold.

[0025] Optionally, the method further comprises:

[0026] input the clamp force estimation model with the verification clamp position information to obtain verification clamp force corresponding to the verification clamp position information;

[0027] If the difference between the actual clamp force corresponding to the verification clamp position information and the verification clamp force is greater than or equal to a first preset threshold, it is determined that the operation is abnormal.

[0028] If the number of times of determining that the operation is abnormal is greater than a second preset threshold, the initial position of the clamp is re-executed.

[0029] Optionally, the method further comprises:

[0030] When the current positive position information or the current negative position information reaches a preset position, if the motor speed fluctuation within a preset time is higher than a third preset threshold, it is determined that the operation is abnormal.

[0031] If the number of times of determining that the operation is abnormal is greater than a fourth preset threshold, the initial position of the clamp is re-executed.

[0032] Optionally, the method further comprises:

[0033] If the absolute value of the difference between the positive torque information and the negative torque information is greater than the maximum value of all positive torque information and negative torque information, it is determined that the operation is abnormal.

[0034] If the number of times of determining that the operation is abnormal is greater than a fifth preset threshold, the initial position of the clamp is re-executed.

[0035] Optionally, the current clamp position information is related to current torque data, and the current torque data is the product of the motor torque coefficient and the current motor q-axis current.

[0036] In a second aspect, the application provides a clamp force estimation device, which comprises an information acquisition module and a model output module.

[0037] The information acquisition module is configured to acquire current clamp position information.

[0038] The model output module is configured to input the current clamp position information into a clamp force estimation model to obtain clamp force corresponding to the current clamp position information.

[0039] Optionally, the clamp force estimation model is constructed by the following modules:

[0040] The first acquisition module is configured to acquire the initial position of the clamp.

[0041] The second acquisition module is configured to acquire positive torque information corresponding to current positive position information every preset distance in a stroke increasing direction, the positive position information being the caliper initial position, and a sum of a product of the number of acquisitions and the preset distance; and acquire negative torque information corresponding to current negative position information every preset distance in a stroke decreasing direction, the negative position information being the caliper initial position, and a difference of a product of the number of acquisitions and the preset distance.

[0042] The third acquisition module is configured to acquire clamping force information corresponding to the positive torque information and the negative torque information, the positive torque information and the negative torque information being torque information with equal distances and opposite directions from the caliper initial position.

[0043] The model construction module is configured to train a neural network model by taking the positive torque information and the negative torque information as input and taking the clamping force information as output, to obtain a clamping force estimation model.

[0044] Optionally, the third acquisition module specifically includes a first acquisition submodule and a second acquisition submodule.

[0045] The first acquisition submodule is configured to take an average of the positive torque information and the negative torque information to obtain average torque information.

[0046] The second acquisition submodule is configured to obtain clamping force information corresponding to the positive torque information and the negative torque information by dividing a product of the average torque information and a transmission ratio by an equivalent radius of a transmission structure ball screw.

[0047] Optionally, the third acquisition module specifically includes a third acquisition submodule, a fourth acquisition submodule, and a fifth acquisition submodule.

[0048] The third acquisition submodule is configured to take an average of the positive torque information and the negative torque information to obtain average torque information.

[0049] The fourth acquisition submodule is configured to acquire comprehensive torque information according to the average torque information and static friction equivalent torque information, the static friction equivalent torque information being related to motor output revolutions.

[0050] The fifth acquisition submodule is configured to acquire comprehensive clamping force information corresponding to the comprehensive torque information.

[0051] The model training module is configured to train a neural network model by taking the comprehensive torque information as input and taking the comprehensive clamping force information as output.

[0052] Optionally, the model training module is specifically configured to, if the size of the comprehensive clamping force information is less than or equal to a preset threshold, train a neural network model by taking the comprehensive torque information as input and the comprehensive clamping force information as output.

[0053] Optionally, the device further comprises a verification input module, a first abnormality determination module and a first re-execution module.

[0054] The verification input module is configured to input verification caliper position information into the clamping force estimation model to obtain verification clamping force corresponding to the verification caliper position information.

[0055] The first abnormality determination module is configured to determine that an operation is abnormal if a difference between the actual clamping force corresponding to the verification caliper position information and the verification clamping force is greater than or equal to a first preset threshold.

[0056] The first re-execution module is configured to re-execute the acquisition of the initial position of the caliper if the number of times of determining that the operation is abnormal is greater than a second preset threshold.

[0057] Optionally, the device further comprises a second abnormality determination module and a second re-execution module.

[0058] The second abnormality determination module is configured to determine that an operation is abnormal if a motor speed fluctuation within a preset time is higher than a third preset threshold when the current forward position information or the current reverse position information reaches a preset position.

[0059] The second re-execution module is configured to re-execute the acquisition of the initial position of the caliper if the number of times of determining that the operation is abnormal is greater than a fourth preset threshold.

[0060] Optionally, the device further comprises a third abnormality determination module and a third re-execution module.

[0061] The third abnormality determination module is configured to determine that an operation is abnormal if an absolute value of a difference between the forward torque information and the reverse torque information is greater than a maximum value of all forward torque information and reverse torque information.

[0062] The third re-execution module is configured to re-execute the acquisition of the initial position of the caliper if the number of times of determining that the operation is abnormal is greater than a fifth preset threshold.

[0063] Optionally, the current caliper position information is related to current torque data, and the current torque data is a product of a motor torque coefficient and a current motor q-axis current.

[0064] In a third aspect, the present application provides a vehicle comprising the clamp force estimation device according to the second aspect, wherein the clamp force estimation device is configured to execute the clamp force estimation method according to the first aspect.

[0065] Compared with the prior art, the present application has the following beneficial effects:

[0066] The present application provides a clamp force estimation method, device and vehicle, which comprises: acquiring current caliper position information; inputting the current caliper position information into a clamp force estimation model to obtain the clamp force corresponding to the current caliper position information. Thus, by inputting the current caliper position information of the caliper friction plate into the clamp force estimation model, the clamp force can be obtained, which avoids the problem that in the related art, the clamp force can only be obtained by using an expensive clamp force sensor with high installation requirements, and even in the case of low technical cost and production cost, the electronic mechanical brake system can still achieve precise control of the vehicle. BRIEF DESCRIPTION OF DRAWINGS

[0067] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0068] Figure 1 A flowchart of a clamp force estimation method provided by an embodiment of the present application;

[0069] Figure 2 A structural schematic diagram of an electronic mechanical brake system provided by an embodiment of the present application;

[0070] Figure 3 A schematic diagram of a system for realizing stroke control provided by an embodiment of the present application;

[0071] Figure 4 A schematic diagram of the relationship between stroke information and clamp force provided by an embodiment of the present application;

[0072] Figure 5 A schematic diagram of the relationship between stroke information and clamp force provided by another embodiment of the present application;

[0073] Figure 6 A schematic diagram of the relationship between stroke information and clamp force of different friction plates provided by an embodiment of the present application;

[0074] Figure 7 A flowchart of verification of the difference between stroke information and torque information provided by an embodiment of the present application;

[0075] Figure 8 A flowchart of a travel stability verification disclosed by an embodiment of the present application;

[0076] Figure 9 A schematic diagram of a clamping force estimation device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0077] As described above, with the popularity of vehicle intelligence and electrification, the electronic mechanical brake system, with its high linearity, four-wheel independent control, and low noise, etc., has replaced the electro-hydraulic brake system and become an important research direction in the field of automobile brake control technology.

[0078] The difference between the electronic mechanical brake system and the electro-hydraulic brake system lies in the execution structure of the clamping and release of the caliper. Due to space limitations, the electronic mechanical brake system is suitable for using a wheel-end permanent magnet synchronous motor and a transmission mechanism with a high power density ratio to realize the clamping and release of the caliper. After the friction plate and brake disc model of the caliper is determined, the size of the braking force is directly related to the clamping force. At present, the size of the clamping force can be measured by a clamping force sensor in theory.

[0079] However, due to the high price and high installation requirements of the clamping force sensor, it is actually difficult to install the clamping force sensor into the electronic mechanical brake system, so the size of the clamping force cannot be accurately measured, which will affect the accurate control of the electronic mechanical brake system on the vehicle.

[0080] Therefore, the present application provides a clamping force estimation method and device and a vehicle. The method comprises: obtaining current caliper position information; inputting the current caliper position information into a clamping force estimation model to obtain a clamping force corresponding to the current caliper position information. In this way, by inputting the current caliper position information of the caliper friction plate into the clamping force estimation model, the clamping force can be obtained, thereby avoiding the problem that in the related art, the clamping force can only be obtained by using a clamping force sensor with high price and high installation requirements. Even in the case of low technical cost and low production cost, the electronic mechanical brake system can still achieve accurate control of the vehicle.

[0081] In order for those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described in detail below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0082] Reference Figure 1The figure is a flowchart of a clamping force estimation method provided in an embodiment of this application. The method includes:

[0083] S101: Obtain motor torque and stroke data.

[0084] First, it is necessary to obtain the motor's torque and stroke data. (See...) Figure 2 This figure is a schematic diagram of the structure of an electromechanical braking system provided in an embodiment of this application. It can be achieved through, as shown in... Figure 2 The electromechanical braking system shown acquires the motor's torque information and stroke data.

[0085] The stroke data refers to the stroke value of the caliper at a certain moment. Torque refers to the average torque output from the crankshaft end when the motor is running. Since there is no direct sensor for the motor torque, but the motor torque is related to the q-axis current of the motor, the torque data of the motor driven by the sine wave can be calculated by the following formula (1):

[0086] T motor =K T *i q (1)

[0087] Among them, T motor For torque data, K T i is the motor torque coefficient. q Let q be the q-axis current of the motor.

[0088] S102: Determine the initial position of the caliper by matching the torque data with the stroke data.

[0089] After obtaining the motor's torque and stroke data, the correspondence between the torque and stroke information can be determined, and the initial position of the caliper, i.e., the zero position of the friction plate, can be obtained based on the correspondence.

[0090] In some specific implementations, the motor needs to first clamp the brake pad with a first torque T1 to obtain the corresponding first motor stroke value P1, then clamp the brake pad with a second torque T2 = 1 / 2T1 to obtain the corresponding second motor stroke value P2, and finally clamp the brake pad with a third torque T3 = 1 / 4T1 to obtain the corresponding third motor stroke value P3. Subsequently, to reduce the influence of static friction, the initial position of the caliper can be obtained using the difference method. For example, the initial position of the caliper can be calculated using the following formula (2):

[0091]

[0092] Wherein, P0 is the caliper initial position, P1 is the first motor stroke value, P2 is the second motor stroke value, P3 is the third motor stroke value, T1 is the first torque, T2 is the second torque, and T3 is the third torque.

[0093] S103: In the stroke advancing direction, the positive torque information corresponding to the current positive position information is obtained every preset distance; in the stroke retreating direction, the negative torque information corresponding to the current negative position information is obtained every preset distance.

[0094] Since the caliper initial position has been obtained through the S102 step, the torque information corresponding to the current position information can be obtained every preset distance Δ based on the initial position. It can be understood that the above-mentioned current position information refers to the sum or difference of the caliper initial position and the product of the preset distance Δ and the number of times of acquisition.

[0095] That is, the electromechanical brake system needs to perform stroke control every preset distance Δ in the stroke advancing (increasing) direction. When the stroke control reaches a steady state, the current positive position information (φ +1 , φ +2 , φ +3 ,…, φ +m ) can be obtained. Subsequently, the positive torque information (T +1 , T +2 , T +3 ,…, T +m ) corresponding to the current positive position information is read again, and the positive torque information T +1 , T +2 , T +3 ,…, T +m forms a positive control torque group.

[0096] Then, the electromechanical brake system needs to perform stroke control again every preset distance Δ in the stroke retreating (decreasing) direction. When the stroke control reaches a steady state, the current negative position information (φ -m ,…, φ -3 , φ -2 , φ -1 ) can be obtained. Subsequently, the negative torque information (T -m , …, T -3 , T -2 , T -1 ) corresponding to the current negative position information is read again, and the negative torque information T -m , …, T -3 , T -2 , T -1 forms a negative control torque group.

[0097] Referring toFigure 3 FIG. 1 is a schematic diagram of a system for implementing stroke control according to an embodiment of the present application. Stroke control can be achieved by the structure shown in FIG. 1. Figure 3 It should be noted that the specific stroke control method is not limited in the present application.

[0098] S104: Obtain the clamping force corresponding to the motor torque according to the positive control torque group and the negative control torque group.

[0099] In some specific implementations, in order to obtain the clamping force corresponding to the motor torque, two torque information with equal distance and opposite direction from the initial position of the caliper can be first averaged. Specifically, the formula for obtaining the average torque information can be shown in the following formula (3):

[0100]

[0101] wherein T n is the average torque information, T +n is the positive torque information, and T -n is the negative torque information.

[0102] Subsequently, according to the system transmission characteristics, the corresponding clamping force can be obtained based on the average torque information. Specifically, the formula for obtaining the clamping force through the average torque information can be shown in the following formula (4):

[0103]

[0104] wherein F Caliper is the clamping force, η is the transmission ratio, r is the equivalent radius of the transmission structure ball screw, and T n is the average torque information.

[0105] Referring to FIG. 2, which is a schematic diagram of the relationship between stroke information and clamping force according to an embodiment of the present application. As shown in FIG. 2, the size of the stroke information is positively correlated with the size of the clamping force. Figure 4 It can be understood that the positive clamping force can be first obtained according to the positive torque information, and then the negative clamping force can be obtained according to the negative torque information. Subsequently, the final clamping force information can be obtained by averaging the negative clamping force and the negative clamping force. Referring to FIG. 3, which is another schematic diagram of the relationship between stroke information and clamping force according to an embodiment of the present application. The first curve is the curve corresponding to the stroke information and the positive clamping force, and the second curve is the curve corresponding to the stroke information and the negative clamping force. It should be noted that the specific clamping force obtaining method is not limited in the present application. Figure 4 Figure 5

[0106] ​​It should be noted that the above method of obtaining the clamping force is only through the clamping force equivalent moment information. However, in the actual situation, the static friction force existing in the electromechanical brake system has a great influence on the calculation of the clamping force, so the static friction equivalent torque information can also be considered in the direction of increasing and decreasing stroke, and the clamping force equivalent torque information and the static friction equivalent torque information are integrated into comprehensive torque information, and the corresponding clamping force is obtained according to the comprehensive torque information, so as to reduce the error.

[0107] For example, the positive torque information considering the static friction equivalent torque (i.e. positive comprehensive torque information) can be shown in the following formula (5):

[0108] T +n’ =T n +T friction (5)

[0109] Wherein, T +n’ is the positive comprehensive torque information, T n is the average torque information, and T friction is the static friction equivalent torque.

[0110] Similarly, the negative torque information considering the static friction equivalent torque (i.e. negative comprehensive torque information) can be shown in the following formula (6):

[0111] T -n’ =T n -T friction (6)

[0112] Wherein, T -n’ is the negative comprehensive torque information, T n is the average torque information, and T friction is the static friction equivalent torque.

[0113] Specifically, the above static friction equivalent torque can be obtained by the following formula (7):

[0114]

[0115] Wherein, T e is the motor output revolution, w is the mechanical angular velocity, J is the motor rotational inertia, D is the rotational damping coefficient, T l is the equivalent clamping force torque at the motor end, which is equal to the average torque information T n , φ trend is the stroke trend, if the stroke increases, the trend sgn(φ trend ) = 1, if the stroke decreases, the trend sgn(φ trend ) = -1.

[0116] And, the positive comprehensive torque information and the negative comprehensive torque information can be added and then averaged, and the corresponding clamping force is calculated based on the average value. The specific obtaining method is shown in formulas (3) and (4), which will not be described here.

[0117] Referring to Figure 6 FIG. 3 is a schematic diagram of the relationship between the stroke information of different friction plates and the clamping force according to an embodiment of the present application. As shown in FIG. 3, the abscissa represents the stroke information of the friction plate, and the ordinate represents the clamping force of the friction plate. Figure 6 As can be seen, as the wear degree of the friction plate increases, the clamping force of the friction plate under the same stroke also increases. Therefore, if the clamping force calculated by the above formula is lower than or equal to the preset threshold value, it means that the friction plate can continue to be used, and the clamping force estimation model can be trained based on all information corresponding to the friction plate.

[0118] In some specific implementations, after obtaining all the above position information, torque information and stroke direction, a table corresponding to the position information and the torque information can be made for backup. As shown in Table 1, the table is a table corresponding to the position information and the torque information according to an embodiment of the present application.

[0119] Table 1

[0120]

[0121]

[0122] S105: Training the neural network model with the current position information as the input and the clamping force as the output to obtain the clamping force estimation model.

[0123] After obtaining the current position information and the corresponding clamping force, the neural network model is trained with the current position information as the input and the corresponding clamping force as the output to obtain the clamping force estimation model.

[0124] It can be understood that if the static friction equivalent torque is considered, the comprehensive torque information is used as the input, the comprehensive clamping force information is used as the output, and the neural network model is trained to obtain the clamping force estimation model. The present application does not limit this.

[0125] S106: Difference verification of stroke information and torque information, stroke stability verification, and / or friction plate wear degree verification are performed on the clamping force estimation model.

[0126] To ensure the accuracy of the training result, after the clamping force estimation model is trained, the clamping force estimation model needs to be verified again. For example, one or more of the following difference verification of stroke information and torque information, stroke stability verification, and friction plate wear degree verification can be performed on the clamping force estimation model. If the test passes, the above clamping force estimation model can be put into use.

[0127] See Figure 7 This figure is a flowchart illustrating the difference verification of stroke information and torque information disclosed in an embodiment of this application. Specifically, the difference verification of stroke information and torque information refers to the fact that, since the stroke step length is a preset distance Δ, the position information shown in Table 1 is known. The controller can input the position information in Table 1 as the verification caliper position information into the clamping force estimation model to obtain the verification clamping force corresponding to the verification caliper position information. Subsequently, it is determined whether the difference between the actual clamping force sampled by the motor and the verification clamping force is less than a first preset threshold. If it is less than the first preset threshold, the clamping force estimation model is determined to have been successfully trained. If it is greater than or equal to the first preset threshold, an operation abnormality is determined. If the number of operation abnormality determinations exceeds a second preset threshold, the clamping force estimation model is determined to have failed to train, and the initial position of the caliper needs to be reacquired. It should be noted that the above-mentioned second preset threshold can be 3, 4, etc., and this application does not limit the specific first and second preset thresholds.

[0128] See Figure 8 This figure is a flowchart of a stroke stability verification method disclosed in an embodiment of this application. Specifically, stroke stability verification refers to determining whether the motor speed is stable after reaching the position corresponding to the preset target stroke information, that is, if the current positive or negative position information reaches the preset position, thus determining that the controller's stroke control has reached a stable state. Specifically, if the motor speed fluctuation at the sampling time is greater than the third preset threshold within a set time, the sampling within this stroke range is abnormal, the motor torque sampling result is discarded, and the operation is judged to be abnormal. If the number of discards is greater than the fourth preset threshold, or the number of times the operation is judged to be abnormal is greater than the fourth preset threshold, the clamping force estimation model training is judged to have failed, and the initial position of the caliper needs to be obtained again. It should be noted that the above-mentioned third preset threshold can be 50 rpm (revolutions per minute), etc., and the above-mentioned fourth preset threshold can be 3, 4, etc. This application does not limit the specific third and fourth preset thresholds.

[0129] Specifically, the friction plate wear verification refers to obtaining the torque information corresponding to each position after reaching the position information in Table 1, and calculating whether the absolute value of the difference between the positive torque information and the negative torque information is greater than the maximum value of all torque information. If so, the sampling is abnormal, the motor torque sampling result is discarded, and the operation is judged to be abnormal. If the number of discards is greater than the fifth preset threshold, or the number of times the operation is judged to be abnormal is greater than the fifth preset threshold, the clamping force estimation model is judged to have failed to train, and the initial position of the caliper needs to be obtained again. It should be noted that the above-mentioned fifth preset threshold can be 3, 4, etc., and this application does not limit the specific fifth preset threshold.

[0130] In addition, other kinds of verifications can be performed. For example, it can be determined whether two adjacent situations exist on all position information where training fails. If yes, it is determined that the clamping force estimation model training fails, and the initial position of the caliper needs to be reacquired.

[0131] Alternatively, it can be determined whether the number of training failures on all position information exceeds n / 3. If yes, it is determined that the clamping force estimation model training fails, and the initial position of the caliper needs to be reacquired. n is the number of single direction calibration.

[0132] Alternatively, it can be determined whether the difference between the clamping force corresponding to any positive torque information and the clamping force corresponding to the torque information of the initial position of the caliper is greater than a sixth preset threshold value, or whether the difference between the clamping force corresponding to any negative torque information and the clamping force corresponding to the torque information of the initial position of the caliper is greater than a sixth preset threshold value. If no, it is determined that the clamping force estimation model training fails, and the initial position of the caliper needs to be reacquired. It should be noted that the specific sixth preset threshold value is not limited in the present application.

[0133] S107: inputting the current caliper position information into the clamping force estimation model to obtain the clamping force corresponding to the current caliper position information.

[0134] At any time after the establishment of the clamping force estimation model, the current caliper position information can be acquired, and the clamping force corresponding to the current caliper position information can be obtained by inputting the caliper position information into the clamping force estimation model.

[0135] In summary, the present application discloses a clamping force estimation method. The clamping force can be obtained by inputting the current caliper position information of the caliper friction plate into the clamping force estimation model, thereby avoiding the problem that the clamping force sensor must be used in the related art to obtain the clamping force, which is expensive and has high installation requirements. Even in the case of low technical cost and low production cost, the electronic mechanical brake system can still achieve precise control of the vehicle. Moreover, a series of stroke angles of the motor can be given by the controller, and the influence of dynamic and static friction can be removed by the successive and positive and negative direction method, and combined with the corresponding operation strategy, thereby achieving precise control of the vehicle by the electronic mechanical brake system.

[0136] Referring to Figure 9 , the figure is a clamping force estimation device provided by an embodiment of the present application. The clamping force estimation device 900 comprises an information acquisition module 901 and a model output module 902.

[0137] Specifically, the information acquisition module 901 is configured to acquire current caliper position information; and the model output module 902 is configured to input the current caliper position information into the clamping force estimation model to obtain the clamping force corresponding to the current caliper position information.

[0138] Optionally, the clamp force estimation model is constructed by the following modules:

[0139] The first obtaining module is configured to obtain an initial position of the caliper;

[0140] The second obtaining module is configured to obtain positive torque information corresponding to current positive position information every preset distance in the stroke increasing direction, the positive position information being the initial position of the caliper and the sum of the product of the number of times of obtaining and the preset distance; and obtain negative torque information corresponding to current negative position information every preset distance in the stroke decreasing direction, the negative position information being the initial position of the caliper and the difference of the product of the number of times of obtaining and the preset distance;

[0141] The third obtaining module is configured to obtain clamp force information corresponding to the positive torque information and the negative torque information, the positive torque information and the negative torque information being torque information with equal distance and opposite directions from the initial position of the caliper;

[0142] The model construction module is configured to take the positive torque information and the negative torque information as input and take the clamp force information as output to train a neural network model to obtain the clamp force estimation model.

[0143] Optionally, the third obtaining module specifically includes a first obtaining submodule and a second obtaining submodule.

[0144] Specifically, the first obtaining submodule is configured to average the positive torque information and the negative torque information to obtain average torque information; and the second obtaining submodule is configured to obtain the clamp force information corresponding to the positive torque information and the negative torque information by multiplying the average torque information by the transmission ratio and dividing the result by the equivalent radius of the transmission structure ball screw.

[0145] Optionally, the third obtaining module specifically includes a third obtaining submodule, a fourth obtaining submodule and a fifth obtaining submodule.

[0146] Specifically, the third obtaining submodule is configured to average the positive torque information and the negative torque information to obtain average torque information; the fourth obtaining submodule is configured to obtain comprehensive torque information according to the average torque information and static friction equivalent torque information, the static friction equivalent torque information being related to the motor output revolutions; and the fifth obtaining submodule is configured to obtain comprehensive clamp force information corresponding to the comprehensive torque information.

[0147] Therefore, the model training module is configured to take the comprehensive torque information as input and take the comprehensive clamp force information as output to train a neural network model.

[0148] Optionally, the model training module is specifically configured to train the neural network model by taking the comprehensive torque information as input and the comprehensive clamping force information as output if the size of the comprehensive clamping force information is less than or equal to a preset threshold.

[0149] Optionally, the device further comprises a verification input module, a first abnormality determination module and a first re-execution module.

[0150] Specifically, the verification input module is configured to input the verification caliper position information into the clamping force estimation model to obtain verification clamping force corresponding to the verification caliper position information; the first abnormality determination module is configured to determine that the operation is abnormal if a difference between the actual clamping force corresponding to the verification caliper position information and the verification clamping force is greater than or equal to a first preset threshold; and the first re-execution module is configured to re-execute the acquisition of the initial position of the caliper if the number of times of determining that the operation is abnormal is greater than a second preset threshold.

[0151] Optionally, the device further comprises a second abnormality determination module and a second re-execution module.

[0152] Specifically, the second abnormality determination module is configured to determine that the operation is abnormal if the motor speed fluctuation within a preset time is higher than a third preset threshold when the current positive position information or the current negative position information reaches a preset position; and the second re-execution module is configured to re-execute the acquisition of the initial position of the caliper if the number of times of determining that the operation is abnormal is greater than a fourth preset threshold.

[0153] Optionally, the device further comprises a third abnormality determination module and a third re-execution module.

[0154] Specifically, the third abnormality determination module is configured to determine that the operation is abnormal if an absolute value of a difference between the positive torque information and the negative torque information is greater than a maximum value of all positive torque information and negative torque information; and the third re-execution module is configured to re-execute the acquisition of the initial position of the caliper if the number of times of determining that the operation is abnormal is greater than a fifth preset threshold.

[0155] Optionally, the current caliper position information is related to current torque data, and the current torque data is a product of a motor torque coefficient and a current motor q-axis current.

[0156] In summary, the application discloses a clamping force estimation device, which can obtain the clamping force by inputting the current clamp position information of the clamp friction plate into the clamping force estimation model, thereby avoiding the problem that the clamping force can be obtained only by using an expensive and high installation requirement clamping force sensor in the related art, and achieving precise control of the electronic mechanical brake system on the vehicle even in the case of low technical cost and production cost. Moreover, a series of stroke angles of the motor can be given by the controller, and the influence of the dynamic and static friction can be removed by the method of successive and positive and negative directions, and the corresponding operation strategy is combined, so that precise control of the electronic mechanical brake system on the vehicle is achieved.

[0157] Correspondingly, the application also discloses a vehicle comprising the clamping force estimation device as described in the foregoing embodiments.

[0158] The vehicle provided by the embodiments of the application has the beneficial effects of the clamping force estimation device as described above.

[0159] It should be noted that each of the embodiments in the specification adopts a progressive manner for description, and the same and similar parts between each embodiment can be referred to each other, and each embodiment mainly describes the difference from other embodiments. Especially, the method and vehicle embodiments are basically similar to the method embodiments, so the description is relatively simple, and the related parts can be referred to the part of the method embodiments. The method and vehicle described above are only schematic, and the units described as separate components can be or can not be physically separate, and the components prompted as units can be or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. According to the actual needs, part or all of the modules can be selected to achieve the purpose of the embodiments of the application. Those skilled in the art can understand and implement it without creative labor.

[0160] The above is only a specific embodiment of the application, but the protection scope of the application is not limited to this. Any skilled person in the art can easily think of changes or replacements within the technical range disclosed in the application, which should be covered in the protection scope of the application. Therefore, the protection scope of the application should be subject to the protection scope of the claims.

Claims

1. A clamping force estimation method characterized by, The method comprises: acquiring current caliper position information; inputting the current caliper position information into a clamping force estimation model to obtain clamping force corresponding to the current caliper position information; the clamping force estimation model is constructed by the following method: acquiring caliper initial position; in the increasing direction of stroke, acquiring positive torque information corresponding to the current positive position information every preset distance, the positive position information being the caliper initial position, and the sum of the acquisition times and the product of the preset distance; in the decreasing direction of stroke, acquiring negative torque information corresponding to the current negative position information every preset distance, the negative position information being the caliper initial position, and the difference of the acquisition times and the product of the preset distance; acquiring clamping force information corresponding to the positive torque information and the negative torque information, the positive torque information and the negative torque information being torque information with equal distance and opposite direction from the caliper initial position; training a neural network model with the positive torque information and the negative torque information as input and the clamping force information as output to obtain the clamping force estimation model.

2. The method of claim 1, wherein, The acquiring of the clamping force information corresponding to the positive torque information and the negative torque information comprises: averaging the positive torque information and the negative torque information to obtain average torque information; multiplying the average torque information by the transmission ratio, dividing by the equivalent radius of the transmission structure ball screw to obtain the clamping force information corresponding to the positive torque information and the negative torque information.

3. The method of claim 1, wherein, The acquiring of the clamping force information corresponding to the positive torque information and the negative torque information comprises: averaging the positive torque information and the negative torque information to obtain average torque information; acquiring comprehensive torque information according to the average torque information and static friction equivalent torque information, the static friction equivalent torque information being related to motor output revolutions; acquiring comprehensive clamping force information corresponding to the comprehensive torque information; The training of the neural network model with the positive torque information and the negative torque information as input and the clamping force information as output comprises: training the neural network model with the comprehensive torque information as input and the comprehensive clamping force information as output.

4. The method of claim 3, wherein, The training of the neural network model with the positive torque information and the negative torque information as input and the clamping force information as output comprises: if the size of the comprehensive clamping force information is less than or equal to a preset threshold, training the neural network model with the comprehensive torque information as input and the comprehensive clamping force information as output.

5. The method of claim 1, wherein, The method further comprises: inputting verification caliper position information into the clamping force estimation model to obtain verification clamping force corresponding to the verification caliper position information; if the difference between the actual clamping force corresponding to the verification caliper position information and the verification clamping force is greater than or equal to a first preset threshold, determining that the operation is abnormal; if the number of times of determining that the operation is abnormal is greater than a second preset threshold, re-executing the acquiring of the caliper initial position.

6. The method of claim 1, wherein, The method further comprises: When the current positive position information or the current negative position information reaches a preset position, if the motor speed fluctuation within a preset time is higher than a third preset threshold, it is determined that an operation is abnormal; If the number of times of determining that the operation is abnormal is greater than a fourth preset threshold, the obtaining of the initial position of the caliper is re-executed.

7. The method of claim 1, wherein, The method further comprises: If the absolute value of the difference between the positive torque information and the negative torque information is greater than the maximum value of all positive torque information and negative torque information, it is determined that an operation is abnormal; If the number of times of determining that the operation is abnormal is greater than a fifth preset threshold, the obtaining of the initial position of the caliper is re-executed.

8. The method of claim 1, wherein, The current caliper position information is related to current torque data, and the current torque data is the product of the motor torque coefficient and the current motor q-axis current.

9. A clamp force estimation device characterized by comprising: The device comprises an information acquisition module and a model output module. The information acquisition module is configured to acquire current caliper position information. The model output module is configured to input the current caliper position information into a clamping force estimation model to obtain clamping force corresponding to the current caliper position information; the clamping force estimation model is constructed by the following modules: A first acquisition module is configured to acquire an initial position of a caliper. A second acquisition module is configured to acquire positive torque information corresponding to current positive position information every preset distance in the stroke increasing direction, the positive position information being the initial position of the caliper, and the sum of the number of acquisitions and the product of the preset distance; and acquire negative torque information corresponding to current negative position information every preset distance in the stroke decreasing direction, the negative position information being the initial position of the caliper, and the difference between the number of acquisitions and the product of the preset distance. A third acquisition module is configured to acquire clamping force information corresponding to positive torque information and negative torque information, the positive torque information and the negative torque information being torque information with equal distance and opposite directions from the initial position of the caliper. A model construction module is configured to take the positive torque information and the negative torque information as input, take the clamping force information as output, train a neural network model, and obtain a clamping force estimation model.

10. A vehicle characterized by comprising: The vehicle comprises a clamping force estimation device configured to execute the clamping force estimation method of any one of claims 1-8.

Images