Diagnostic methods and diagnostic devices for brake pads

Abstract

The present disclosure relates to an apparatus and method for diagnosing brake pad conditions and abnormal phenomena by analyzing vibration sensor or acoustic sensor data and CAN bus signal data. A vehicle brake diagnosis method according to one aspect of the present disclosure includes the steps of acquiring a vehicle's CAN bus signal and sensor data, performing a diagnosis of normal wear of a brake pad based on the CAN bus data, performing a diagnosis of the brake's condition based on the sensor data, and performing a comprehensive diagnosis of the brake by combining the result of the normal wear diagnosis and the result of the condition diagnosis.

Description

Technology Field

[0001] The following embodiments relate to a device and method for diagnosing abnormalities in a brake pad. More specifically, they relate to a device and method for diagnosing the condition of a brake pad and abnormal phenomena by analyzing vibration sensor or acoustic sensor data and CAN bus signal data. Background Technology

[0002] In the past, checking the wear of brake pads was done by the user directly or by using a U-shaped metal clip that induces noise when the pad reaches a certain thickness or lower.

[0003] Recently, the results of advancements in various industrial sectors are being incorporated into vehicles, and as automotive technology develops, research and development on autonomous vehicles are continuing. Consequently, a variety of services related to autonomous vehicles are emerging. Furthermore, as autonomous vehicles become more widespread, researchers anticipate that vehicle ownership will gradually shift towards a sharing concept, considering factors such as cost, environmental impact, and user convenience.

[0004] Furthermore, with the expansion of connectivity between user devices and vehicles driven by advancements in internet technology, autonomous vehicle sharing services are gradually emerging for a diverse range of users based on the development of autonomous vehicle technology. Consequently, there is a need to develop technology that allows users to check brake pad wear and abnormalities based on data from attached sensors, without having to physically inspect the wear themselves.

[0005] The aforementioned background technology is technical information that the inventor possessed for the derivation of the present invention or acquired during the process of deriving the present invention, and it cannot be considered as prior art disclosed to the general public prior to the filing of the present invention. The problem to be solved

[0006] The present invention aims to provide a method for checking wear and abnormal phenomena based on data from an attached sensor without the user having to directly check the wear.

[0007] The problems that the present invention aims to solve are not limited to those mentioned above, and other problems and advantages of the present invention not mentioned can be understood from the following description and will be more clearly understood by the embodiments of the present invention. Furthermore, it will be understood that the problems and advantages that the present invention aims to solve can be realized by the means and combinations thereof set forth in the claims. means of solving the problem

[0008] A method for diagnosing a vehicle brake according to one aspect includes the steps of: acquiring a CAN bus signal and sensor data of a vehicle; performing a diagnosis of normal wear of a brake pad based on the CAN bus data; performing a diagnosis of the condition of the brake based on the sensor data; and combining the result of the diagnosis of normal wear and the result of the diagnosis of the condition to perform a comprehensive diagnosis of the brake.

[0009] A vehicle brake diagnostic device according to another aspect comprises: a memory in which at least one program is stored; and at least one processor that operates by executing the at least one program, wherein the processor performs a diagnosis of normal wear of a brake pad based on CAN bus data of the vehicle, performs a diagnosis of the condition of the brake based on sensor data of the vehicle, and performs a comprehensive diagnosis of the brake by combining the result of the diagnosis of normal wear and the result of the diagnosis of the condition.

[0010] A computer-readable recording medium according to another aspect includes a recording medium that records a program for executing the above-described method on a computer. Effects of the invention

[0011] According to the means for solving the problem of the present disclosure described above, data from various sensors can be pre-processed and extracted using CAN bus data, and abnormal phenomena such as brake pad condition, judder, and squeal can be diagnosed based on vibration and noise characteristics due to brake wear.

[0012] In addition, since the above process is performed on the server side and includes a transmission and reception process for verification on the user display, the user can also check the brake pad status in real time. As a result, costs for managing multiple vehicles can be reduced, and accidents caused by brake pad defects can be prevented in advance by providing the user with the replacement timing based on the brake pads.

[0013] In addition, since abnormal phenomena can be identified based on data from attached sensors without the user having to directly check the degree of wear, multiple vehicles can be effectively managed in a shared vehicle system. The effects of the embodiments are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art from the description of the present invention. Brief explanation of the drawing

[0014] FIG. 1 is a drawing for illustrating an example of a vehicle brake diagnostic system according to one embodiment. FIG. 2 is a flowchart illustrating an example of a vehicle brake diagnosis method according to one embodiment. FIG. 3 is a flowchart illustrating an example of an overall process for performing normal wear diagnosis and brake condition diagnosis according to one embodiment. FIG. 4 is a flowchart illustrating an example of a method for a diagnostic device according to one embodiment to obtain a brake status diagnosis result. FIG. 5 is a flowchart illustrating an example of a method for a diagnostic device according to one embodiment to obtain a normal wear diagnosis result. FIG. 6 is an exemplary diagram showing the relationship between brake pad wear and brake hydraulic pressure in one embodiment. FIGS. 7a and FIGS. 7b are exemplary drawings for explaining the preprocessing of sensor data according to one embodiment. FIGS. 8a and FIGS. 8b are exemplary drawings for explaining a method for analyzing the frequency characteristics of a frequency domain signal according to one embodiment. FIG. 9 is an exemplary drawing for illustrating a method of extracting frequency characteristics according to one embodiment. FIGS. 10a and 10b are exemplary drawings for illustrating a method of classifying brake conditions according to one embodiment. FIG. 11 is a block diagram showing an example of a vehicle brake diagnostic device according to one embodiment. Specific details for implementing the invention

[0015] The terms used in the embodiments have been selected to be as close as possible to currently widely used general terms; however, these may vary depending on the intent of those skilled in the art, case law, the emergence of new technologies, etc. Additionally, in specific cases, terms have been selected at the applicant's discretion, and in such cases, their meanings will be described in detail in the relevant description section. Therefore, terms used in the specification must be defined not merely by their names, but based on their meanings and the content throughout the specification.

[0016] When a part of the specification is described as “comprising” a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components. Furthermore, terms such as “~ unit” and “~ module” as used in the specification refer to a unit that processes at least one function or operation, and this may be implemented in hardware or software, or as a combination of hardware and software.

[0017] Additionally, terms including ordinal numbers, such as “first” or “second” used in the specification, may be used to describe various components, but said components should not be limited by said terms. said terms may be used for the purpose of distinguishing one component from another.

[0018] Embodiments are described in detail below with reference to the attached drawings. However, embodiments may be implemented in various different forms and are not limited to the examples described herein.

[0020] FIG. 1 is a drawing for illustrating an example of a vehicle brake diagnostic system according to one embodiment.

[0021] A vehicle brake diagnostic system (10) according to one embodiment may include a vehicle (101) and a diagnostic device (100) including an acoustic sensor (110), a vibration sensor (120), a CAN bus (130), a data collection module (140), a communication module (150), and a display (160).

[0022] The acoustic sensor (110) can be used to collect noise data generated when the vehicle brakes are operated and to determine the wear condition of the brake pads. The acoustic sensor (110) can measure not only human audible frequencies but also sounds below and above audible frequencies.

[0023] The vibration sensor (120) can collect vibration data generated when the vehicle's brakes are operated. The vibration sensor (120) can detect vibrations generated by friction between the brake pad and the disc.

[0024] The CAN bus (130) is a network system that enables communication between various control devices within a vehicle. The CAN bus (130) can transmit CAN bus data, such as vehicle speed, brake operation status, brake hydraulic pressure, and steering angle (steering angle), to a data collection module (140).

[0025] The data collection module (140) may be configured to collect acoustic data, vibration data, and CAN bus data in real time and store them in memory (not shown). According to one embodiment, the data collection module (140) may control the collected sensor data and CAN bus data to be transmitted to the diagnostic device (100) in real time through the communication module (150).

[0026] According to another embodiment, the data collection module (140) determines whether the collected sensor data and CAN bus data satisfy a predetermined standard to determine the data to be analyzed, and controls the data to be analyzed so that it can be transmitted to the diagnostic device (100) through the communication module (150).

[0027] The communication module (150) may provide a configuration or function for the vehicle (101) and the diagnostic device (100) to communicate with each other via a network. Additionally, the communication module (150) may transmit data collected in real time by the data collection module (140) or data determined as data to be analyzed by the data collection module (140) to the diagnostic device (100).

[0028] The display (160) can provide the driver of the vehicle (101) with the results of the brake condition diagnosis in real time. The display (160) can visually display the wear condition of the brake pads and whether there are abnormal phenomena (squeal, judder, etc.), so that the driver can take appropriate measures according to the condition of the brake pads without having to check the condition of the brake pads directly.

[0029] The diagnostic device (100) is a device that acquires CAN bus signals and sensor data of a vehicle (101) and analyzes them to diagnose the condition of the brake pads. The diagnostic device (100) can perform a diagnosis of normal wear of the brake pads based on CAN bus data and can perform a diagnosis of the condition of the brakes based on sensor data. In addition, the diagnostic device (100) can perform a comprehensive diagnosis of the brakes by combining the results of the normal wear diagnosis and the results of the condition diagnosis.

[0031] FIG. 2 is a flowchart illustrating an example of a vehicle brake diagnosis method according to one embodiment.

[0032] Referring to FIG. 2, in step 210, the diagnostic device (100) can acquire CAN bus data and sensor data of the vehicle.

[0033] CAN bus data may include at least one of the wheel speed, brake operation status, brake hydraulic pressure, and steering angle of the vehicle. Additionally, sensor data may be obtained from at least one of the acoustic sensor or vibration sensor of the vehicle.

[0034] According to one embodiment, the diagnostic device (100) can acquire CAN bus data and sensor data collected in real time by a data collection module of a vehicle, and determine data to be analyzed based on the acquired CAN bus data.

[0035] According to another embodiment, the diagnostic device (100) can acquire data to be analyzed, which is determined as an analysis target by a data collection module of a vehicle based on predetermined conditions.

[0036] For convenience of explanation, an example of a diagnostic method described below with reference to FIGS. 2 to 8b involves a diagnostic device (100) acquiring CAN bus data and sensor data collected in real time and performing an operation to determine data to be analyzed that satisfies a predetermined condition. However, it will be easily understood by those skilled in the art that each step of the diagnostic method described below applies even when the diagnostic device (100) acquires data to be analyzed determined by the data collection module (140) of FIG. 1.

[0038] In step 220, the diagnostic device (100) can perform a diagnosis of normal wear of the brake pad based on CAN bus data.

[0039] Normal wear refers to the natural wear condition that occurs as a vehicle is driven. Normal wear diagnosis is performed by calculating the remaining thickness of the brake pad and evaluating the degree of wear by comparing it with the initial thickness. A specific example of how the diagnostic device (100) of the present disclosure performs normal wear diagnosis is described later in FIG. 5.

[0040] In step 230, the diagnostic device (100) can perform a diagnosis of the brake's condition based on sensor data.

[0041] According to one embodiment, the condition of the brake can be classified into any one of judder, squeal, normal wear, or abnormal wear. Judder and squeal are typical NVH (Noise, Vibration, and Harshness) problems that occur in a brake system.

[0042] Squeal is primarily caused by self-excited vibrations induced by friction with the disc pads and geometric instability of the brake resonance system. Squeal occurs in the high-frequency band of thousands of Hz and is characterized by being independent of speed.

[0043] Judder is known to be caused by unstable friction between a disc and a pad that has been thermally deformed by frictional heat, which generates heat spots, and by changes in Surface Runout (SRO) and Disc Thickness Variation (DTV) exacerbated by the grown heat spots. Judder appears in the low-frequency band of tens to hundreds of Hz and has the characteristic of vibrating in proportion to speed.

[0044] Abnormal wear refers to an abnormal wear condition of the brake pads and may include uneven wear or excessive wear.

[0045] According to one embodiment, the diagnostic device (100) can determine the data to be analyzed that satisfies the straight driving condition and the brake operating condition in the sensor data based on the CAN bus data.

[0046] At this time, the diagnostic device (100) can determine whether the straight driving condition is satisfied by using the steering angle included in the CAN bus data. For example, the diagnostic device (100) can determine that the straight driving condition is satisfied when the steering angle is below a predetermined threshold value. Alternatively, the diagnostic device (100) can determine that the straight driving condition is satisfied when the steering angle is 0. The diagnostic device (100) of the present disclosure can increase the accuracy of the analysis by using data when the vehicle is driving in a straight line as the subject of analysis.

[0047] Additionally, the diagnostic device (100) can determine whether the brake operation condition is satisfied by using the brake operation status included in the CAN bus data. According to one embodiment, the diagnostic device (100) can determine that the brake operation condition is satisfied when the brake operation status signal included in the CAN bus data is in the ON state.

[0048] According to another embodiment, the diagnostic device (100) can determine that the brake operation condition is satisfied when the vehicle is in a deceleration state by using wheel speed data included in the CAN bus data. Alternatively, the diagnostic device (100) can determine whether the brake operation condition is satisfied by considering both whether the brake is operated and the wheel speed.

[0049] The diagnostic device (100) of the present disclosure can effectively analyze acoustic and vibration data generated during brake operation by determining the data when the brake is in operation as the target for analysis.

[0050] Additionally, the diagnostic device (100) can extract data to be analyzed in response to the wheel speed of the satisfying data reaching a preset analysis start speed. For example, the preset analysis start speed may be set to 30 km / h or 50 km / h, but may be set in various ways and is not limited to the stated numerical values. The diagnostic device (100) of the present disclosure can analyze data in a stable driving state by making the data after the vehicle reaches a specific speed the target of analysis.

[0051] Subsequently, the diagnostic device (100) can convert the data to be analyzed into frequency domain data. For example, the diagnostic device (100) can convert the data to be analyzed, which is time series data, into frequency domain data through a Fast Fourier Transform (FFT). According to one embodiment, the diagnostic device (100) can extract frequency features from the frequency domain data. The frequency features may include average amplitude values ​​for each frequency band at regular intervals.

[0052] The diagnostic device (100) can diagnose the brake condition by using the extracted frequency characteristics as input to a machine learning-based classification model and obtaining the classification result as output. At this time, the classification model can classify the brake condition into at least one of squeal, judder, normal wear, and abnormal wear based on the extracted frequency characteristics.

[0053] Neural Networks and Support Vector Machines (SVMs) can be used as classification models, and training and validation are performed using cross-validation and the hold-out method. The classification model trained and validated in this way diagnoses the brake condition by continuously classifying newly generated data during actual vehicle usage.

[0054] According to another embodiment, the diagnostic device (100) can extract time-series features from the data to be analyzed, which is time-series data. In this case, the time-series features may include statistical characteristics such as mean, root mean square (RMS), data percentile, maximum value, minimum value, variance, standard deviation, peak to peak, skewness, kurtosis, and entropy. According to another embodiment, the diagnostic device (100) can use frequency features and time-series features as inputs to a classification model.

[0056] FIG. 4 is a flowchart illustrating an example of a method for a diagnostic device according to one embodiment to obtain a brake status diagnosis result.

[0057] Referring to FIG. 4, the diagnostic device (100) can analyze frequency domain data characteristics in step 400 and determine whether the low frequency band increases in step 401.

[0058] And, in step 402, the diagnostic device (100) can obtain a judder diagnosis result in response to an increase in the low frequency band. Judder is diagnosed based on the characteristic that it appears at low frequencies of tens to hundreds of Hz and vibrates in proportion to speed.

[0059] In step 403, the diagnostic device (100) can determine whether the abnormal wear observation band increases if the low frequency band does not increase.

[0060] In step 404, the diagnostic device (100) can obtain a squeal diagnosis result if the abnormal wear observation band does not increase. That is, the diagnostic device (100) can obtain a squeal diagnosis result if the high-frequency band increases. Squeal is diagnosed based on characteristics that appear at high frequencies of thousands of Hz and are independent of speed.

[0061] Additionally, in step 405, the diagnostic device (100) can obtain an abnormal wear diagnosis result in response to an increase in the abnormal wear observation band.

[0062] Since judder is a vibration that occurs when the brake pedal is pressed and has the most direct effect on the driver, the diagnostic device (100) of the present disclosure can perform judder diagnosis by first determining whether there is an increase in the low-frequency band. The diagnostic device (100) can determine the applicability in the order of judder, squeal, and abnormal wear, which have a significant impact on the safety and performance of the brake system, and obtain a diagnostic result. However, this diagnostic order is merely one embodiment and is not limited thereto.

[0064] Referring again to FIG. 2, in step 240, the diagnostic device (100) can perform a comprehensive diagnosis of the brake by combining the normal wear diagnosis result and the condition diagnosis result.

[0065] For example, the diagnostic device (100) can verify the diagnostic result by comparing the result of normal wear diagnosis based on CAN bus data and the result of brake condition diagnosis based on sensor data.

[0067] FIG. 3 is a flowchart illustrating an example of an overall process for performing normal wear diagnosis and brake condition diagnosis according to one embodiment.

[0069] First, with reference to steps 310 through 316, an example of a brake condition diagnosis method based on sensor data will be described.

[0070] In step 310, the diagnostic device (100) can acquire sensor data.

[0071] In step 311, the diagnostic device (100) can divide and preprocess the acquired sensor data. Specific examples of the method for preprocessing sensor data are described later in FIGS. 7a and FIGS. 7b.

[0072] In step 312, the diagnostic device (100) can determine the data to be analyzed from the preprocessed sensor data based on the CAN bus data.

[0073] For example, the diagnostic device (100) can determine the data satisfying a predetermined condition as the data to be analyzed based on whether the brake is operated, the steering angle, and the wheel speed included in the CAN bus data.

[0074] In step 313, the diagnostic device (100) can convert the data to be analyzed into frequency domain data.

[0075] In step 314, the diagnostic device (100) can extract characteristics for classifying the brake state based on data. According to one embodiment, the characteristics may be frequency characteristics extracted from frequency domain data and may include average amplitude values ​​for each frequency band at regular intervals. According to another embodiment, the characteristics may further include time series characteristics extracted from data to be analyzed in a time series.

[0076] In step 315, the diagnostic device (100) can select significant characteristics from among the extracted characteristics. According to one embodiment, the diagnostic device (100) can select significant characteristics using statistical methods such as the Kruskal-Wallis test.

[0077] In step 316, the diagnostic device (100) can diagnose the brake condition using selected characteristics. For example, the diagnostic device (100) can classify the brake condition into one of squeal, judder, normal wear, and abnormal wear by using the selected characteristics as input to a machine learning-based classification model.

[0079] Next, referring to steps 320 and 321, an example of a normal wear diagnosis method will be described.

[0081] In step 316, the diagnostic device (100) can acquire CAN bus data.

[0082] Subsequently, the diagnostic device (100) can determine data to be analyzed that satisfies a predetermined condition in the CAN bus data. At this time, the predetermined condition may be the same as the criteria for determining the data to be analyzed from the sensor data described above. That is, the data to be analyzed in normal wear diagnosis and brake condition diagnosis may be CAN bus data or sensor data of the same time interval.

[0083] In step 321, the diagnostic device (100) can perform normal wear diagnosis based on CAN bus data. A specific example of a normal wear diagnosis method is described later in FIG. 5.

[0085] FIG. 5 is a flowchart illustrating an example of a method for a diagnostic device according to one embodiment to obtain a normal wear diagnosis result.

[0086] Referring to FIG. 5, in step 510, the diagnostic device (100) acquires CAN bus data.

[0087] In step 510, the diagnostic device (100) can determine whether the measured hydraulic pressure value has increased relative to the initial hydraulic pressure value. In this case, the initial hydraulic pressure value refers to the reference value of the brake hydraulic pressure set at the time of manufacturing the vehicle. Additionally, the measured hydraulic pressure value refers to the brake hydraulic pressure value measured in real time while the vehicle is in motion.

[0088] If the measured hydraulic pressure value does not increase compared to the initial hydraulic pressure value, the diagnostic device (100) can continue to acquire CAN bus data without performing normal wear diagnosis and monitor whether it increases.

[0089] In step 530, the diagnostic device (100) can calculate the thickness of the remaining pad in response to determining that the measured hydraulic value has increased compared to the initial hydraulic value.

[0090] For example, the diagnostic device (100) can calculate the remaining thickness by substituting the measured hydraulic value into a hydraulic-wear relationship equation in response to the measured hydraulic value exceeding the initial hydraulic value. According to one embodiment, the hydraulic-wear relationship equation may be determined by extracting a trend of the amount of wear according to hydraulic pressure from a plurality of previously collected data including hydraulic values ​​and the amount of wear.

[0091] FIG. 6 is an exemplary diagram showing the relationship between brake pad wear and brake hydraulic pressure in one embodiment.

[0092] Referring to Fig. 6, it can be seen that the brake cylinder pressure changes depending on the degree of wear of the brake pad. In Fig. 6, the horizontal axis represents the remaining thickness of the worn brake pad as a percentage (%), and the vertical axis represents the brake cylinder pressure in Bar units. Referring to Fig. 6, it can be seen that the brake cylinder pressure tends to increase as the wear of the brake pad progresses. This is because as the brake pad wears down, its thickness decreases, and a higher hydraulic pressure is required to compensate for this.

[0093] In step 540, the diagnostic device (100) can obtain a normal wear diagnosis result based on the thickness of the remaining pad calculated.

[0095] Referring again to FIG. 3, in step 317, the diagnostic device (100) can perform a comprehensive diagnosis by combining the results of the normal wear diagnosis and the results of the brake condition diagnosis.

[0096] For example, the diagnostic device (100) can compare the normal wear diagnosis result with the brake condition diagnosis result to evaluate the overall condition of the vehicle's brake system and generate a diagnostic report recommending maintenance or replacement if necessary. The diagnostic device (100) transmits the overall diagnostic result to the vehicle, and the driver can check the information on the brake condition through the vehicle display and take necessary actions.

[0098] FIGS. 7a and FIGS. 7b are exemplary drawings for explaining the preprocessing of sensor data according to one embodiment.

[0099] FIG. 7a shows the original signal divided and the data before preprocessing by the diagnostic device (100), and shows the change in amplitude on the time axis. According to one embodiment, the diagnostic device (100) can divide the signal collected from the sensor into fixed time intervals and then preprocess it.

[0100] First, the diagnostic device (100) can apply a band stop filter to remove unnecessary frequency components and remove sensor DC components to center the signal to zero. Subsequently, to prevent discontinuities at both ends of the signal, a Hanning window can be applied to smooth the signal. FIG. 7b shows a signal after preprocessing is complete, illustrating the state in which unnecessary frequency components and DC components have been removed and a Hanning window has been applied.

[0102] FIGS. 8a and FIGS. 8b are exemplary drawings for explaining a method for analyzing the frequency characteristics of a frequency domain signal according to one embodiment.

[0103] Figure 8a shows data converted into the frequency domain by performing a Fast Fourier Transform (FFT) on time-series signals acquired from a sensor at 30%, 50%, 70%, and 100% wear remaining states. Figure 8a shows the signal change in the frequency domain according to the degree of brake pad wear. For example, it is possible to visually check how the frequency characteristics change at 30%, 50%, 70%, and 100% wear remaining states.

[0104] Figure 8b shows the data from Figure 8a processed to average the values ​​to reduce noise.

[0105] The diagnostic device (100) can reduce noise and identify the overall trend of the signal by grouping the converted frequency domain signals into a predetermined number and performing average value processing. Through this, changes in frequency characteristics according to the residual wear state become more distinct.

[0107] FIG. 9 is an exemplary drawing for illustrating a method of extracting frequency characteristics according to one embodiment.

[0108] Referring to FIG. 9, the frequency domain signal can be divided into multiple frequency bands (f_1, f_2, …, f_k) at regular intervals. The diagnostic device (100) can calculate an average amplitude value within each frequency band (f_1, f_2, …, f_k) and use it as a frequency characteristic.

[0110] FIG. 10 is an exemplary drawing illustrating a method for selecting important characteristics for brake condition diagnosis according to one embodiment.

[0111] Referring to FIG. 10, the diagnostic device (100) can select important features among the features extracted through the Kruskal-Wallis test. The horizontal axis of FIG. 10 represents the Importance Score, and the vertical axis represents the Feature. For example, the features of the frequency bands 1500-2000 Hz and 5000-5500 Hz may be determined to have the highest importance. This means that the signals in the frequency bands provide important information for brake condition diagnosis.

[0112] According to one embodiment, the diagnostic device (100) selects top features with high importance scores and inputs them into a classification model (e.g., Quadratic-SVM model) to predict the remaining state of the brake pad.

[0114] FIG. 11 is a block diagram showing an example of a vehicle brake diagnostic device according to one embodiment.

[0115] Referring to FIG. 11, the vehicle brake diagnostic device (1100) of the present disclosure may include a communication module (1110), a processor (1130), and a memory (1120). Only the components related to the embodiment are shown in the vehicle brake diagnostic device (1100) of FIG. 7. Therefore, a person skilled in the art will understand that other general-purpose components may be included in addition to the components shown in FIG. 11.

[0116] The communication module (1110) may include one or more components that enable wired / wireless communication with the vehicle's display, data collection module, vehicle communication module and / or other external devices. For example, the communication module (1110) may include at least one of a short-range communication unit (not shown), a mobile communication unit (not shown), and a broadcast receiving unit (not shown).

[0117] The memory (1120) is hardware that stores various data processed within the vehicle brake diagnostic device (1100) and can store a program for processing and controlling the processor (1130).

[0118] The memory (1120) may include RAM (random access memory), such as DRAM (dynamic random access memory) and SRAM (static random access memory), ROM (read-only memory), EEPROM (electrically erasable programmable read-only memory), CD-ROM, Blu-ray or other optical disc storage, HDD (hard disk drive), SSD (solid state drive), or flash memory.

[0119] The processor (1130) controls the overall operation of the vehicle brake diagnostic device (1100). For example, the processor (1130) can control the input unit (not shown), display (not shown), communication module (1110), memory (1120), etc., by executing programs stored in memory (1120). The processor (1130) can control the operation of the vehicle brake diagnostic device (1100) by executing programs stored in memory (1120).

[0120] The processor (1130) can control at least some of the operations of the diagnostic device (100) described in FIGS. 1 to 10.

[0121] For example, the processor (1130) can acquire CAN bus data and sensor data of the vehicle, perform a diagnosis of normal wear of the brake pad based on the CAN bus data, and perform a diagnosis of the condition of the brake based on the sensor data. Then, the processor (1130) can perform a comprehensive diagnosis of the brake by combining the results of the normal wear diagnosis and the results of the condition diagnosis.

[0122] Meanwhile, a specific example of the operation of the processor (1130) is the same as described above with reference to FIGS. 1 to 10. Therefore, a specific description of the operation of the processor (1130) is omitted below.

[0123] The processor (1130) may be implemented using at least one of ASICs (application specific integrated circuits), DSPs (digital signal processors), DSPDs (digital signal processing devices), PLDs (programmable logic devices), FPGAs (field programmable gate arrays), controllers, microcontrollers, microprocessors, and other electrical units for performing functions.

[0125] Meanwhile, the above-described method can be written as a program executable on a computer and can be implemented on a general-purpose digital computer that operates the program using a computer-readable recording medium. In addition, the structure of the data used in the above-described method can be recorded on a computer-readable recording medium through various means. The computer-readable recording medium includes storage media such as magnetic storage media (e.g., ROM, RAM, USB, floppy disk, hard disk, etc.) and optical reading media (e.g., CD-ROM, DVD, etc.).

[0126] A person skilled in the art related to the present embodiment will understand that it may be implemented in modified forms without departing from the essential characteristics of the description above. Therefore, the disclosed methods should be considered in an illustrative rather than a restrictive sense, and the scope of rights is defined in the claims rather than the description above, and should be interpreted to include all differences within the scope of equivalence. Explanation of the symbols

[0127] 10: Vehicle Brake Diagnostic System 101: Vehicle 100: Diagnostic device 110: Acoustic sensor 120: Vibration sensor 130: CAN bus 140: Data Collection Module 150: Communication module 160: Display

Claims

Claim 1 A vehicle brake diagnosis method comprising: a step of acquiring CAN bus data and sensor data of a vehicle; a step of performing a normal wear diagnosis of a brake pad by analyzing the relationship between brake pad wear and brake hydraulic pressure based on brake hydraulic pressure data included in the CAN bus data; a step of performing a condition diagnosis of a brake based on the sensor data; and a step of performing a comprehensive diagnosis of the brake by combining the result of the normal wear diagnosis and the result of the condition diagnosis, wherein the step of performing the normal wear diagnosis includes a step of calculating the remaining thickness of the brake pad using brake hydraulic pressure data included in the CAN bus data. Claim 2 delete Claim 3 The method according to claim 1, wherein the calculating step comprises: a step of determining whether a measured hydraulic value measured from brake hydraulic data exceeds an initial hydraulic value; and a step of calculating the remaining thickness by substituting the measured hydraulic value into a hydraulic-wear relationship equation in response to the fact that the measured hydraulic value exceeds the initial hydraulic value, wherein the hydraulic-wear relationship equation is determined by extracting a trend of the amount of wear according to hydraulic pressure from a plurality of previously collected data including hydraulic values ​​and the amount of wear. Claim 4 A method according to claim 1, wherein the step of performing the condition diagnosis comprises: determining analysis target data that satisfies straight driving conditions and brake operating conditions in the sensor data based on the CAN bus data; converting the analysis target data into frequency domain data; extracting frequency features from the frequency domain data; and classifying the state of the brake into one of squeal, judder, normal wear, and abnormal wear based on the extracted frequency features. Claim 5 In claim 4, the determining step comprises: a step of determining whether the wheel speed included in the CAN bus data has reached a preset analysis start speed; a method. Claim 6 In claim 4, the classifying step comprises the step of using the frequency characteristics as input to a machine learning-based classification model and obtaining a classification result as output; a method. Claim 7 A method according to claim 1, wherein the step of performing the comprehensive diagnosis comprises the step of verifying by comparing the result of the normal wear diagnosis and the result of the condition diagnosis. Claim 8 A method according to claim 1, wherein the CAN bus data includes at least one of the wheel speed, brake operation status, and steering angle of the vehicle, and the sensor data is obtained from at least one of the acoustic sensor or vibration sensor of the vehicle. Claim 9 A computer-readable recording medium storing a program for executing the method according to claim 1 on a computer. Claim 10 A vehicle brake diagnostic device comprising: a memory in which at least one program is stored; and at least one processor that operates by executing the at least one program, wherein the processor calculates the remaining thickness of a brake pad by utilizing brake hydraulic data included in the vehicle's CAN bus data, performs a diagnosis of normal wear of the brake pad using the remaining thickness, performs a diagnosis of the brake's condition based on the vehicle's sensor data, and performs a comprehensive diagnosis of the brake by combining the result of the normal wear diagnosis and the result of the condition diagnosis. Claim 11 delete Claim 12 In claim 10, the processor determines whether a measured hydraulic value measured from brake hydraulic data exceeds an initial hydraulic value, and in response to the measured hydraulic value exceeding the initial hydraulic value, calculates a remaining thickness by substituting the measured hydraulic value into a hydraulic-wear relationship equation, wherein the hydraulic-wear relationship equation is determined by extracting a trend of the amount of wear according to hydraulic pressure from a plurality of previously collected data including hydraulic values ​​and the amount of wear. Claim 13 In claim 10, the processor extracts data to be analyzed that satisfies straight driving conditions and brake operating conditions from sensor data based on CAN bus data, converts the data to be analyzed into frequency domain data, extracts frequency features from the frequency domain data, and classifies the state of the brake into one of squeal, judder, normal wear, and abnormal wear based on the extracted frequency features. Claim 14 In claim 13, the processor is a device that extracts the data to be analyzed in response to the wheel speed included in the CAN bus data reaching a preset analysis start speed. Claim 15 A device according to claim 10, wherein the CAN bus data includes at least one of the wheel speed, brake operation status, and steering angle of the vehicle, and the sensor data is obtained from at least one of the acoustic sensor or vibration sensor of the vehicle.

Images