Method for generating estimation model, method for estimating vehicle load and device thereof

Abstract

The present invention discloses a method for generating an estimation model, a method for estimating vehicle load and a device thereof, which comprises the following steps: continuously performing a first operation for multiple times, the first operation specifically being: obtaining the load of the vehicle, and performing a second operation for any tire; the second operation corresponding to the tire specifically being: obtaining the start time of the contact surface and the end time of the contact surface from a first sensor in the tire, obtaining the start time of the contact surface and the end time of the contact surface from a second sensor in the tire, obtaining the contact surface and creating an estimation model. The estimation model can estimate the vehicle load in an efficient and relatively accurate manner.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle load estimation, and in particular to a method for generating an estimation model, a method for estimating vehicle load, and a device thereof. Background Art

[0002] In recent years, with the rapid development of autonomous driving technology and the increase in passenger vehicles, the demand for precise control of vehicle dynamics has gradually increased the quality of the vehicle, and effective vehicle load estimation technology has become increasingly important.

[0003] In order to accurately predict the load condition of the vehicle, the following methods are mainly used: the first type is based on sensor measurement, which mainly makes mass identification simple by installing corresponding sensors on the vehicle; the second type is based on vehicle dynamics, which mainly obtains information such as driving torque, acceleration and vehicle speed from the CAN bus, and processes the data through algorithms such as recursive least squares method and extended Kalman filter to obtain estimated mass. However, the first type of method requires the installation of sensors, which increases the production cost of the vehicle and is difficult to meet the actual needs of the project; the second type of method has high requirements for data quality, which is often difficult to achieve for ordinary vehicles.

[0004] Therefore, designing an efficient and relatively accurate method to estimate vehicle load has become an urgent problem to be solved. Summary of the invention

[0005] In view of this, the main purpose of the present invention is to provide a method for generating an estimation model, a method for estimating vehicle load and a device thereof.

[0006] To achieve the above object, the technical solution of the present invention is implemented as follows: a method for generating an estimation model for vehicle load, wherein the vehicle is provided with N tires , N is a natural number, N ≥ 2; in any tire The inner wall of the tire is provided with a first sensor and a second sensor, and the first and second sensors are distributed along the preset rotation direction of the tire; when the tire When stationary, the first sensor is located at a position Position in a preset rotation direction. When rotating in the preset direction, the arc length of the second sensor is When the second sensor is located at a position Position in a preset rotation direction, i is a natural number, i=1, 2, ..., N; comprising the following steps: controlling each tire to rotate along a preset rotation direction, k=1, continuously performing the first operation M times, M is a natural number, M≥2; the first operation is specifically: obtaining the load of the vehicle , and for any tire The second operation is performed; tire The corresponding second operation is specifically: The starting time when the first sensor in obtains the contact surface is and the end time of the contact surface , from the tire The start time of the second sensor acquiring the contact surface is and the end time of the contact surface , the length of the contact surface in the kth period , , , the value of k increases by 1; based on Create an estimation model.

[0007] As an improvement of an embodiment of the present invention, the estimation model is specifically: a clustering model, a linear regression model, a nonlinear regression model, a support vector machine model, a neural network model or a random forest model.

[0008] As an improvement of the embodiment of the present invention, the estimation model is specifically a multiple linear regression model; the multiple linear regression equation in the multiple linear regression model is: ;Will , , is the noise, and the multivariate linear regression equation is input to obtain the matrix B.

[0009] As an improvement of the embodiment of the present invention, each first sensor and each second sensor is provided with an RC integration circuit; The starting time when the first sensor in obtains the contact surface is and the end time of the contact surface , from the tire The start time of the second sensor acquiring the contact surface is and the end time of the contact surface Specifically including: from tires The first signal is obtained from the RC integration circuit corresponding to the first sensor in the embodiment, and the start time of the contact surface is obtained based on the first signal: and the end time of the contact surface , from the tire The second signal is obtained from the RC integration circuit corresponding to the second sensor in the embodiment, and the start time of the contact surface is obtained based on the second signal: and the end time of the contact surface .

[0010] As an improvement to the embodiment of the present invention, the output signals of the first sensor and the second sensor include: pressure, vibration, deformation, acceleration or temperature.

[0011] The embodiment of the present invention also provides a device for generating an estimation model for vehicle load, wherein the vehicle is provided with N tires. , N is a natural number, N ≥ 2; in any tire The inner wall of the tire is provided with a first sensor and a second sensor, and the first and second sensors are distributed along the preset rotation direction of the tire; when the tire When stationary, the first sensor is located at a position Position in a preset rotation direction. When rotating in the preset direction, the arc length of the second sensor is When the second sensor is located at a position Position in a preset rotation direction, i is a natural number, i=1, 2, ..., N; comprising the following modules: a first information acquisition module, used to control each tire to rotate along a preset rotation direction, k=1, and continuously perform the first operation M times, M is a natural number, M≥2; the first operation is specifically: obtaining the load of the vehicle , and for any tire The second operation is performed; tire The corresponding second operation is specifically: The starting time when the first sensor in obtains the contact surface is and the end time of the contact surface , from the tire The start time of the second sensor acquiring the contact surface is and the end time of the contact surface , the length of the contact surface in the kth period , , , the value of k increases by 1; the model creation module is used to Create an estimation model.

[0012] The embodiment of the present invention also provides a method for estimating vehicle load, wherein the vehicle is provided with N tires. , N is a natural number, N ≥ 2; in any tire The first sensor and the second sensor are arranged on the inner wall of the tire, and the first and second sensors are arranged along the rotation direction of the tire, and the distance between the first and second sensors in the rotation direction is , i is a natural number, i=1, 2, ..., N; comprising the following steps: executing the above generation method to generate an estimation model; for any tire The second operation is performed; tire The corresponding second operation is specifically: The starting time when the first sensor in obtains the contact surface is and the end time of the contact surface , from the tire The start time of the second sensor acquiring the contact surface is and the end time of the contact surface , the length of the contact surface , , ;based on The estimated model obtains the load of the vehicle.

[0013] As an improvement of the embodiment of the present invention, the load of the vehicle= .

[0014] The embodiment of the present invention also provides a vehicle load estimation device, wherein the vehicle is provided with N tires. , N is a natural number, N ≥ 2; in any tire The first sensor and the second sensor are arranged on the inner wall of the tire, and the first and second sensors are arranged along the rotation direction of the tire, and the distance between the first and second sensors in the rotation direction is , i is a natural number, i=1, 2, ..., N; comprising the following modules: a second information acquisition module, used to execute the above generation method to generate an estimation model; for any tire The second operation is performed; tire The corresponding second operation is specifically: The starting time when the first sensor in obtains the contact surface is and the end time of the contact surface , from the tire The start time of the second sensor acquiring the contact surface is and the end time of the contact surface , the length of the contact surface , , ; Load calculation module, used based on The estimated model obtains the load of the vehicle.

[0015] As an improvement of the embodiment of the present invention, the load of the vehicle= .

[0016] The generation method of the estimation model, the estimation method of the vehicle load and the device thereof provided by the embodiment of the present invention have the following advantages: The embodiment of the present invention discloses a generation method of the estimation model, the estimation method of the vehicle load and the device thereof, which includes the following steps: continuously performing a first operation multiple times, the first operation is specifically: obtaining the load of the vehicle, and performing a second operation on any tire; the second operation corresponding to the tire is specifically: obtaining the start time of the contact surface and the end time of the contact surface from the first sensor in the tire, obtaining the start time of the contact surface and the end time of the contact surface from the second sensor in the tire, obtaining the contact surface and creating an estimation model. The estimation model can estimate the vehicle load in an efficient and relatively accurate way. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a structural diagram including a tire and first and second sensors in an embodiment;

[0018] Figure 2 The working principle diagram of the first and second sensors in the embodiment;

[0019] Figure 3 is a structural diagram of an RC integration circuit in an embodiment;

[0020] Figure 4 It is a flowchart of a method for generating an estimation model for vehicle load in an embodiment. DETAILED DESCRIPTION

[0021] The present invention will be described in detail below in conjunction with the embodiments shown in the accompanying drawings. However, the embodiments do not limit the present invention, and any structural, methodological, or functional changes made by a person skilled in the art based on the embodiments are all within the protection scope of the present invention.

[0022] The following description and accompanying drawings fully illustrate the specific embodiments of this article so that those skilled in the art can practice them. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. The scope of the embodiments of this article includes the entire scope of the claims, as well as all available equivalents of the claims. Herein, the terms "first", "second", etc. are only used to distinguish one element from another, without requiring or implying any actual relationship or order between these elements. In fact, the first element can also be called the second element, and vice versa. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the structure, device or equipment including a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also include elements inherent to such structure, device or equipment. In the absence of more restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the structure, device or equipment including the elements. Each embodiment is described in a progressive manner herein, and each embodiment focuses on the differences from other embodiments, and the same and similar parts between the embodiments can be referred to each other.

[0023] The terms "longitudinal", "lateral", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc. in this document indicate the orientation or position relationship based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing this document and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In the description of this document, unless otherwise specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a mechanical connection or an electrical connection, it can also be the internal communication of two elements, it can be a direct connection, or it can be indirectly connected through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0024] Embodiment 1 of the present invention provides a method for generating an estimation model for vehicle load, such as Figure 1 As shown, the vehicle is provided with N tires , N is a natural number, N ≥ 2; in any tire The inner wall of the tire is provided with a first sensor 11 and a second sensor 12, and the first and second sensors are distributed along the preset rotation direction of the tire; when the tire When stationary, the first sensor 11 is located at a position Position in a preset rotation direction. When rotating in the preset direction, the arc length of the second sensor 12 is When the second sensor 12 is located at a position Position in a preset rotation direction, i is a natural number, i=1, 2, ..., N; here, for a tire, there are two opposite rotation directions, namely, counterclockwise rotation direction or clockwise rotation direction. Figure 1 middle, The first sensor 11 is located at the position Position, when the arc length of the tire along the preset rotation direction is , the second sensor 12 is located at position Position.

[0025] The following steps are involved:

[0026] Step 401: Control each tire to rotate along a preset rotation direction, k=1, and continue to perform the first operation M times, M is a natural number, M≥2; the first operation is specifically: obtain the load of the vehicle , and for any tire The second operation is performed; tire The corresponding second operation is specifically: The start time when the first sensor 11 obtains the contact surface is and the end time of the contact surface , from the tire The start time when the second sensor 12 obtains the contact surface is and the end time of the contact surface , the length of the contact surface in the kth period , , , the value of k increases by 1.

[0027] Here, the signals that can be detected by the first and second sensors may be: pressure, vibration, deformation, acceleration, temperature, etc., and the start or end of the contact surface can be determined based on the changes in these signals.

[0028] Here, a total of M tests are performed, and in each test, the length of the corresponding contact surface is obtained for each tire. It can be understood that when the vehicle is loaded, the tire will be partially flattened, so that a contact surface will be formed between the tire and the ground.

[0029] Step 402: Based on Create an estimation model.

[0030] In the inventor's experiments, the estimation model can estimate the vehicle load in an efficient and relatively accurate manner.

[0031] In this embodiment, the estimation model is specifically: a clustering model, a linear regression model, a nonlinear regression model, a support vector machine model, a neural network model or a random forest model.

[0032] Here, the clustering model is to divide the samples into multiple classes consisting of similar objects. After clustering, statistical models can be used more accurately to estimate, analyze or predict in each class separately, and the correlation and main differences between different classes can also be explored. Clustering models include: K-means++ model, system hierarchy model and DBSCAN model.

[0033] The linear regression model is a mathematical regression model that determines the correlation between variables. It can be divided into: univariate linear regression model and multivariate linear regression model.

[0034] Nonlinear regression is a regression function with a nonlinear structure with respect to unknown regression coefficients. Commonly used processing methods include linear iteration of regression function, segmented regression, iterative least squares method, etc. The main content of nonlinear regression analysis is similar to that of linear regression analysis.

[0035] Support Vector Machine (SVM) is a generalized linear classifier that performs binary classification of data in a supervised learning manner. Its decision boundary is the maximum margin hyperplane solved for the learning samples.

[0036] Neural Networks (NN) is a complex network system formed by a large number of simple processing units widely connected to each other. It reflects many basic characteristics of human brain functions and is a highly complex nonlinear dynamic learning system. Neural networks have large-scale parallel, distributed storage and processing, self-organization, self-adaptation and self-learning capabilities.

[0037] Random Forest is a classic bagging model whose weak learner is a decision tree model. As shown in the figure below, the random forest model randomly samples from the original data set to form n different sample data sets, and then builds n different decision tree models based on these data sets. Finally, the final result is obtained based on the average value (for regression models) or voting (for classification models) of these decision tree models.

[0038] In this embodiment, the estimation model is specifically a multiple linear regression model.

[0039] The multiple linear regression equation in the multiple linear regression model is: .

[0040] Will , , is the noise, and the multivariate linear regression equation is input to obtain the matrix B.

[0041] In this embodiment, each first sensor 11 and each second sensor 12 is correspondingly provided with an RC integration circuit;

[0042] The tire The start time when the first sensor 11 obtains the contact surface is and the end time of the contact surface , from the tire The start time when the second sensor 12 obtains the contact surface is and the end time of the contact surface Specifically including: from tires The first signal is obtained from the RC integration circuit corresponding to the first sensor 11 in the embodiment, and the start time of the contact surface is obtained based on the first signal. and the end time of the contact surface , from the tire The second signal is obtained from the RC integration circuit corresponding to the second sensor 12 in the embodiment, and the start time of the contact surface is obtained based on the second signal. and the end time of the contact surface .

[0043] here, Figure 3 A circuit diagram of an RC integrator circuit is shown, wherein the output of the RC integrator circuit ,in, is the output result of the kth period, is the input of the kth period, is the resistance, is the capacitance, is the sampling interval, is the sampling rate. It can be understood that the signal after passing through the RC integrator circuit greatly reduces the impact of impulse noise and other noises. Figure 2 A first signal and a second signal are shown.

[0044] In this embodiment, the output signals of the first sensor 11 and the second sensor 12 include: pressure, vibration, deformation, acceleration or temperature.

[0045] This embodiment 2 provides a method for providing a vehicle with N tires. , N is a natural number, N ≥ 2; in any tire The inner wall of the tire is provided with a first sensor 11 and a second sensor 12, and the first and second sensors are distributed along the preset rotation direction of the tire; when the tire When stationary, the first sensor 11 is located at a position Position in a preset rotation direction. When rotating in the preset direction, the arc length of the second sensor 12 is When the second sensor 12 is located at a position Position in a preset rotation direction, i is a natural number, i=1, 2, ..., N; comprising the following modules:

[0046] The first information acquisition module is used to control each tire to rotate along a preset rotation direction, k=1, and continuously perform the first operation M times, M is a natural number, M≥2; the first operation is specifically: obtaining the load of the vehicle , and for any tire The second operation is performed; tire The corresponding second operation is specifically: The start time when the first sensor 11 obtains the contact surface is and the end time of the contact surface , from the tire The start time when the second sensor 12 obtains the contact surface is and the end time of the contact surface , the length of the contact surface in the kth period , , , the value of k increases by 1.

[0047] Model creation module for Create an estimation model.

[0048] This embodiment 3 provides a method for estimating vehicle load. The vehicle is provided with N tires. , N is a natural number, N ≥ 2; in any tire The inner wall of the tire is provided with a first sensor 11 and a second sensor 12, the first and second sensors are arranged along the rotation direction of the tire, and the distance between the first and second sensors in the rotation direction is , i is a natural number, i=1, 2, ..., N; comprising the following steps:

[0049] Execute the generation method in the first embodiment to generate an estimation model; for any tire The second operation is performed; tire The corresponding second operation is specifically: The start time when the first sensor 11 obtains the contact surface is and the end time of the contact surface , from the tire The start time when the second sensor 12 obtains the contact surface is and the end time of the contact surface , the length of the contact surface , , .

[0050] based on The estimated model obtains the load of the vehicle.

[0051] In this embodiment, the vehicle load= .

[0052] This fourth embodiment provides a vehicle load estimation device, wherein the vehicle is provided with N tires , N is a natural number, N ≥ 2; in any tire The inner wall of the tire is provided with a first sensor 11 and a second sensor 12, the first and second sensors are arranged along the rotation direction of the tire, and the distance between the first and second sensors in the rotation direction is , i is a natural number, i=1, 2, ..., N; including the following modules:

[0053] The second information acquisition module is used to execute the generation method in the first embodiment to generate an estimation model; The second operation is performed; tire The corresponding second operation is specifically: The start time when the first sensor 11 obtains the contact surface is and the end time of the contact surface , from the tire The start time when the second sensor 12 obtains the contact surface is and the end time of the contact surface , the length of the contact surface , , ; Load calculation module, used based on The estimated model obtains the load of the vehicle.

[0054] In this embodiment, the vehicle load= .

[0055] It should be noted that although the above describes the various steps in a specific order, it does not mean that the various steps must be executed in the above specific order. In fact, some of these steps can be executed concurrently or even in a different order as long as the required functions can be achieved.

[0056] The present invention may be a system, a method and / or a computer program product. The computer program product may include a readable storage medium carrying computer readable program instructions for causing a processor to implement various aspects of the present invention.

[0057] The readable storage medium can be a tangible device that holds and stores instructions used by the instruction execution device. The readable storage medium can include, for example, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (non-exhaustive list) of readable storage media include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a protruding structure in a groove on which instructions are stored, and any suitable combination thereof.

[0058] The embodiments of the present invention have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for generating an estimation model for vehicle load, wherein the vehicle is provided with N tires , N is a natural number, N ≥ 2; in any tire A first sensor (11) and a second sensor (12) are arranged on the inner wall of the tire, and the first and second sensors are distributed along a preset rotation direction of the tire; when the tire When stationary, the first sensor (11) is located at a position Position in a preset rotation direction. When rotating in the preset direction, the arc length of the second sensor (12) is When the second sensor (12) is located at a position Position in a preset rotation direction, i is a natural number, i=1, 2, ..., N; characterized in that, The following steps are involved: Control each tire to rotate along a preset rotation direction, k=1, and continue to perform the first operation M times, M is a natural number, M≥2; the first operation is specifically: obtain the load of the vehicle , and for any tire The second operation is performed; tire The corresponding second operation is specifically: The first sensor (11) in the image captures the start time of the contact surface as and the end time of the contact surface , from the tire The second sensor (12) in the image captures the start time of the contact surface as and the end time of the contact surface , the length of the contact surface in the kth period , , , the value of k increases by 1; based on Create an estimation model.

2. The method for generating an estimation model for vehicle load according to claim 1, characterized in that: The estimation model is specifically: a clustering model, a linear regression model, a nonlinear regression model, a support vector machine model, a neural network model or a random forest model.

3. The method for generating an estimation model for vehicle load according to claim 2, characterized in that: The estimation model is specifically a multiple linear regression model; The multiple linear regression equation in the multiple linear regression model is: ; Will , , is the noise, and the multivariate linear regression equation is input to obtain the matrix B.

4. The method for generating an estimation model for vehicle load according to claim 1, characterized in that: Each first sensor (11) and each second sensor (12) is correspondingly provided with an RC integration circuit; The tire The first sensor (11) in the image captures the start time of the contact surface as and the end time of the contact surface , from the tire The second sensor (12) in the image captures the start time of the contact surface as and the end time of the contact surface Specifically including: from tires A first signal is obtained from an RC integration circuit corresponding to the first sensor (11) in the embodiment, and the start time of the contact surface is obtained based on the first signal: and the end time of the contact surface , from the tire A second signal is obtained from the RC integration circuit corresponding to the second sensor (12) in the embodiment, and the start time of the contact surface is obtained based on the second signal: and the end time of the contact surface .

5. The method for generating an estimation model for vehicle load according to claim 4, characterized in that: The output signals of the first sensor (11) and the second sensor (12) include pressure, vibration, deformation, acceleration or temperature.

6. A device for generating an estimation model for vehicle load, wherein the vehicle is provided with N tires , N is a natural number, N ≥ 2; in any tire A first sensor (11) and a second sensor (12) are arranged on the inner wall of the tire, and the first and second sensors are distributed along a preset rotation direction of the tire; when the tire When stationary, the first sensor (11) is located at a position Position in a preset rotation direction. When rotating in the preset direction, the arc length of the second sensor (12) is When the second sensor (12) is located at a position Position in a preset rotation direction, i is a natural number, i=1, 2, ..., N; characterized in that, Includes the following modules: The first information acquisition module is used to control each tire to rotate along a preset rotation direction, k=1, and continuously perform the first operation M times, M is a natural number, M≥2; the first operation is specifically: obtaining the load of the vehicle , and for any tire The second operation is performed; tire The corresponding second operation is specifically: The first sensor (11) in the image captures the start time of the contact surface as and the end time of the contact surface , from the tire The second sensor (12) in the image captures the start time of the contact surface as and the end time of the contact surface , the length of the contact surface in the kth period , , , the value of k increases by 1; Model creation module for Create an estimation model.

7. A method for estimating the load of a vehicle, wherein the vehicle is provided with N tires , N is a natural number, N ≥ 2; in any tire A first sensor (11) and a second sensor (12) are arranged on the inner wall of the tire, the first and second sensors are arranged along the rotation direction of the tire, and the distance between the first and second sensors in the rotation direction is , i is a natural number, i=1, 2, ..., N; it is characterized in that, The following steps are involved: Execute the generation method described in any one of claims 1 to 5 to generate an estimation model; for any tire The second operation is performed; tire The corresponding second operation is specifically: The first sensor (11) in the image captures the start time of the contact surface as and the end time of the contact surface , from the tire The second sensor (12) in the image captures the start time of the contact surface as and the end time of the contact surface , the length of the contact surface , , ; based on The estimated model obtains the load of the vehicle.

8. The method for estimating vehicle load according to claim 7, characterized in that: The estimation model is generated by claim 3; The vehicle's load = .

9. A vehicle load estimation device, wherein the vehicle is provided with N tires , N is a natural number, N ≥ 2; in any tire A first sensor (11) and a second sensor (12) are arranged on the inner wall of the tire, the first and second sensors are arranged along the rotation direction of the tire, and the distance between the first and second sensors in the rotation direction is , i is a natural number, i=1, 2, ..., N; it is characterized in that, Includes the following modules: The second information acquisition module is used to execute the generation method described in any one of claims 1 to 5 to generate an estimation model; for any tire The second operation is performed; tire The corresponding second operation is specifically: The first sensor (11) in the image captures the start time of the contact surface as and the end time of the contact surface , from the tire The second sensor (12) in the image captures the start time of the contact surface as and the end time of the contact surface , the length of the contact surface , , ; Load calculation module for The estimated model obtains the load of the vehicle.

10. The vehicle load estimation device according to claim 9, characterized in that: The estimation model is generated by claim 3; The vehicle's load = .

Images