Slip ratio calculation device, slip ratio calculation program, and recording medium

Abstract

To solve the problem that an error is generated in an estimation result under a traveling condition which cannot be expressed by a vehicle model, and the problem that parameter identification is required again when a vehicle is changed.SOLUTION: A slip ratio calculation device (10) is a device that calculates a slip ratio in a vehicle including a traveling motor. The slip ratio calculation device includes a determination unit (13). The determination unit is configured to determine a selection mode of a plurality of slip ratio calculation logics different from each other based on a characteristic value related to motion of the vehicle. The characteristic value is, for example, a torque slew rate in the traveling motor or a wheel speed difference between predetermined wheels. The determination unit determines, for example, a selection mode of the first slip ratio calculation unit (11) and the second slip ratio calculation unit (12).SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to a slip ratio calculation device, a slip ratio calculation program, and a computer-readable, non-transient, tangible recording medium on which such a slip ratio calculation program is recorded, for calculating the slip ratio in a vehicle equipped with a traction motor. [Background technology]

[0002] Patent Document 1 discloses a tire contact state estimation device that can suppress noise amplification of tire rotation state detection values ​​and estimate tire contact state with high accuracy. Specifically, the technology described in Patent Document 1 combines information such as slip ratio and friction coefficient using multiple sensors and model formulas, mutually complementing unknown parameters and correcting known parameters to perform high-accuracy estimation. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2012-56365 Summary of the Invention [Problem to be solved by the invention]

[0004] The conventional techniques have problems such as errors occurring in the estimation results under driving conditions that cannot be expressed by a vehicle model, and the need to identify parameters again when the vehicle is changed. The present invention has been made in view of the circumstances exemplified above. [Means for solving the problem]

[0005] The slip ratio calculation device (10) according to claim 1 is a device for calculating a slip ratio in a vehicle (1) equipped with a traction motor (4), The system includes a decision unit (13) that decides a selection mode from among a plurality of different slip ratio calculation logics based on the characteristic value related to the vehicle motion. A slip ratio calculation program according to claim 14 is a computer program executed by a slip ratio calculation device (10) that calculates a slip ratio in a vehicle (1) equipped with a traction motor (4), The process executed by the slip ratio calculation device is A process of acquiring a characteristic value related to the motion of the vehicle; a process of determining a selection mode of a plurality of different slip ratio calculation logics based on a characteristic value related to the motion of the vehicle; Includes: The recording medium according to claim 15 is a computer-readable non-transient tangible recording medium storing a slip ratio calculation program executed by a slip ratio calculation device (10) that calculates a slip ratio in a vehicle (1) equipped with a traction motor (4), The process included in the slip ratio calculation program is as follows: A process of acquiring a characteristic value related to the motion of the vehicle; a process of determining a selection mode of a plurality of different slip ratio calculation logics based on a characteristic value related to the motion of the vehicle; Includes:

[0006] In addition, in each section of the application documents, each element may be assigned a reference symbol in parentheses. However, such reference symbol merely indicates an example of the correspondence between the element and the specific means described in the embodiment described below. Therefore, the present invention is not limited in any way by the above-mentioned reference symbols. [Brief explanation of the drawings]

[0007] [Figure 1] 1 is a diagram showing a schematic configuration of a vehicle to which the present invention is applied; [Figure 2] 1 is a block diagram showing a schematic functional configuration of a slip ratio calculation device according to an embodiment of the present invention; [Figure 3]10 is a graph showing an outline of a calculation error of a slip ratio due to a torque through rate. [Figure 4] 10 is a graph showing an outline of a calculation error of a slip ratio due to a wheel speed difference. [Figure 5] 3 is a flowchart showing an outline of an example of the operation of the slip ratio calculation device shown in FIG. 2. [Figure 6] FIG. 10 is a block diagram showing a schematic functional configuration of a slip ratio calculation device according to another embodiment of the present invention. [Figure 7] 7 is a graph showing an outline of an operation example of the slip ratio calculation device shown in FIG. 6. [Figure 8] 7 is a flowchart showing an outline of an example of operation of the slip ratio calculation device shown in FIG. 6. [Figure 9] 7 is a graph showing an outline of another example of operation of the slip ratio calculation device shown in FIG. 6. [Figure 10] 7 is a graph showing an outline of another example of operation of the slip ratio calculation device shown in FIG. 6. [Figure 11] FIG. 10 is a block diagram showing a schematic functional configuration of a slip ratio calculation device according to still another embodiment of the present invention. [Figure 12] 12 is a time chart showing an outline of an example of operation of the slip ratio calculation device shown in FIG. 11. [Figure 13] FIG. 10 is a block diagram showing a schematic functional configuration of a slip ratio calculation device according to still another embodiment of the present invention. [Figure 14] 14 is a graph showing an outline of an example of operation of the slip ratio calculation device shown in FIG. 13. [Figure 15] 14 is a flowchart showing an outline of an example of operation of the slip ratio calculation device shown in FIG. 13. DETAILED DESCRIPTION OF THE INVENTION

[0008] (Embodiment) Hereinafter, exemplary embodiments or specific examples of the present invention will be described with reference to the drawings as appropriate. Note that the following embodiments and their modifications, as well as the descriptions in the drawings, are schematic or simplified for the purpose of concisely explaining the contents of the present invention, and are not intended to limit the contents of the present invention in any way. Therefore, it goes without saying that the descriptions in the drawings do not necessarily coincide with the specific device configurations that are actually manufactured and sold. In other words, unless expressly limited by the applicant in the prosecution history of this application, it goes without saying that the present invention should not be interpreted as being limited by the descriptions in the drawings and the device configurations, functions, or operations described below corresponding thereto.

[0009] (Vehicle configuration) 1, vehicle 1 is an automobile that travels on a road and has wheels 3, namely, a left front wheel 3a, a right front wheel 3b, a left rear wheel 3c, and a right rear wheel 3d, at the four corners of a box-shaped body 2. Vehicle 1 to which the present invention is applicable is an electric vehicle equipped with a traction motor 4, and is configured to be able to transmit rotational driving force from the traction motor 4 to the drive wheels via a power transmission mechanism 5 including a reduction mechanism and a drive shaft 6.

[0010] It should be noted that the term "electric vehicle" is not limited to electric vehicles or fuel cell vehicles that use only electrical energy as driving energy, but also includes, for example, hybrid vehicles that also use an internal combustion engine, plug-in hybrid vehicles, etc. Also, for the sake of simplicity of illustration and explanation, Fig. 1 shows an example of the configuration of a so-called front-wheel drive vehicle in which the drive wheels are the left front wheel 3a and the right front wheel 3b, but the present invention is not limited to this embodiment.

[0011] The vehicle 1 is equipped with a large number of on-board sensors for detecting physical quantities related to its motion. "Physical quantities related to motion" are physical quantities corresponding to the behavior or motion state of the entire vehicle 1 or each part of the vehicle 1 while it is traveling, and include, for example, speed, acceleration, angular velocity, rotation speed, etc. Specifically, in this embodiment, the vehicle 1 is equipped with at least a wheel speed sensor 7 and a resolver 8. The wheel speed sensors 7 are provided corresponding to the left front wheel 3a, right front wheel 3b, left rear wheel 3c, and right rear wheel 3d, respectively. The resolver 8 is provided in the traction motor 4 so as to generate an output signal corresponding to the rotation state of the traction motor 4.

[0012] The vehicle 1 is equipped with a vehicle control device 9, which is an electronic control device (i.e., ECU). ECU is an abbreviation for Electronic Control Unit. The vehicle control device 9 is configured to execute operations of the vehicle 1 (for example, traction control, braking control, etc.) based on output signals from the above-mentioned on-board sensors and command signals for driving operations by the driver or other ECUs. In this embodiment, the vehicle control device 9 is configured as a microcomputer equipped with one or more processors and memories programmed to execute one or more functions embodied by a computer program.

[0013] A processor includes at least one arithmetic unit having the functions or configuration of a CPU or MPU, and its peripheral circuits (e.g., a timer circuit, etc.). Memory includes at least RAM, ROM, or nonvolatile rewritable memory among various non-transient physical storage media such as ROM, RAM, and nonvolatile rewritable memory. "Storage medium" can also be referred to as "recording medium." Nonvolatile rewritable memory is a storage device that allows information to be rewritten while the power is on, but retains information in an unrewritable manner while the power is off, such as flash memory.

[0014] The vehicle control device 9 is configured so that the processor reads and executes a computer program from the memory to realize predetermined functions related to driving the vehicle 1. The memory stores the computer program as well as various data such as initial values, maps, look-up tables, etc., required to execute the program.

[0015] (First embodiment) 2 shows a schematic functional configuration of a slip ratio calculation device 10 according to one embodiment of the present invention. Note that although this embodiment is referred to as the "first embodiment," this is because it is being described first for the sake of convenience in describing the simplest embodiment of the present invention, and does not indicate that it is the main embodiment.

[0016] In this embodiment, the slip ratio calculation device 10 is realized as one functional component of the vehicle control device 9 shown in FIG. 1. The slip ratio calculation device 10 is configured to calculate the slip ratio of the vehicle 1 and output it to other applications (for example, an electric TRC or an electric ABS). TRC stands for traction control. ABS stands for antilock brake system.

[0017] The slip ratio calculation device 10 according to the embodiment of the present invention is configured to determine the selection mode of a plurality of different slip ratio calculation logics based on characteristic values ​​related to the motion of the vehicle 1. The "characteristic values ​​related to the motion" include command values ​​for controlling the motion of the vehicle 1 in addition to the above-mentioned "physical quantities related to the motion."

[0018] In this embodiment, the torque through rate or wheel speed difference can be used as the "physical quantity related to motion." The wheel speed difference is the difference in wheel speed between multiple wheels 3, and is typically the difference between the left and right of a pair of drive wheels. Specifically, in the configuration example shown in FIG. 1, the wheel speed difference is the difference in wheel speed between the left front wheel 3a and the right front wheel 3b. The "selection mode" includes not only the selection of one of multiple slip ratio calculation logics and their calculation results, but also the selection of a weighting mode for the calculation results of multiple slip ratio calculation logics.

[0019] 2, the slip ratio calculation device 10 includes a first slip ratio calculation unit 11, a second slip ratio calculation unit 12, and a determination unit 13 as functional components realized by the vehicle control device 9. These functional components can be realized on a processor and memory by executing a computer program.

[0020] The first slip ratio calculation unit 11 calculates the slip ratio based on the output of the wheel speed sensor 7, which serves as the first sensor of the present invention. The calculation result of the slip ratio by the first slip ratio calculation unit 11 using the output of the wheel speed sensor 7 is referred to as a first calculation result S w The second slip ratio calculation unit 12 calculates the slip ratio based on the output of the resolver 8, which serves as the second sensor of the present invention. The calculation result of the slip ratio by the second slip ratio calculation unit 12 using the output of the resolver 8 is referred to as the second calculation result S res The determination unit 13 determines the manner of selection between the first slip ratio calculation unit 11 and the second slip ratio calculation unit 12 based on the torque through rate and the wheel speed difference.

[0021] In this embodiment, the determination unit 13 has a function as a selection unit 131 that determines a selection mode based on the relationship between the characteristic value and the threshold value. That is, the determination unit 13 determines the first calculation result S w and the second calculation result S resA selection unit 131 selects which of the above to output as the final slip ratio calculation result. More specifically, the selection unit 131 has a threshold determination unit 132 that compares the characteristic value with a threshold value, and outputs the first calculation result S based on the determination result by the threshold determination unit 132. w and the second calculation result S res The output is selected from either of the above.

[0022] 3 and 4 show the first calculation result S based on the output of the wheel speed sensor 7. w The calculation error (dashed line) in and the second calculation result S based on the output of resolver 8 res The threshold determination unit 132 outputs a determination result as to whether the torque slew rate or the wheel speed difference is equal to or greater than a threshold. If the torque slew rate or the wheel speed difference is equal to or greater than a threshold, the selection unit 131 selects the first calculation result S w If it is less than the threshold, the second calculation result S res The threshold value may be a predetermined value, i.e., a predetermined value set in advance based on the results of prior measurement such as an experiment, or may be a learned value obtained by machine learning or the like.

[0023] (Example of operation) Below, an overview of the slip ratio calculation operation performed by the slip ratio calculation device 10 according to this embodiment having the above-described configuration will be described, along with the effects of this configuration. The slip ratio calculation device 10 according to this embodiment, the slip ratio calculation method and slip ratio calculation program executed thereby, and a computer-readable, non-transient, tangible recording medium on which this slip ratio calculation program is recorded may be collectively referred to as "this embodiment." This recording medium may be realized, for example, as a ROM, non-volatile rewritable memory, magnetic disk, optical disk, etc. Specifically, this recording medium may be realized in any format, for example, as an external server, a portable terminal device, an optical disk such as a CD-ROM, a memory card that is detachable from a computer device such as a terminal device, etc.

[0024] For example, the road friction coefficient μ can be expressed by the following formula (1) during slow acceleration and by the following formula (2) during sudden acceleration. x is the driving force, F Z is the ground load, r is the radius of the wheel 3, N is the gear ratio in the power transmission mechanism 5, T MG is the command torque for the traction motor 4, J MG is the inertia of the traction motor 4, J s is the inertia of the drive shaft 6.

number

number

[0025] Unlike equation (1) during slow acceleration, equation (2) during sudden acceleration contains an inertia term, and during sudden acceleration, vehicle speed changes significantly, necessitating the identification of each inertia term. Therefore, in conventional technology using model equations, the number of identification parameters increases, necessitating identification for each vehicle. Meanwhile, wheel speed sensor 7 calculates wheel speed as (number of pulses x distance per pulse) / calculation cycle. Therefore, when traveling at low speeds, there are fewer pulses within the calculation cycle, so consideration of the phase difference component of each pulse is necessary, but detecting the phase difference between each pulse is difficult. Thus, in conventional technology, when considering the above scenario, identification for each vehicle is required, making it difficult to address the situation simply by replacing the algorithm.

[0026] As shown in FIG. 3, in the region where the torque slew rate is small, the second calculation result S res The calculation error (solid line) of the first calculation result S using the output of the wheel speed sensor 7 is w On the other hand, in the region where the torque slew rate is large, the first calculation result S using the output of the wheel speed sensor 7, which shows the influence of the resonance of the drive shaft 6, is smaller than the calculation result S w The calculation error (dashed line) is greater than the second calculation result S using the output of resolver 8. resThe calculation error is smaller than the solid line.

[0027] Also, as shown in FIG. 4, in the region where the wheel speed difference is small, the second calculation result S res The calculation error (solid line) of the first calculation result S using the output of the wheel speed sensor 7 is w On the other hand, in the region where the wheel speed difference is large, the first calculation result S using the output of the wheel speed sensor 7 that can perform independent calculations on the left and right wheels is smaller than the calculation result S w The calculation error (dashed line) is greater than the second calculation result S using the output of resolver 8. res The calculation error is smaller than the solid line.

[0028] Therefore, in this embodiment, when the torque through rate or the wheel speed difference is equal to or greater than a threshold value, the first calculation result S w If the threshold value is less than the threshold value, the second calculation result S res In this way, by determining the selection mode of the slip ratio calculation results by each sensor using a threshold value, it is possible to select a sensor that always provides high slip ratio calculation accuracy without parameter identification.

[0029] FIG. 5 is a flowchart showing an example of operation according to this embodiment. In the flowchart shown in FIG. 5, "S" is an abbreviation for "step." This also applies to other flowcharts described later. The slip ratio calculation routine shown in FIG. 5 is repeatedly executed at predetermined time intervals while predetermined execution conditions are met. The predetermined execution conditions include, for example, that the ignition switch of the vehicle 1 is turned on, that the shift range is other than the "P" range, etc.

[0030] When the slip ratio calculation routine shown in FIG. 5 is started, the processor sequentially executes the processes of steps 101 to 103. First, in step 101, the processor acquires various signals corresponding to physical quantities and characteristic values ​​related to motion. Next, in step 102, the processor calculates the slip ratio using the output of the wheel speed sensor 7 and outputs a first calculation result S w The output of the resolver 8 is used to calculate the slip ratio, and the second calculation result S res Subsequently, in step 103, the processor determines whether the characteristic values, i.e., the torque slew rate and the wheel speed difference, are equal to or greater than threshold values.

[0031] If the characteristic value is equal to or greater than the threshold value (i.e., step 103=YES), the processor executes the process of step 104 and then temporarily ends this routine. w On the other hand, if the characteristic value is less than the threshold value (i.e., step 103=NO), the processor executes the process of step 105 and then temporarily ends this routine. In step 105, the processor selects and outputs the second calculation result S res is selected and output as the final slip ratio calculation result.

[0032] In the above specific example, the operation of the threshold value determination unit 132, i.e., step 103, is a determination of whether the characteristic value is greater than or equal to a predetermined threshold value. Therefore, in this case, the input to the threshold value determination unit 132 may be only one of the torque through rate and the wheel speed difference. That is, the operation of step 103 may be only a determination of whether the torque through rate is equal to or greater than a threshold value, or may be only a determination of whether the wheel speed difference is equal to or greater than a threshold value. This makes it possible to achieve the above-mentioned effect with a simple configuration. Alternatively, when both the torque through rate and the wheel speed difference are used, the first calculation result S w and the second calculation result S res Alternatively, only one of the results may be selected, or a weighted average of both may be used.

[0033] Second Embodiment FIG. 6 shows a schematic functional configuration of a slip ratio calculation device 10 according to a second embodiment of the present invention. In the following description of the second embodiment, differences from the first embodiment will be mainly described. In addition, identical or equivalent parts in the first and second embodiments are denoted by the same reference numerals. Therefore, in the following description of the second embodiment, the description of the first embodiment can be appropriately applied to components having the same reference numerals as those in the first embodiment, unless there is a technical contradiction or special additional explanation. The same applies to the third and subsequent embodiments and modified examples described below.

[0034] This embodiment includes a configuration for machine learning a threshold value. Specifically, as shown in Fig. 6, in this embodiment, the determination unit 13 includes a threshold value setting unit 133 that sets a threshold value through machine learning of a slip ratio calculation error. The threshold value setting unit 133 includes a first variation calculation unit 133a, a second variation calculation unit 133b, a data storage unit 133c, and a threshold value learning unit 133d.

[0035] The first variation calculation unit 133a calculates the first calculation result S w Specifically, the first variance calculation unit 133a obtains information about the calculation accuracy, i.e., the variance, of the first calculation result S w The first standard deviation σ, which is the standard deviation as a statistical value corresponding to the variation in w The following formula is calculated:

[0036] The second variation calculation unit 133b calculates the second calculation result S res Specifically, the second variation calculation unit 133b calculates the second calculation result S res The second standard deviation σ, which is the standard deviation as a statistical value corresponding to the variation in res The following formula is calculated:

[0037] The data storage unit 133c stores the accuracy labeling information in association with the torque slew rate information and the wheel speed information. w and the second calculation result S res Specifically, the accuracy labeling information is information about which of the following has higher calculation accuracy: w >Second standard deviation σ res If this holds, then t i =1, and if not, t i = 0. The data storage unit 133c creates table data in which, for example, accuracy labeling information is recorded in the first column, torque slew rate information in the second column, and wheel speed information in the third column, and stores the data in memory.

[0038] The threshold learning unit 133d calculates the threshold by performing optimization calculations based on the table data stored in the data storage unit 133c. The threshold learning unit 133d can calculate the threshold by, for example, machine learning using a support vector machine. FIG. 7 shows an example of an outline of machine learning using a support vector machine. In FIG. 7, the horizontal axis indicates torque slew rate information, the vertical axis indicates wheel speed information, and circles indicate the first calculation results S w indicates the case where the variation is smaller, and the cross marks indicate the second calculation result S res This shows a case where the variation is smaller when the sample set is a circle. The dashed-dotted line indicates the separating hyperplane, i.e., the boundary between the sample set marked with a circle and the sample set marked with an cross, and corresponds to the threshold. Note that support vector machines were already well known at the time of filing this application, and therefore further detailed explanation will be omitted in this specification.

[0039] Fig. 8 is a flowchart showing an example of operation according to this embodiment. The slip ratio calculation routine shown in Fig. 8 is repeatedly executed at predetermined time intervals while predetermined execution conditions are met. When the slip ratio calculation routine shown in Fig. 8 is started, the processor first executes the processes of steps 201 to 204 in order. Then, when the determination result in step 204 is "YES," the processor causes the process to proceed to step 205 and subsequent steps.

[0040] In step 201, the processor acquires various signals corresponding to physical quantities and characteristic values ​​related to the motion. In step 202, the processor calculates the slip ratio using the output of the wheel speed sensor 7 and outputs a first calculation result S w The output of the resolver 8 is used to calculate the slip ratio, and the second calculation result S res In step 203, the processor stores the calculation result in step 202 in association with the torque slew rate information and the wheel speed information. w and the second calculation result S res A set of data is considered to be one data set, and the number of saved data sets is considered to be the number of data N.

[0041] In step 204, the processor determines whether the number of data N exceeds a predetermined value Nth. w and the second calculation result S res The variation of the first standard deviation σ w and the second standard deviation σ res This corresponds to a determination as to whether the number of data N has become large enough to enable meaningful calculation. If the number of data N is equal to or smaller than the predetermined value Nth (i.e., step 204=NO), the processor returns the process to step 201. This results in the addition of a new data set and the increment of the number of data N. On the other hand, if the number of data N exceeds the predetermined value Nth (i.e., step 204=YES), the processor causes the process to proceed to step 205 and subsequent steps.

[0042] In step 205, the processor calculates the first calculation result S w and the second calculation result S res In step 206, the processor calculates the average value of the first calculation result S w and the second calculation result S res The standard deviation of , that is, the first standard deviation σ w and the second standard deviation σ res In step 207, the processor creates the above table data based on the calculation result in step 206.

[0043] In step 208, the processor uses the table data created in step 207 to solve an optimization problem that minimizes the objective function under the following conditions: Constraints:t i (w T x i -h)≧0

[0044] In step 209, the processor performs a threshold determination. T x i - Determine whether h>0 is true. T x i If -h>0 holds (i.e., step 209=YES), the processor executes the process of step 210 and then temporarily ends this routine. w is selected and output as the final slip ratio calculation result. T x i If -h>0 is not true (i.e., step 209=NO), the processor executes the process of step 211 and then temporarily ends this routine. res is selected and output as the final slip ratio calculation result.

[0045] In this embodiment, a threshold value can be determined in real time from measurement results obtained during driving and used for judgment. This makes it possible to dynamically select a highly accurate sensor without using a model. Furthermore, because judgments are made based only on real-time measurement data, there is no need to identify parameters in advance. Therefore, according to this embodiment, it is possible to always select calculated values ​​obtained from highly accurate sensors.

[0046] In addition, for example, there may be cases where the left and right wheels are in contact with road surfaces with different characteristics (for example, one of them is a frozen road surface). In this case, in a driving state where the wheel speed difference is large and the torque through rate is small, the calculation error is smaller than the first calculation result S w is smaller, and from the viewpoint of torque slew rate, the second calculation result S res In this way, even if the advantages and disadvantages from each viewpoint are different, according to the present embodiment, by performing classification using machine learning, it is possible to properly determine the sensor to be used for calculating the slip ratio.

[0047] Note that by using a linear kernel function, the calculation time can be reduced and the threshold can be updated in a short cycle. However, as shown in Figure 9, incorrect judgments may occur in the area surrounded by the dashed line.

[0048] In this regard, it is possible to set a threshold with higher accuracy by using a nonlinear kernel, as shown in Fig. 10. For example, when the kernel function shown in the following equation (3) is used, the following equation (4) holds in the region to the upper right of the threshold curve in Fig. 10, and the following equation (5) holds in the region to the lower left.

number

number

number

[0049] In this case, the constraint condition in step 208 is as shown in the following equation (6).

number

[0050] (Third embodiment) 11 shows a schematic functional configuration of a slip ratio calculation device 10 according to a third embodiment of the present invention. This embodiment has a configuration that takes into account the timing of machine learning of thresholds. That is, in this embodiment, the threshold setting unit 133 includes a first variance calculation unit 133a, a second variance calculation unit 133b, a data storage unit 133c, a threshold learning unit 133d, and a learning timing control unit 133e.

[0051] For example, the learning timing control unit 133e can execute machine learning at a predetermined cycle, thereby reducing the calculation load and improving the calculation accuracy of the slip ratio compared to conventional methods.

[0052] Alternatively, for example, the learning timing control unit 133e may calculate the first calculation result S w and the second calculation result S res The system may determine whether a learning condition is met based on a comparison with the actual data, and execute machine learning when the learning condition is met. This reduces the frequency of calculations, thereby reducing the required computational resources.

[0053] 12 shows an example of the relationship between the calculation result of the slip ratio and the learning condition. In the time chart of the slip ratio at the top of FIG. 12, the broken line indicates the first calculation result S based on the output of the wheel speed sensor 7. w The solid line indicates the second calculation result S based on the output of the resolver 8. res The horizontal axis represents time. The learning timing control section 133e then calculates the first calculation result S w and the second calculation result S res When the difference or ratio between the threshold value and the actual value becomes equal to or greater than a predetermined value, the table data is updated and threshold learning is performed. This allows threshold learning to be performed in a timely manner.

[0054] (Fourth embodiment) 13 shows a schematic functional configuration of a slip ratio calculation device 10 according to a fourth embodiment of the present invention. In this embodiment, instead of the selection unit 131 in FIG. 6 or FIG. 11, a first calculation result S w and the second calculation result S res A final result calculation unit 134 is provided to perform a weighting calculation with the above.

[0055] That is, in this embodiment, the determination unit 13 performs a weighting calculation process on a plurality of slip ratio calculation results instead of a threshold determination and a selection process according to the result of the determination. w and the second calculation result S res The results of the statistical processing performed on each of the characteristic values ​​after weighting are calculated and output as the slip ratio calculation result.

[0056] 14 and 15 show examples of weighting according to the distance d from the threshold using a linear kernel. In FIG. 14, the reference distance d for normalizing the distance d is range Specifically, is the maximum distance.

[0057] In the flowchart shown in Fig. 15, the processing contents of steps 301 to 308 are the same as the processing contents of steps 201 to 208 in the flowchart shown in Fig. 8. Therefore, the processing contents after step 308 will be explained below.

[0058] In step 309, the processor calculates the normalized distance d using the following equation (7).

number

[0059] In the next step 310, the processor calculates an output value s by weighting according to the distance d using the following equation (8): sis a weighting coefficient according to the distance d.

number

[0060] (effect) The following describes the configurations corresponding to the above-described embodiments and the effects achieved thereby. Note that the following (1) to (13) can be appropriately combined with each other (for example, (1) + (2) + (4) + (9)) as long as there is no logical inconvenience such as being in parallel with each other.

[0061] (1) A slip ratio calculation device 10 that calculates a slip ratio in a vehicle 1 equipped with a traction motor 4 includes a determination unit 13. The determination unit 13 determines a selection mode from among a plurality of different slip ratio calculation logics based on characteristic values ​​related to the motion of the vehicle 1. This allows the slip ratio calculation logic that provides higher calculation accuracy to be used preferentially.

[0062] (2) The slip ratio calculation device 10 further includes a first slip ratio calculation unit 11 and a second slip ratio calculation unit 12. The first slip ratio calculation unit 11 calculates the slip ratio based on the output of a first sensor (e.g., wheel speed sensor 7) that is an on-board sensor that detects physical quantities related to the motion of the vehicle 1. The second slip ratio calculation unit 12 calculates the slip ratio based on the output of a second sensor (e.g., resolver 8) that is an on-board sensor different from the first sensor. The determination unit 13 determines the selection manner between the first slip ratio calculation unit 11 and the second slip ratio calculation unit 12. This makes it possible to select a sensor that always provides high accuracy in calculating the slip ratio.

[0063] (3) The characteristic value is the torque through rate of the traction motor 4 or the wheel speed difference between predetermined wheels 3. This makes it possible to select a slip ratio calculation logic that always provides high slip ratio calculation accuracy based on the torque slew rate and / or wheel speed information.

[0064] (4) The first sensor is a wheel speed sensor 7, and the second sensor is a resolver 8 attached to the traction motor 4. This makes it possible to select either the wheel speed sensor 7 or the resolver 8, whichever sensor provides higher accuracy in calculating the slip ratio.

[0065] (5) The determination unit 13 determines the selection mode based on the relationship between the characteristic value and the threshold value. This makes it possible to select a slip ratio calculation logic that always provides high slip ratio calculation accuracy without parameter identification, thereby effectively resolving problems with the prior art, such as errors in estimation results under driving conditions that cannot be represented by a vehicle model, and the need for parameter identification for each vehicle.

[0066] (6) The threshold value is a predetermined value that is set in advance. This allows the processing load to be reduced effectively by using a predetermined value determined in advance based on the results of preliminary measurements such as experiments.

[0067] (7) The determination unit 13 includes a threshold setting unit 133 that sets a threshold value by machine learning of the slip ratio calculation error. This makes it possible to dynamically select slip ratio calculation logic with high accuracy without prior measurement or models. Furthermore, because the decision is made based solely on real-time measurement data, prior parameter identification is not required. Therefore, it is possible to select slip ratio calculation logic that always provides high slip ratio calculation accuracy.

[0068] (8) The threshold setting unit 133 performs machine learning using a support vector machine with a linear kernel. This reduces the calculation time and enables the threshold to be updated at short intervals.

[0069] (9) The threshold setting unit 133 performs machine learning using a support vector machine with a nonlinear kernel. This makes it possible to set the threshold value with higher accuracy.

[0070] (10) The threshold setting unit 133 executes machine learning at a predetermined cycle. This makes it possible to reduce the calculation load and improve the calculation accuracy of the slip ratio compared to the conventional method.

[0071] (11) The threshold setting unit 133 determines whether the learning conditions are met based on a comparison between the calculation results by the first slip ratio calculation unit 11 and the calculation results by the second slip ratio calculation unit 12, and performs machine learning when the learning conditions are met. This reduces the frequency of calculations, thereby making it possible to reduce the required calculation resources.

[0072] (12) The determination unit 13 includes a selection unit 131 that selects which of the calculation results from the first slip ratio calculation unit 11 and the second slip ratio calculation unit 12 is to be used as the slip ratio calculation result. This reduces the calculation load and enables high-speed processing.

[0073] (13) The determination unit 13 includes a final result calculation unit 134 that weights the calculation results by the first slip ratio calculation unit 11 and the calculation results by the second slip ratio calculation unit 12 based on characteristic values ​​and performs statistical processing to obtain the slip ratio calculation result. This effectively prevents extreme calculation results from being output by combining multiple calculation results.

[0074] (Variation) The present invention is not limited to the above-described embodiments and specific examples. Therefore, the above-described embodiments and the like can be modified as appropriate. Representative modifications will be described below. In the following description of the modifications, differences from the above-described embodiments and the like will be mainly described. Furthermore, the same reference numerals are used for parts that are identical or equivalent to each other in the above-described embodiments and the following modifications. Therefore, in the following description of the modifications, the explanations in the above-described embodiments and the like can be used as appropriate for components that have the same reference numerals as the above-described embodiments and the like, unless there is a technical contradiction or special additional explanation.

[0075] The present invention is not limited to the specific applications and device configurations shown in the above embodiments. For example, there is no particular limitation on the type of vehicle 1, and it may be, for example, a so-called standard automobile or a so-called large automobile.

[0076] A computer program according to the present invention, which enables the execution of various operations, procedures, or processes described in the above embodiments, can be downloaded or upgraded via V2X communication using a communication device. V2X stands for Vehicle to X. Alternatively, such a computer program can be downloaded or upgraded via a terminal device installed in a vehicle manufacturing plant, a repair shop, a dealer, or the like. Such a computer program can be stored on a memory card, an optical disk, a magnetic disk, or the like.

[0077] All or part of the vehicle control device 9 may be configured with a digital circuit, such as an ASIC or FPGA, configured to be able to realize the above-mentioned functions or operations. ASIC stands for Application Specific Integrated Circuit. FPGA stands for Field Programmable Gate Array. In other words, the vehicle control device 9 may have both an on-board microcomputer and a digital circuit.

[0078] In this way, each of the above functional configurations and processes may be realized by a special-purpose computer provided by configuring a processor and memory programmed to execute one or more functions embodied in a computer program. Alternatively, each of the above functional configurations and processes may be realized by a special-purpose computer provided by configuring a processor with one or more dedicated hardware logic circuits. Alternatively, each of the above functional configurations and processes may be realized by one or more special-purpose computers configured by combining one or more processors programmed to execute one or more functions, one or more memories, and one or more other processors configured with one or more hardware logic circuits. Furthermore, the computer program may be stored in a computer-readable, non-transitory storage medium as instructions to be executed by a computer. In other words, each of the above functional configurations and processes may be expressed as a computer program including procedures for implementing the same, or as a non-transitory storage medium storing the computer program.

[0079] The present invention is not limited to the specific functions and operation modes shown in the above embodiment. That is, for example, the present invention is not limited to the first calculation result S w and the second slip ratio calculation unit 12 calculates the second calculation result S res The present invention is not limited to an embodiment in which a selection is made between the first slip ratio calculation unit 11 and the second slip ratio calculation unit 12 after the first slip ratio calculation unit 11 or the second slip ratio calculation unit 12 is calculated. Therefore, for example, the present invention also includes an embodiment in which a selection is made first between the first slip ratio calculation unit 11 and the second slip ratio calculation unit 12, and then the selected unit performs the slip ratio calculation process. Furthermore, the machine learning technique is not limited to a support vector machine.

[0080] It goes without saying that the elements constituting the above-described embodiments are not necessarily essential unless they are particularly clearly stated as essential or are considered to be clearly essential in principle. Furthermore, when numerical values ​​such as the number, value, amount, range, etc. of components are mentioned, the present invention is not limited to those specific numbers unless they are particularly clearly stated as essential or are clearly limited to specific numbers in principle. Similarly, when the shape, direction, positional relationship, etc. of components are mentioned, the present invention is not limited to those shapes, directions, positional relationship, etc. unless they are particularly clearly stated as essential or are clearly limited to specific shapes, directions, positional relationship, etc. in principle.

[0081] Similar expressions such as "acquire," "calculate," "estimate," "detect," and "sensing" may be substituted for each other as appropriate within the scope of technical inconsistency. Furthermore, "exceeding the threshold" and "above the threshold" may be substituted for each other as appropriate within the scope of technical inconsistency. The same applies to "below the threshold" and "below the threshold."

[0082] The variations are not limited to the above examples. For example, all or part of one of the multiple embodiments may be combined with all or part of another embodiment, provided that there is no technical inconsistency. Similarly, all or part of one of the multiple variations may be combined with all or part of another embodiment, provided that there is no technical inconsistency. Furthermore, all or part of the above specific example and all or part of the above variations may be combined with each other, provided that there is no technical inconsistency. [Explanation of symbols]

[0083] 1 vehicle 3 wheels 4. Traction motor 7 Wheel speed sensor 8 Resolver 10. Slip ratio calculation device 11 First slip ratio calculation unit 12 First slip ratio calculation unit 13 Decision Section 131 Selection Section

Claims

1. A slip ratio calculation device (10) for calculating a slip ratio in a vehicle (1) equipped with a traction motor (4), comprising: a determination unit (13) that determines a selection mode of a plurality of different slip ratio calculation logics based on a characteristic value related to the vehicle motion; Slip ratio calculation device.

2. a first slip ratio calculation unit (11) that calculates the slip ratio based on an output of a first sensor (7) that is an on-vehicle sensor that detects a physical quantity related to the motion of the vehicle; a second slip ratio calculation unit (12) that calculates the slip ratio based on an output of a second sensor (8) that is an on-vehicle sensor different from the first sensor; Furthermore, the determination unit determines the selection manner between the first slip ratio calculation unit and the second slip ratio calculation unit. The slip ratio calculation device according to claim 1 .

3. The characteristic value is a torque through rate of the traction motor or a wheel speed difference between predetermined wheels (3). The slip ratio calculation device according to claim 2 .

4. the first sensor is a wheel speed sensor, the second sensor is a resolver attached to the traction motor, 4. The slip ratio calculation device according to claim 3.

5. the determination unit determines the selection mode based on a relationship between the characteristic value and a threshold value.

5. The slip ratio calculation device according to claim 4.

6. The threshold value is a predetermined value that is set in advance.

6. The slip ratio calculation device according to claim 5.

7. The determination unit includes a threshold setting unit (133) that sets the threshold value by machine learning of the slip ratio calculation error.

7. The slip ratio calculation device according to claim 6.

8. the threshold setting unit performs machine learning using a support vector machine with a linear kernel. The slip ratio calculation device according to claim 7.

9. the threshold setting unit performs machine learning using a support vector machine with a nonlinear kernel. The slip ratio calculation device according to claim 7.

10. the threshold setting unit executes the machine learning at a predetermined cycle. The slip ratio calculation device according to claim 7.

11. the threshold setting unit determines whether a learning condition is met based on a comparison between the calculation result by the first slip ratio calculation unit and the calculation result by the second slip ratio calculation unit, and performs the machine learning when the learning condition is met. The slip ratio calculation device according to claim 7.

12. the determination unit includes a selection unit (131) that selects which of the calculation results by the first slip ratio calculation unit and the second slip ratio calculation unit is to be used as the slip ratio calculation result. The slip ratio calculation device according to claim 2 .

13. the determination unit includes a final result calculation unit (134) that performs weighting based on the characteristic value on the calculation results by the first slip ratio calculation unit and the calculation results by the second slip ratio calculation unit, and determines the result as a slip ratio calculation result by performing statistical processing on the weighted result. The slip ratio calculation device according to claim 2 .

14. A slip ratio calculation program executed by a slip ratio calculation device (10) that calculates a slip ratio in a vehicle (1) equipped with a traction motor (4), comprising: The process executed by the slip ratio calculation device is A process of acquiring a characteristic value related to the motion of the vehicle; a process of determining a selection mode of a plurality of different slip ratio calculation logics based on a characteristic value related to the motion of the vehicle; A slip ratio calculation program including:

15. A computer-readable non-transient tangible recording medium storing a slip ratio calculation program executed by a slip ratio calculation device (10) that calculates a slip ratio in a vehicle (1) equipped with a traction motor (4), The process included in the slip ratio calculation program is as follows: A process of acquiring a characteristic value related to the motion of the vehicle; a process of determining a selection mode of a plurality of different slip ratio calculation logics based on a characteristic value related to the motion of the vehicle; A recording medium including:

Images