A brake disc performance prediction method based on artificial intelligence

Abstract

The present invention relates to the field of data processing technology, and specifically to a brake disc performance prediction method based on artificial intelligence, comprising: obtaining the degree of excellence of the brake effect of the brake disc during each braking test based on the similarity of the distribution of the degree of brake stress loss of the brake disc in each rotation cycle during each braking test; obtaining the degree of temperature control performance of the brake disc during each braking test; obtaining the degree of braking performance reflection of the brake disc during each braking test; obtaining the degree of performance excellence of the brake disc based on the changing trend of the degree of braking performance reflection of the brake disc during different braking tests; obtaining the braking performance prediction coefficient of each brake disc based on the difference in performance excellence between different brake discs; and performing a braking performance prediction evaluation on each brake disc based on the braking performance prediction coefficient. The present invention improves the accuracy of the braking performance prediction evaluation results of the brake disc.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a brake disc performance prediction method based on artificial intelligence. Background Art

[0002] As a core component of the automobile braking system, the performance of the brake disc is directly related to driving safety. The traditional brake disc performance prediction method is to set up a brake disc performance prediction experiment. During the experiment, brake discs are randomly sampled as test samples, and the sample brake discs are rotated to a preset linear speed level. They are braked by the test caliper, and the brake disc performance is predicted and evaluated by the braking time when the brake disc linear speed returns to zero. However, in actual scenarios, it is difficult for the brake disc surface to be completely flat, resulting in a loss of braking propulsion force between the caliper and it, resulting in poor braking time. In addition, because the brake disc frequently generates high heat during braking, its braking performance will decline, further resulting in low prediction accuracy obtained by only analyzing the braking time. Summary of the Invention

[0003] In order to solve the above problems, the present invention provides a brake disc performance prediction method based on artificial intelligence, the method comprising:

[0004] Obtain edge linear velocity data, vibration data, and temperature data of each brake disc at each moment during several braking tests;

[0005] For any brake disc, the ideal acceleration of the brake disc is obtained; based on the difference between the reduction amplitude of the edge line velocity data at each moment in each braking test and the ideal acceleration of the brake disc, the degree of braking speed deviation of the brake disc at each moment in each braking test is obtained; based on the fluctuation of the vibration data within the neighborhood time of each moment in each braking test, the degree of braking speed deviation is corrected to obtain the degree of braking stress loss of the brake disc at each moment in each braking test;

[0006] Divide all moments of the brake disc during each braking test into multiple rotation cycles; obtain the degree of excellence of the brake effect of the brake disc during each braking test based on the similarity of the distribution of the degree of brake stress loss of the brake disc in each rotation cycle during each braking test; obtain the degree of temperature control performance of the brake disc during each braking test based on the change of the temperature data of the brake disc during each braking test; obtain the degree of braking performance reflection of the brake disc during each braking test based on the degree of temperature control performance and the degree of excellence of the braking effect; obtain the degree of performance excellence of the brake disc based on the change trend of the degree of braking performance reflection of the brake disc during different braking tests; obtain the braking performance prediction coefficient of each brake disc based on the difference in performance excellence between different brake discs;

[0007] The braking performance prediction evaluation is performed on each brake disc based on the braking performance prediction coefficient.

[0008] Preferably, the method of obtaining the degree of braking speed deviation of the brake disc at each moment during each braking test according to the difference between the reduction amplitude of the edge linear velocity data at each moment during each braking test and the ideal acceleration of the brake disc includes the following specific methods:

[0009] The binomial fitting method is used to perform curve fitting on the edge linear velocity data of the brake disc at all times during each braking test to obtain the linear velocity change curve of the brake disc during each braking test.

[0010] The normalized value of the difference between the ideal acceleration of the brake disc and the slope value of the linear velocity change curve of the brake disc at the jth moment during the i-th braking test is used as the braking speed deviation degree of the brake disc at the j-th moment during the i-th braking test.

[0011] Preferably, the method of correcting the braking speed deviation degree according to the fluctuation of the vibration data in the neighborhood time at each moment during each braking test to obtain the braking stress loss degree of the brake disc at each moment during each braking test includes the following specific methods:

[0012] A neighborhood parameter a is preset, and the time sequence consisting of a moments before and a moments after the jth moment in the i-th braking experiment is recorded as the neighborhood time sequence of the jth moment;

[0013] The standard deviation of the vibration data of the brake disc at all moments in the neighborhood time sequence of the jth moment during the i-th braking test is recorded as the neighborhood vibration data fluctuation value of the jth moment;

[0014] The ratio of the fluctuation value of the neighborhood vibration data of the brake disc at the jth moment during the i-th braking test to the maximum value of the fluctuation value of the neighborhood vibration data of the brake disc at all moments during the i-th braking test is recorded as the first ratio; the ratio of the vibration data of the brake disc at the jth moment during the i-th braking test to the maximum value of the vibration data of the brake disc at the jth moment during the i-th braking test is recorded as the second ratio; the product of the first ratio and the second ratio is used as the vibration significance level at the jth moment during the i-th braking test;

[0015] According to the vibration significance and the braking speed deviation, the vibration speed correlation compliance degree at the jth moment in the i-th braking test is obtained;

[0016] The normalized value of the product of the vibration velocity correlation compliance degree at the jth moment during the i-th braking test and the braking speed deviation degree of the brake disc at the j-th moment during the i-th braking test is used as the braking stress loss degree of the brake disc at the j-th moment during the i-th braking test.

[0017] Preferably, the method of obtaining the vibration speed correlation compliance degree at the jth moment during the i-th braking test according to the vibration significance degree and the braking speed deviation degree includes the following specific methods:

[0018] A rectangular coordinate system constructed with time as the horizontal axis and vibration significance as the vertical axis is recorded as the first coordinate system; a rectangular coordinate system constructed with time as the horizontal axis and braking speed deviation as the vertical axis is recorded as the second coordinate system; the vibration significance at all moments during the i-th braking test is input into the first coordinate system to obtain a vibration significance curve of the brake disc during the i-th braking test; the braking speed deviation at all moments during the i-th braking test is input into the second coordinate system to obtain a braking speed deviation curve of the brake disc during the i-th braking test; the Pearson correlation coefficient between the vibration significance curve of the brake disc during the i-th braking test and the braking speed deviation curve of the brake disc during the i-th braking test is recorded as the retained correlation;

[0019] Input the vibration significance levels at all moments except the jth moment during the i-th braking test into the first coordinate system to obtain the vibration significance removal curve of the brake disc at the jth moment during the i-th braking test; input the braking speed deviation levels at all moments except the jth moment during the i-th braking test into the second coordinate system to obtain the braking speed deviation removal curve of the brake disc at the jth moment during the i-th braking test; detect the Pearson correlation coefficient between the vibration significance removal curve of the brake disc at the jth moment during the i-th braking test and the braking speed deviation removal curve of the brake disc at the jth moment during the i-th braking test, and record it as the removal correlation;

[0020] The ratio of the retained correlation to the removed correlation is taken as the degree of compliance of the vibration velocity correlation at the jth moment during the i-th braking experiment.

[0021] Preferably, the method of dividing all moments of the brake disc during each braking test into a plurality of rotation cycles includes:

[0022] The outer edge circumference of the brake disc is read through the brake disc parameter configuration system; a two-dimensional coordinate system is constructed with time as the horizontal axis and the edge linear velocity data as the vertical axis, and the edge linear velocity data of the brake disc at all times during the i-th braking test are input into the two-dimensional coordinate system to obtain the edge linear velocity curve of the brake disc during the i-th braking test; all segmentation points on the edge linear velocity curve of the brake disc during the i-th braking test are obtained, and the integral value between any two adjacent segmentation points is equal to the outer edge circumference of the brake disc; the time period formed by the moments corresponding to any two adjacent segmentation points is recorded as the rotation period of the brake disc during the i-th braking test.

[0023] Preferably, the method of obtaining the braking effect excellence of the brake disc during each braking test according to the similarity of the distribution of the braking stress loss degree of the brake disc in each rotation cycle during each braking test includes the following specific methods:

[0024] A two-dimensional coordinate system is constructed with time as the horizontal axis and the degree of brake stress loss as the vertical axis. The degree of brake stress loss of the brake disc at all times during the i-th braking test is input into the two-dimensional coordinate system to obtain a brake stress loss degree curve of the brake disc during the i-th braking test. The brake stress loss degree curve of the brake disc during the i-th braking test is divided into multiple curve segments according to the rotation cycle of the brake disc during the i-th braking test.

[0025] Combine all curve segments into any two combinations to obtain several curve segment combinations. Use the DTW algorithm to obtain the DTW value between the two curve segments in each curve segment combination, and record it as the distribution similarity of each curve segment combination. The mean of the distribution similarities of all curve segment combinations is used as the degree of compliance with the periodic law of the brake disc during the i-th braking test.

[0026] The normalized value of the inverse proportion between the reciprocal of the degree of compliance of the brake disc with the periodic law during the i-th braking test and the average value of the braking stress loss degree of the brake disc at all moments during the i-th braking test is taken as the braking effect excellence of the brake disc during the i-th braking test.

[0027] Preferably, the temperature control performance of the brake disc during each braking test is obtained according to the change in the temperature data of the brake disc during each braking test, including the following specific methods:

[0028] A two-dimensional coordinate system is constructed with time as the horizontal axis and temperature data as the vertical axis, and the temperature data of the brake disc at all times during the i-th braking test are input into the two-dimensional coordinate system to obtain the temperature data change curve of the brake disc during the i-th braking test; the data point corresponding to the maximum value of the temperature data in the temperature data change curve is recorded as the peak temperature data point; the data point corresponding to the temperature data of the temperature data change curve as the indoor temperature is recorded as the indoor temperature data point; traverse from the peak temperature data point as the starting point until the first indoor temperature data point is encountered, and the data segment composed of all data points in the traversal process is recorded as the heat dissipation data segment; the product of the absolute value of the mean of the slopes of all data points in the heat dissipation data segment and the inverse of the temperature data of the peak temperature data point is used as the temperature control performance of the brake disc during the i-th braking test.

[0029] Preferably, the method of obtaining the degree of braking performance of the brake disc during each braking test according to the degree of temperature control performance and the degree of excellence of braking effect includes the following specific methods:

[0030] The product of the temperature control performance of the brake disc during the i-th braking test and the braking effect excellence of the brake disc during the i-th braking test is used as the braking performance reflection degree of the brake disc during the i-th braking test.

[0031] Preferably, the method of obtaining the performance excellence of the brake disc according to the changing trend of the braking performance of the brake disc during different braking tests includes the following specific methods:

[0032] A two-dimensional coordinate system is constructed with the braking test order as the horizontal axis and the braking performance reflection degree as the vertical axis. The braking performance reflection degree of the n-th brake disc during all braking tests is input into the two-dimensional coordinate system, and the least squares method is used for linear fitting to obtain the braking performance reflection performance line of the n-th brake disc; the normalized value of the product of the slope of the braking performance reflection performance line of the n-th brake disc and the mean value of the braking performance reflection degree of the n-th brake disc during all braking tests is used as the performance excellence of the n-th brake disc.

[0033] Preferably, the method of obtaining the braking performance prediction coefficient of each brake disc according to the difference in performance excellence between different brake discs includes:

[0034] The reciprocal of the absolute value of the difference between the performance excellence of the nth brake disc and the mean of the performance excellence of all brake discs is recorded as the first reciprocal; the normalized value of the product of the first reciprocal and the performance excellence of the nth brake disc is used as the braking performance prediction coefficient of the nth brake disc.

[0035] The beneficial effects of the technical solution of the present invention are as follows: the present invention obtains the degree of excellence of the braking effect of the brake disc during each braking test according to the similarity of the distribution of the degree of brake stress loss of the brake disc in each rotation cycle during each braking test; obtains the degree of temperature control performance of the brake disc during each braking test according to the change of the temperature data of the brake disc during each braking test; obtains the degree of braking performance reflection of the brake disc during each braking test according to the degree of temperature control performance and the degree of excellence of the braking effect; obtains the degree of performance excellence of the brake disc according to the change trend of the degree of braking performance reflection of the brake disc during different braking tests; obtains the braking performance prediction coefficient of each brake disc according to the difference in performance excellence between different brake discs; performs braking performance prediction and evaluation on each brake disc based on the braking performance prediction coefficient; and performs auxiliary analysis in combination with the vibration of the brake disc and the heat treatment effect, thereby improving the accuracy of the braking performance prediction and evaluation results of the brake disc. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0037] Figure 1 This is a flowchart of the steps of a brake disc performance prediction method based on artificial intelligence of the present invention;

[0038] Figure 2 This is a characteristic relationship flow chart of a brake disc performance prediction method based on artificial intelligence of the present invention. DETAILED DESCRIPTION

[0039] To further illustrate the technical means and effectiveness of the present invention in achieving its intended objectives, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effectiveness of an artificial intelligence-based brake disc performance prediction method proposed by the present invention. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0040] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0041] The following describes in detail a specific solution of a brake disc performance prediction method based on artificial intelligence provided by the present invention with reference to the accompanying drawings.

[0042] See also Figure 1 , which shows a flowchart of a brake disc performance prediction method based on artificial intelligence provided by one embodiment of the present invention, the method comprising the following steps:

[0043] Step S001: Obtain edge linear velocity data, vibration data, and temperature data of each brake disc at each moment during several braking tests.

[0044] It should be noted that the brake disc is a component used for automobile braking. It is inlaid synchronously with the tire. When the brake disc is set, the tire is braked synchronously. The brake disc and various brake components work in coordination to achieve tire braking. During the braking process, the piston in the brake caliper applies a certain braking propulsion force to the brake disc, accelerating the friction between the brake pad and the brake disc, and slowing down the rotational linear speed of the brake disc. Predicting the performance of the brake disc can help companies optimize the product design of the brake disc while reducing product application risks. In traditional brake disc performance prediction experiments, the performance prediction accuracy obtained by analyzing the braking time of the brake disc alone is insufficient. Therefore, this embodiment combines the vibration and heat treatment effects of the brake disc in the actual experimental test scenario to obtain more accurate performance prediction results.

[0045] Specifically, we first need to collect edge linear velocity data, vibration data, and temperature data of each brake disc at each moment during several braking tests. The specific process is as follows:

[0046] Randomly sample 8 brake discs from a new production batch that have performance prediction requirements. Fix each brake disc sample on an operating table. Accelerate the brake disc linear speed to the initial linear speed through an acceleration gear in contact with the brake disc. When each brake disc reaches the initial linear speed, disengage the acceleration gear and simultaneously apply a propulsion force toward the brake disc to the piston in the caliper. Read the edge linear speed data at each moment during the braking test through the built-in linear speed sensor of each brake disc. Read the vibration data at each moment during the braking test through the built-in vibration sensor of each brake disc. Read the temperature data of each brake disc at each moment during the braking test through a temperature detector.

[0047] In this embodiment, the initial linear velocity of the brake disc is selected as 100 km / h, the propulsion force is selected as 1200 N, and the number of braking tests is selected as 100 times.

[0048] Thus, the edge linear velocity data, vibration data and temperature data of each brake disc at each moment during several braking tests are obtained through the above method.

[0049] Step S002: For any brake disc, obtain the ideal acceleration of the brake disc; obtain the degree of braking speed deviation of the brake disc at each moment in each braking test based on the difference between the reduction amplitude of the edge line velocity data at each moment in each braking test and the ideal acceleration of the brake disc; correct the degree of braking speed deviation based on the fluctuation of the vibration data in the neighborhood time at each moment in each braking test, and obtain the degree of braking stress loss of the brake disc at each moment in each braking test.

[0050] It should be noted that the flatness of the brake disc surface directly affects braking performance. Considering that under ideal flatness conditions, the net force acting on the brake disc is the friction force with the brake pad, and the friction force is only related to the piston thrust and the constant material friction coefficient, and because the piston thrust is a constant value in the experiment, the brake disc linear velocity should present a uniform deceleration form with a constant negative acceleration. Therefore, the acceleration of the brake disc linear velocity under ideal flatness conditions during braking can be obtained based on the friction coefficient and the piston thrust, that is, the ideal slope of the edge linear velocity change. Then, the degree of brake disc braking speed deviation at each moment can be obtained based on the difference between each point of the actual linear velocity change curve and the ideal slope. Since the degree of brake speed deviation may be caused by the unevenness of the brake disc surface or noise caused by insufficient instrument acquisition accuracy, the uneven brake disc surface will produce large vibrations under the action of the piston thrust. Therefore, in order to further determine the degree of brake speed deviation caused by the unevenness of the brake disc surface, the brake speed deviation degree can be corrected in combination with the vibration characteristics to obtain the degree of brake stress error for each brake disc.

[0051] Preferably, in some implementations of the embodiments of the present invention, considering that the resultant force on the brake disc under ideal flat conditions is the friction force with the brake pad, and the friction force is only related to the piston propulsion force and the constant material friction coefficient, and because the piston propulsion force is a constant value in the experiment, the brake disc linear velocity should present a uniform deceleration form with a constant negative acceleration. Therefore, the acceleration of the brake disc linear velocity under ideal flat conditions during braking can be obtained according to the friction coefficient and the piston propulsion force, that is, the ideal slope of the edge linear velocity change, and then the degree of braking speed deviation of the brake disc at each moment can be obtained according to the difference between each point of the actual linear velocity change curve and the ideal slope; then, according to the difference between the reduction amplitude of the edge linear velocity data at each moment during each braking test and the ideal acceleration of each brake disc, the specific method for obtaining the degree of braking speed deviation of each brake disc at each moment during each braking test is as follows:

[0052] This embodiment is described using any brake disc as an example;

[0053] The friction coefficient of the brake disc material and the mass of the brake disc are obtained through the brake disc parameter configuration system, and the friction coefficient and the mass of the brake disc are input into Newton's second law to obtain the ideal acceleration of the brake disc;

[0054] The binomial fitting method is used to perform curve fitting on the edge linear velocity data of the brake disc at all times during each braking test to obtain the linear velocity change curve of the brake disc during each braking test.

[0055] The normalized value of the difference between the ideal acceleration of the brake disc and the slope value of the linear velocity change curve of the brake disc at the jth moment during the i-th braking test is used as the braking velocity deviation degree of the brake disc at the j-th moment during the i-th braking test;

[0056] The specific formula is:

[0057] G i,j =norm(K′―K i,j )

[0058] Where G i,j Indicates the degree of braking speed deviation of the brake disc at the jth moment during the i-th braking test; K ′ Indicates the ideal acceleration of the brake disc; K i,j It represents the slope value of the linear velocity change curve of the brake disc at the jth moment during the i-th braking test; norm() represents the linear normalization function.

[0059] It should be noted that, if the difference between the slope value of the linear velocity change curve of the brake disc at the jth moment during the i-th braking test and the ideal acceleration of the brake disc is greater, it means that the deviation between the linear velocity braking effect of the brake disc at this time and the ideal braking is greater; the binomial fitting method and Newton's second law are existing technologies, and will not be described in detail in this embodiment.

[0060] Preferably, in some implementations of the embodiments of the present invention, since the degree of braking speed deviation may be caused by the uneven surface of the brake disc, or may be noise caused by insufficient instrument acquisition accuracy, and the uneven surface of the brake disc will generate large vibrations under the action of the piston propulsion force, in order to further determine the degree of braking speed deviation caused by the uneven surface of the brake disc, the degree of braking speed deviation can be corrected in combination with the vibration characteristics to obtain the degree of braking stress error of each brake disc; the degree of braking speed deviation is corrected according to the fluctuation of vibration data in the neighborhood time at each moment during each braking test, and the specific method for obtaining the degree of braking stress loss of each brake disc at each moment during each braking test is as follows:

[0061] A neighborhood parameter a is preset, wherein this embodiment is described by taking a=3 as an example, and this embodiment is not specifically limited, wherein a is determined according to specific implementation conditions;

[0062] The time sequence consisting of a moments before and a moments after the jth moment in the i-th braking experiment is recorded as the neighborhood time sequence of the jth moment;

[0063] The standard deviation of the vibration data of the brake disc at all moments in the neighborhood time sequence of the jth moment during the i-th braking test is recorded as the neighborhood vibration data fluctuation value of the jth moment;

[0064] The ratio of the fluctuation value of the neighborhood vibration data of the brake disc at the jth moment during the i-th braking test to the maximum value of the fluctuation value of the neighborhood vibration data of the brake disc at all moments during the i-th braking test is recorded as the first ratio; the ratio of the vibration data of the brake disc at the jth moment during the i-th braking test to the maximum value of the vibration data of the brake disc at the jth moment during the i-th braking test is recorded as the second ratio; the product of the first ratio and the second ratio is used as the vibration significance level at the jth moment during the i-th braking test;

[0065] The specific formula is:

[0066]

[0067] Where, IA i,j Indicates the vibration significance at the jth moment during the i-th braking test; σ i,j Represents the standard deviation of the vibration data of the brake disc at all moments in the neighborhood time sequence of the jth moment during the i-th braking test; σmax i represents the maximum value of the neighborhood vibration data fluctuation value of the brake disc at all moments during the i-th braking test; P i,j represents the vibration data of the brake disc at the jth moment during the i-th braking test; Pmax i It represents the maximum value of the vibration data of the brake disc at the jth moment during the i-th braking test.

[0068] A rectangular coordinate system constructed with time as the horizontal axis and vibration significance as the vertical axis is recorded as the first coordinate system; a rectangular coordinate system constructed with time as the horizontal axis and braking speed deviation as the vertical axis is recorded as the second coordinate system; the vibration significance at all moments during the i-th braking test is input into the first coordinate system to obtain a vibration significance curve of the brake disc during the i-th braking test; the braking speed deviation at all moments during the i-th braking test is input into the second coordinate system to obtain a braking speed deviation curve of the brake disc during the i-th braking test; the Pearson correlation coefficient between the vibration significance curve of the brake disc during the i-th braking test and the braking speed deviation curve of the brake disc during the i-th braking test is recorded as the retained correlation;

[0069] Input the vibration significance levels at all moments except the jth moment during the i-th braking test into the first coordinate system to obtain the vibration significance removal curve of the brake disc at the jth moment during the i-th braking test; input the braking speed deviation levels at all moments except the jth moment during the i-th braking test into the second coordinate system to obtain the braking speed deviation removal curve of the brake disc at the jth moment during the i-th braking test; detect the Pearson correlation coefficient between the vibration significance removal curve of the brake disc at the jth moment during the i-th braking test and the braking speed deviation removal curve of the brake disc at the jth moment during the i-th braking test, and record it as the removal correlation;

[0070] The ratio of the retained correlation to the removed correlation is used as the degree of compliance of the vibration velocity correlation at the jth moment during the i-th braking test;

[0071] The normalized value of the product of the vibration velocity correlation compliance degree at the jth moment in the i-th braking test and the braking speed deviation degree of the brake disc at the jth moment in the i-th braking test is used as the braking stress loss degree of the brake disc at the jth moment in the i-th braking test;

[0072] The specific formula is:

[0073] U i,j =norm(IF i,j ×G i,j )

[0074] Where U i,j G represents the degree of brake stress loss of the brake disc at the jth moment during the i-th braking test; i,j Indicates the degree of braking speed deviation of the brake disc at the jth moment during the i-th braking test; IF i,jIt represents the degree of vibration velocity correlation at the jth moment during the i-th braking test; norm() represents the linear normalization function.

[0075] It should be noted that, the higher the degree of vibration velocity correlation at the jth moment during the i-th braking test, the more likely the braking speed deviation at that moment is caused by the flatness of the brake disc surface, which means that the brake disc is more likely to have piston propulsion force loss at that moment, that is, the greater the degree of braking stress loss; the Pearson correlation coefficient is a prior art and will not be elaborated on in detail in this embodiment.

[0076] Thus, the braking stress loss degree of each brake disc at each moment during each braking test is obtained through the above method.

[0077] Step S003: Divide all moments of the brake disc during each braking test into multiple rotation cycles; obtain the degree of excellence of the brake effect of the brake disc during each braking test based on the similarity of the distribution of the degree of brake stress loss of the brake disc in each rotation cycle during each braking test; obtain the degree of temperature control performance of the brake disc during each braking test based on the change of temperature data of the brake disc during each braking test; obtain the degree of braking performance reflection of the brake disc during each braking test based on the temperature control performance and the degree of excellence of the braking effect; obtain the degree of performance excellence of the brake disc based on the change trend of the degree of braking performance reflection of the brake disc during different braking tests; obtain the braking performance prediction coefficient of each brake disc based on the difference in performance excellence between different brake discs.

[0078] It should be noted that one complete rotation of the brake disc is considered a rotation cycle, and since the surface flatness of the brake disc will not change significantly in a short-term single braking test, the same position of the brake disc should show similar brake stress loss levels in different rotation cycles of a single braking test. The degree of braking excellence is then determined based on the periodic characteristics of the brake stress loss level. At the same time, the brake disc generates a lot of heat during the braking process. If its heat treatment performance is poor, it will affect and cause the braking performance to decay. Therefore, the degree of brake disc performance is further analyzed based on the heat treatment of the brake disc.

[0079] Preferably, in some implementations of the embodiments of the present invention, the specific method of dividing all moments of the brake disc during each braking test into multiple rotation cycles is:

[0080] The outer edge circumference of the brake disc is read through the brake disc parameter configuration system; a two-dimensional coordinate system is constructed with time as the horizontal axis and the edge linear velocity data as the vertical axis, and the edge linear velocity data of the brake disc at all times during the i-th braking test are input into the two-dimensional coordinate system to obtain the edge linear velocity curve of the brake disc during the i-th braking test; all segmentation points on the edge linear velocity curve of the brake disc during the i-th braking test are obtained, and the integral value between any two adjacent segmentation points is equal to the outer edge circumference of the brake disc; the time period formed by the moments corresponding to any two adjacent segmentation points is recorded as the rotation period of the brake disc during the i-th braking test.

[0081] Preferably, in some implementations of the embodiments of the present invention, based on the similarity of the distribution of the degree of brake stress loss of the brake disc in each rotation cycle during each braking test, a specific method for obtaining the braking effect excellence of the brake disc during each braking test is as follows:

[0082] A two-dimensional coordinate system is constructed with time as the horizontal axis and the degree of brake stress loss as the vertical axis. The degree of brake stress loss of the brake disc at all times during the i-th braking test is input into the two-dimensional coordinate system to obtain a brake stress loss degree curve of the brake disc during the i-th braking test. The brake stress loss degree curve of the brake disc during the i-th braking test is divided into multiple curve segments according to the rotation cycle of the brake disc during the i-th braking test.

[0083] Combine all curve segments into any two combinations to obtain several curve segment combinations. Use the DTW algorithm to obtain the DTW value between the two curve segments in each curve segment combination, and record it as the distribution similarity of each curve segment combination. The mean of the distribution similarities of all curve segment combinations is used as the degree of compliance with the periodic law of the brake disc during the i-th braking test.

[0084] The normalized value of the inverse ratio between the reciprocal of the degree of compliance with the periodic law of the brake disc during the i-th braking test and the average value of the braking stress loss degree of the brake disc at all moments during the i-th braking test is used as the braking effect excellence of the brake disc during the i-th braking test;

[0085] The specific formula is:

[0086]

[0087] Where, IB i Indicates the braking performance excellence of the brake disc during the i-th braking test; Indicates the degree of compliance of the brake disc with the periodic law during the i-th braking test; represents the mean value of the brake stress loss degree of the brake disc at all times during the i-th braking test; exp( ) represents an exponential function with a natural constant as the base. The embodiment adopts the exp(-x) model to present the inverse proportional relationship and normalization processing, and x is the input of the model. The implementer can select the inverse proportional function and normalization function according to the actual situation.

[0088] It should be noted that, if the degree of conformity of the brake disc to the periodic regularity during the i-th braking test is smaller, it means that the shapes of the various rotation period segments of the braking stress loss curve of the brake disc during the i-th braking test are more similar, which means that the braking stress loss obtained by the brake disc during the i-th braking test is more likely to be caused by the unevenness of the brake disc itself, which means that the confidence level of the braking stress loss is higher. At the same time, if the braking stress loss is greater, it further indicates that the braking effect of the brake disc is worse. The DTW algorithm is a prior art and will not be described in detail in this embodiment.

[0089] Preferably, in some implementations of the embodiments of the present invention, since frequent heat generation of the brake disc will reduce braking performance, if its heat treatment performance is poor, it will affect and cause braking performance to decay; based on the change in temperature data of the brake disc during each braking test, the specific method for obtaining the temperature control performance of the brake disc during each braking test is as follows:

[0090] A two-dimensional coordinate system is constructed with time as the horizontal axis and temperature data as the vertical axis, and the temperature data of the brake disc at all times during the i-th braking test are input into the two-dimensional coordinate system to obtain the temperature data change curve of the brake disc during the i-th braking test; the data point corresponding to the maximum value of the temperature data in the temperature data change curve is recorded as the peak temperature data point; the data point corresponding to the temperature data of the temperature data change curve as the indoor temperature is recorded as the indoor temperature data point; traverse from the peak temperature data point as the starting point until the first indoor temperature data point is encountered, and the data segment composed of all data points in the traversal process is recorded as the heat dissipation data segment; the product of the absolute value of the mean of the slopes of all data points in the heat dissipation data segment and the inverse of the temperature data of the peak temperature data point is used as the temperature control performance of the brake disc during the i-th braking test.

[0091] It should be noted that the lower the peak temperature, the lower the heat generation effect of the brake disc, and the higher the long-term performance guarantee of the brake disc. At the same time, the larger the absolute value of the slope mean of the heat dissipation data segment, the higher the heat dissipation efficiency of the brake disc.

[0092] Preferably, in some implementations of the embodiments of the present invention, the greater the temperature control performance of the brake disc during each braking test and the better the braking effect, the more significant the braking performance of the brake disc. The specific method for obtaining the degree of reflection of the braking performance of the brake disc during each braking test based on the temperature control performance and the braking effect is as follows:

[0093] The product of the temperature control performance of the brake disc during the i-th braking test and the braking effect excellence of the brake disc during the i-th braking test is used as the braking performance reflection degree of the brake disc during the i-th braking test;

[0094] The specific formula is:

[0095] IJ i =norm(IB i ×IC i )

[0096] Where, IJ i Indicates the degree of braking performance of the brake disc during the i-th braking test; IC i Indicates the temperature control performance of the brake disc during the i-th braking test; IB i It represents the braking performance excellence of the brake disc during the i-th braking test; norm() represents the linear normalization function.

[0097] Preferably, in some implementations of the embodiments of the present invention, a single brake disc may experience slight thermal degradation after multiple tests. The more significant the thermal degradation, the less sustainable the performance of the brake disc can be guaranteed. Based on the changing trend of the braking performance of each brake disc during different braking tests, the specific method for obtaining the performance excellence of each brake disc is as follows:

[0098] A two-dimensional coordinate system is constructed with the braking test order as the horizontal axis and the braking performance reflection degree as the vertical axis. The braking performance reflection degree of the n-th brake disc during all braking tests is input into the two-dimensional coordinate system, and the least squares method is used for linear fitting to obtain the braking performance reflection performance line of the n-th brake disc; the normalized value of the product of the slope of the braking performance reflection performance line of the n-th brake disc and the mean value of the braking performance reflection degree of the n-th brake disc during all braking tests is used as the performance excellence of the n-th brake disc.

[0099] It should be noted that the greater the slope of the braking performance reflection line, the lower the thermal attenuation performance of the brake disc braking performance. At the same time, the greater the mean value of the braking performance reflection degree, the better the overall performance of the brake disc.

[0100] Preferably, in some implementations of the embodiments of the present invention, the smaller the difference in performance excellence among multiple brake discs, the higher the confidence level of the brake disc experiment. Based on the difference in performance excellence among different brake discs, the specific method for obtaining the brake performance prediction coefficient of each brake disc is as follows:

[0101] The reciprocal of the absolute value of the difference between the performance excellence of the n-th brake disc and the mean of the performance excellence of all brake discs is recorded as the first reciprocal; the normalized value of the product of the first reciprocal and the performance excellence of the n-th brake disc is used as the braking performance prediction coefficient of the n-th brake disc;

[0102] The specific formula is:

[0103]

[0104] Where, IR n Represents the braking performance prediction coefficient of the nth brake disc; IV n Indicates the performance excellence of the nth brake disc; represents the mean performance excellence of all brake discs; ε represents a preset hyperparameter. In this implementation, ε = 1 is preset to prevent the denominator from being 0; norm() represents a linear normalization function.

[0105] At this point, the braking performance prediction coefficient of each brake disc is obtained through the above method.

[0106] Step S004: performing a braking performance prediction evaluation on each brake disc based on the braking performance prediction coefficient.

[0107] Preferably, in some implementations of the embodiments of the present invention, the specific method for performing brake performance prediction evaluation on each brake disc based on the brake performance prediction coefficient is:

[0108] A threshold parameter T is preset, wherein this embodiment is described by taking T=0.6 as an example, and this embodiment is not specifically limited, wherein T is determined according to specific implementation conditions;

[0109] For any brake disc, if the braking performance prediction coefficient of any brake disc is greater than or equal to the threshold parameter T, the braking performance prediction evaluation result of any brake disc is recorded as qualified; if the braking performance prediction coefficient of any brake disc is less than the threshold parameter T, the braking performance prediction evaluation result of any brake disc is recorded as unqualified.

[0110] See also Figure 2 , which shows a characteristic relationship flow chart of a brake disc performance prediction method based on artificial intelligence;

[0111] At this point, this embodiment is completed.

[0112] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A brake disc performance prediction method based on artificial intelligence, characterized in that: The method comprises the following steps: Obtain edge linear velocity data, vibration data, and temperature data of each brake disc at each moment during several braking tests; For any brake disc, the ideal acceleration of the brake disc is obtained; based on the difference between the reduction amplitude of the edge line velocity data at each moment in each braking test and the ideal acceleration of the brake disc, the degree of braking speed deviation of the brake disc at each moment in each braking test is obtained; based on the fluctuation of the vibration data within the neighborhood time of each moment in each braking test, the degree of braking speed deviation is corrected to obtain the degree of braking stress loss of the brake disc at each moment in each braking test; Divide all moments of the brake disc during each braking test into multiple rotation cycles; obtain the degree of excellence of the brake effect of the brake disc during each braking test based on the similarity of the distribution of the degree of brake stress loss of the brake disc in each rotation cycle during each braking test; obtain the degree of temperature control performance of the brake disc during each braking test based on the change of the temperature data of the brake disc during each braking test; obtain the degree of braking performance reflection of the brake disc during each braking test based on the degree of temperature control performance and the degree of excellence of the braking effect; obtain the degree of performance excellence of the brake disc based on the change trend of the degree of braking performance reflection of the brake disc during different braking tests; obtain the braking performance prediction coefficient of each brake disc based on the difference in performance excellence between different brake discs; The braking performance prediction evaluation is performed on each brake disc based on the braking performance prediction coefficient.

2. The brake disc performance prediction method based on artificial intelligence according to claim 1, characterized in that: The method of obtaining the degree of braking speed deviation of the brake disc at each moment during each braking test according to the difference between the reduction amplitude of the edge linear velocity data at each moment during each braking test and the ideal acceleration of the brake disc includes the following specific methods: The binomial fitting method is used to perform curve fitting on the edge linear velocity data of the brake disc at all times during each braking test to obtain the linear velocity change curve of the brake disc during each braking test. The normalized value of the difference between the ideal acceleration of the brake disc and the slope value of the linear velocity change curve of the brake disc at the jth moment during the i-th braking test is used as the braking speed deviation degree of the brake disc at the j-th moment during the i-th braking test.

3. The brake disc performance prediction method based on artificial intelligence according to claim 1, characterized in that: The method of correcting the braking speed deviation according to the fluctuation of the vibration data in the neighborhood of each moment during each braking test to obtain the braking stress loss degree of the brake disc at each moment during each braking test includes the following specific methods: A neighborhood parameter a is preset, and the time sequence consisting of a moments before and a moments after the jth moment in the i-th braking experiment is recorded as the neighborhood time sequence of the jth moment; The standard deviation of the vibration data of the brake disc at all moments in the neighborhood time sequence of the jth moment during the i-th braking test is recorded as the neighborhood vibration data fluctuation value of the jth moment; The ratio of the fluctuation value of the neighborhood vibration data of the brake disc at the jth moment during the i-th braking test to the maximum value of the fluctuation value of the neighborhood vibration data of the brake disc at all moments during the i-th braking test is recorded as the first ratio; the ratio of the vibration data of the brake disc at the jth moment during the i-th braking test to the maximum value of the vibration data of the brake disc at the jth moment during the i-th braking test is recorded as the second ratio; the product of the first ratio and the second ratio is used as the vibration significance level at the jth moment during the i-th braking test; According to the vibration significance and the braking speed deviation, the vibration speed correlation compliance degree at the jth moment in the i-th braking test is obtained; The normalized value of the product of the vibration velocity correlation compliance degree at the jth moment during the i-th braking test and the braking speed deviation degree of the brake disc at the j-th moment during the i-th braking test is used as the braking stress loss degree of the brake disc at the j-th moment during the i-th braking test.

4. The brake disc performance prediction method based on artificial intelligence according to claim 3, characterized in that: The specific method for obtaining the vibration speed correlation compliance degree at the jth moment during the i-th braking test according to the vibration significance degree and the braking speed deviation degree is as follows: A rectangular coordinate system constructed with time as the horizontal axis and vibration significance as the vertical axis is recorded as the first coordinate system; a rectangular coordinate system constructed with time as the horizontal axis and braking speed deviation as the vertical axis is recorded as the second coordinate system; the vibration significance at all times during the i-th braking test is input into the first coordinate system to obtain a vibration significance curve of the brake disc during the i-th braking test; Input the braking speed deviation degree of the brake disc at all moments during the i-th braking test into the second coordinate system to obtain the braking speed deviation curve of the brake disc during the i-th braking test; and denote the Pearson correlation coefficient between the vibration significance curve of the brake disc during the i-th braking test and the braking speed deviation curve of the brake disc during the i-th braking test as the retained correlation; Input the vibration significance levels at all moments except the jth moment during the i-th braking test into the first coordinate system to obtain the vibration significance removal curve of the brake disc at the jth moment during the i-th braking test; input the braking speed deviation levels at all moments except the jth moment during the i-th braking test into the second coordinate system to obtain the braking speed deviation removal curve of the brake disc at the jth moment during the i-th braking test; detect the Pearson correlation coefficient between the vibration significance removal curve of the brake disc at the jth moment during the i-th braking test and the braking speed deviation removal curve of the brake disc at the jth moment during the i-th braking test, and record it as the removal correlation; The ratio of the retained correlation to the removed correlation is taken as the degree of compliance of the vibration velocity correlation at the jth moment during the i-th braking experiment.

5. The brake disc performance prediction method based on artificial intelligence according to claim 1, characterized in that: The specific method of dividing all moments of the brake disc during each braking test into multiple rotation cycles includes: The outer edge circumference of the brake disc is read through the brake disc parameter configuration system; a two-dimensional coordinate system is constructed with time as the horizontal axis and the edge linear velocity data as the vertical axis, and the edge linear velocity data of the brake disc at all moments during the i-th braking test are input into the two-dimensional coordinate system to obtain the edge linear velocity curve of the brake disc during the i-th braking test; all segmentation points on the edge linear velocity curve of the brake disc during the i-th braking test are obtained, and the integral value between any two adjacent segmentation points is equal to the outer edge circumference of the brake disc; the time period formed by the moments corresponding to any two adjacent segmentation points is recorded as the rotation period of the brake disc during the i-th braking test.

6. The brake disc performance prediction method based on artificial intelligence according to claim 1, characterized in that: The above method of obtaining the braking effect excellence of the brake disc during each braking test based on the similarity of the distribution of the braking stress loss degree of the brake disc during each rotation cycle during each braking test includes the following specific methods: A two-dimensional coordinate system is constructed with time as the horizontal axis and the degree of brake stress loss as the vertical axis. The degree of brake stress loss of the brake disc at all times during the i-th braking test is input into the two-dimensional coordinate system to obtain a brake stress loss degree curve of the brake disc during the i-th braking test. The brake stress loss degree curve of the brake disc during the i-th braking test is divided into multiple curve segments according to the rotation cycle of the brake disc during the i-th braking test. Combine all curve segments into any two combinations to obtain several curve segment combinations. Use the DTW algorithm to obtain the DTW value between the two curve segments in each curve segment combination, and record it as the distribution similarity of each curve segment combination. The mean of the distribution similarities of all curve segment combinations is used as the degree of compliance with the periodic law of the brake disc during the i-th braking test. The normalized value of the inverse proportion between the reciprocal of the degree of compliance of the brake disc with the periodic law during the i-th braking test and the average value of the braking stress loss degree of the brake disc at all moments during the i-th braking test is taken as the braking effect excellence of the brake disc during the i-th braking test.

7. The brake disc performance prediction method based on artificial intelligence according to claim 1, characterized in that: The temperature control performance of the brake disc during each braking test is obtained according to the change in the temperature data of the brake disc during each braking test, including the following specific methods: A two-dimensional coordinate system is constructed with time as the horizontal axis and temperature data as the vertical axis. The temperature data of the brake disc at all times during the i-th braking test are input into the two-dimensional coordinate system to obtain a temperature data change curve of the brake disc during the i-th braking test; the data point corresponding to the maximum temperature data in the temperature data change curve is recorded as the peak temperature data point; the data point corresponding to the indoor temperature in the temperature data change curve is recorded as the indoor temperature data point; Starting from the peak temperature data point, traverse until the first indoor temperature data point is encountered, and the data segment formed by all data points in the traversal process is recorded as the heat dissipation data segment; The product of the absolute value of the mean slope of all data points in the heat dissipation data segment and the inverse of the temperature data of the peak temperature data point is used as the temperature control performance of the brake disc during the i-th braking test.

8. The brake disc performance prediction method based on artificial intelligence according to claim 1, characterized in that: The specific method for obtaining the degree of braking performance of the brake disc during each braking test based on the degree of temperature control performance and the degree of braking effect excellence is as follows: The product of the temperature control performance of the brake disc during the i-th braking test and the braking effect excellence of the brake disc during the i-th braking test is used as the braking performance reflection degree of the brake disc during the i-th braking test.

9. The brake disc performance prediction method based on artificial intelligence according to claim 1, characterized in that: The specific method for obtaining the performance excellence of the brake disc according to the changing trend of the braking performance of the brake disc during different braking tests is as follows: A two-dimensional coordinate system is constructed with the braking test order as the horizontal axis and the braking performance reflection degree as the vertical axis. The braking performance reflection degree of the n-th brake disc during all braking tests is input into the two-dimensional coordinate system, and the least squares method is used for linear fitting to obtain the braking performance reflection performance line of the n-th brake disc; the normalized value of the product of the slope of the braking performance reflection performance line of the n-th brake disc and the mean value of the braking performance reflection degree of the n-th brake disc during all braking tests is used as the performance excellence of the n-th brake disc.

10. The brake disc performance prediction method based on artificial intelligence according to claim 1, characterized in that: The specific method for obtaining the braking performance prediction coefficient of each brake disc based on the difference in performance excellence between different brake discs is as follows: The reciprocal of the absolute value of the difference between the performance excellence of the nth brake disc and the mean of the performance excellence of all brake discs is recorded as the first reciprocal; the normalized value of the product of the first reciprocal and the performance excellence of the nth brake disc is used as the braking performance prediction coefficient of the nth brake disc.

Images