Brake motor anomaly detection device and method and computer readable storage medium

Abstract

The invention discloses a brake motor anomaly detection device and method and a computer readable storage medium. A brake motor abnormality detection device, according to one aspect of the present invention, can detect an abnormality of a brake motor that generates a driving force for displacing a friction member to generate a braking force caused by friction when the friction member disposed on a wheel side of a vehicle is displaced, comprises: a memory for storing one or more commands; and a processor executing the one or more instructions, the processor inputting input data to an artificial neural network model by executing the one or more instructions and acquiring an estimated value of an output variable, and detecting whether the brake motor is abnormal by using the difference between the estimated value of the output variable and the measured value of the output variable, the artificial neural network model receiving the input data and outputting the estimated value of the output variable related to the output value of the brake motor.

Description

Technical Field

[0001] The present invention relates to a brake motor abnormality detection device, method and a computer-readable storage medium storing a program for executing the method, and more specifically, to a brake motor abnormality detection device, a brake motor abnormality detection method and a non-temporary computer-readable storage medium storing a program for executing the brake motor abnormality detection method for detecting an abnormality of a brake motor, wherein the brake motor generates a driving force for displacing a friction member to generate a braking force caused by friction when the friction member configured on the wheel side of a vehicle is displaced. Background Art

[0002] A braking system for braking must be provided on the vehicle. Recently, in order to improve the stability and efficiency of braking, an electromechanical braking system, namely an electromechanical brake (EMB) system, has been proposed.

[0003] Through the EMB system, general braking functions, anti-lock brake system (ABS), electronic stability control (ESC), vehicle dynamic control (VDC) and other functions can be integrated. In addition, the EMB system is conducive to the realization of the vehicle's automatic driving function.

[0004] The EMB system is configured to displace a friction member with the aid of a driving force provided by a brake motor, the friction member being arranged on each wheel side of the vehicle, and generating a braking force by friction during displacement. At this time, the friction member may be a brake pad that may pressurize a brake disc that rotates with the wheel. Furthermore, the brake motor may be arranged on each wheel of the vehicle. On the other hand, the brake motor may be driven by an electrical signal generated according to an input of a brake pedal.

[0005] When a brake motor fails in the EMB system as described above, a braking force corresponding to the input depth of the brake pedal cannot be generated, which may cause a fatal problem in terms of vehicle safety.

[0006] Generally speaking, the output torque of the brake motor may decrease due to demagnetization and corrosion of the insulation material. The output torque of such a brake motor shows a trend of gradually decreasing. Therefore, in order to improve the safety of the brake system, it is preferred to predict the abnormality of the brake motor in advance. However, the conventional method related to the detection of the abnormality of the brake motor still remains in the post-fault diagnosis and subsequent measures.

[0007] Prior art literature

[0008] Patent Literature

[0009] Korean Patent No. 2139586 "Brake actuator, electromechanical brake using the same, and control method thereof", granted on July 24, 2020 Summary of the invention

[0010] Problem that the invention aims to solve

[0011] The present invention aims to solve the above-mentioned problems, and the purpose of the present invention is to provide a brake motor abnormality detection device, a brake motor abnormality detection method and a non-temporary computer-readable storage medium storing a program for executing the brake motor abnormality detection method, which can detect the performance degradation of a brake motor before a failure occurs. The brake motor generates a driving force for shifting a friction member to generate a braking force through friction when the friction member arranged on the wheel side of a vehicle shifts.

[0012] Another object of the present invention is to provide a brake motor abnormality detection device, a brake motor abnormality detection method and a non-temporary computer-readable storage medium storing a program for executing the brake motor abnormality detection method, which utilizes the controller area network (CAN, Controller Area Network) signal in the vehicle to effectively detect the reduction in the output torque of the brake motor in advance.

[0013] Problems of the present invention are not limited to the above-mentioned problems, and other unmentioned problems will be clearly understood by those skilled in the art through the following description.

[0014] Means used to solve problems

[0015] According to one aspect of the present invention, there is provided a brake motor abnormality detection device for detecting abnormality of a brake motor, the brake motor generating a driving force for displacing a friction member so as to generate a braking force caused by friction when the friction member arranged on the wheel side of a vehicle is displaced, wherein the device comprises: a memory for storing one or more instructions; and a processor for executing the one or more instructions. The processor inputs input data into an artificial neural network model and obtains an estimated value of the output variable by executing the one or more instructions, the artificial neural network model receives the input data and outputs an estimated value of the output variable related to the output value of the brake motor, and the processor detects whether an abnormality occurs in the brake motor by using the difference between the estimated value of the output variable and the measured value of the output variable.

[0016] According to the brake motor abnormality detection device according to one aspect of the present invention, the input data may include any one or more of the speed of the vehicle, the lateral acceleration of the vehicle, the input displacement of the brake pedal, or the wheel speed of the vehicle.

[0017] According to the brake motor abnormality detection device of one aspect of the present invention, the output variable may include a brake clamping force generated according to a displacement of the friction member.

[0018] According to the brake motor abnormality detection device of one aspect of the present invention, the input data can be acquired through a controller area network (CAN) of the vehicle.

[0019] According to a brake motor abnormality detection device according to one aspect of the present invention, the artificial neural network model can be composed of a generative adversarial network (GAN), and the generative adversarial network may include: a generator, which receives the input data and generates an estimated value of the output variable; and a discriminator, which receives the measured value of the input data and the output variable and outputs a measurement-related identification value.

[0020] According to the brake motor abnormality detection device of one aspect of the present invention, the discriminator may also receive the input data and an estimated value of the output variable, and output an estimation-related discriminant value.

[0021] According to a brake motor abnormality detection device according to one aspect of the present invention, the artificial neural network model is constructed by alternately learning the generator and the discriminator with each other, and the input data and the measured values ​​of the output variables used in the learning may be data obtained when the vehicle and the brake motor are in normal conditions.

[0022] According to the brake motor abnormality detection device according to one aspect of the present invention, the generator may be composed of a multivariate transformer.

[0023] According to a brake motor abnormality detection device according to one aspect of the present invention, the processor can input error data into the abnormality detection module and determine whether the brake motor has an abnormality by executing one or more instructions, and the error data is associated with the difference between the estimated value of the output variable and the measured value of the output variable.

[0024] According to the brake motor abnormality detection device of one aspect of the present invention, the abnormality detection module may use a One-Class Support Vector Machine (OCSVM) algorithm.

[0025] According to a brake motor abnormality detection device according to one aspect of the present invention, there are multiple data sets, each of which includes the input data, the measured value of the output variable, and the estimated value of the output variable, and the error data may include: the mean value and standard deviation of the error between the measured value of the output variable obtained from each of the multiple data sets and the estimated value of the output variable; the maximum absolute error between the measured value of the output variable obtained from each of the multiple data sets and the estimated value of the output variable; and the identification value of the discriminator for the measured values ​​of the input data and the output variable included in the multiple data sets.

[0026] According to another aspect of the present invention, a brake motor abnormality detection method is provided, which detects abnormalities of a brake motor, wherein the brake motor generates a driving force for displacing a friction member to generate a braking force caused by friction when the friction member arranged on the wheel side of the vehicle is displaced, wherein the method may include: a processor inputs input data into an artificial neural network model by executing one or more instructions and obtains an estimated value of an output variable, the artificial neural network model receives the input data and outputs an estimated value of the output variable related to the output value of the brake motor; and a step in which the processor uses the difference between the estimated value of the output variable and the measured value of the output variable to detect whether an abnormality has occurred in the brake motor.

[0027] According to the brake motor abnormality detection method according to one aspect of the present invention, the input data may include any one or more of the vehicle speed, the vehicle lateral acceleration, the brake pedal input displacement, or the vehicle wheel speed.

[0028] According to the brake motor abnormality detection method according to one aspect of the present invention, the output variable may include a brake clamping force generated according to a displacement of the friction member.

[0029] According to a brake motor abnormality detection method according to one aspect of the present invention, the artificial neural network model can be composed of a generative adversarial network (GAN), which includes: a generator, which receives the input data and generates an estimated value of the output variable; and a discriminator, which receives the measured value of the input data and the output variable and outputs a measurement-related discriminant value.

[0030] According to a brake motor abnormality detection method according to one aspect of the present invention, the artificial neural network model is constructed by alternately learning the generator and the discriminator with each other, and the data used in the learning may be data obtained when the vehicle and the brake motor are in normal states.

[0031] According to a brake motor abnormality detection method according to one aspect of the present invention, the step of detecting whether an abnormality occurs in the brake motor may include: a step in which the processor inputs the input data and the measured value of the output variable into the discriminator and obtains a measurement-related identification value generated by the discriminator; and a step in which the processor inputs the estimation-related identification value and error data including a numerical value related to the difference between the estimated value of the output variable and the measured value of the output variable into an abnormality detection module and obtains the output of the abnormality detection module.

[0032] According to the brake motor abnormality detection method according to one aspect of the present invention, the abnormality detection module may use a One-Class Support Vector Machine (OCSVM) algorithm.

[0033] According to a brake motor abnormality detection method according to one aspect of the present invention, there are multiple data sets, each of which includes the input data, the measured value of the output variable and the estimated value of the output variable, and the error data may include: the mean value and standard deviation of the error between the measured value of the output variable obtained from each of the multiple data sets and the estimated value of the output variable; the maximum absolute error between the measured value of the output variable obtained from each of the multiple data sets and the estimated value of the output variable; and the identification value of the discriminator for the measured values ​​of the input data and the output variable included in the multiple data sets.

[0034] According to still another aspect of the present invention, there is provided a non-transitory computer-readable storage medium storing a program, the program including at least one instruction for executing the brake motor abnormality detection method.

[0035] Effects of the Invention

[0036] According to the above configuration, a brake motor abnormality detection device, method and a non-temporary computer-readable storage medium storing a program for executing the method according to one aspect of the present invention can predict the performance degradation of a brake motor in advance before a brake motor fails based on an artificial intelligence-based digital twin algorithm, wherein the brake motor generates a driving force for displacing a friction member to generate a braking force caused by friction when the friction member configured on the wheel side of the vehicle is displaced.

[0037] Furthermore, according to one aspect of the present invention, a brake motor abnormality detection device, method, and a non-temporary computer-readable storage medium storing a program for executing the method can utilize the vehicle's controller area network (CAN) signal to detect performance degradation of the brake motor without the need for any additional separate sensors.

[0038] The effects of the present invention are not limited to the above-mentioned effects, and should be understood to include all effects that can be inferred from the structure of the present invention described in the detailed description of the present invention or the claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 is a diagram schematically showing the configuration of an electromechanical brake system of a vehicle.

[0040] Figure 2 FIG. 1 is a diagram showing the arrangement of a braking device arranged at each wheel in an electromechanical brake system.

[0041] Figure 3 : is a diagram showing a configuration of a brake motor abnormality detection device according to one embodiment of the present invention.

[0042] Figure 4 : is a diagram showing a model for acquiring an estimated value or for detecting abnormality in a brake motor abnormality detection device according to one embodiment of the present invention.

[0043] Figure 5 is a diagram showing a detailed configuration of an artificial neural network model.

[0044] Figure 6 is a diagram showing a detailed configuration of a generator of an artificial neural network model.

[0045] Figure 7 1 is a diagram showing the operation of the brake motor abnormality detection device according to one embodiment of the present invention.

[0046] Figure 8 is a sequence diagram of a brake motor abnormality detection method according to an embodiment of the present invention.

[0047] Fig. 9 Detailed sequence diagram of steps for detecting whether an abnormality occurs in a brake motor according to a brake motor abnormality detection method according to an embodiment of the present invention.

[0048] Description of Reference Numerals

[0049] 100: Brake motor abnormality detection device

[0050] 110: Memory

[0051] 120: Processor DETAILED DESCRIPTION

[0052] Below, embodiments of the present invention will be described in detail in conjunction with the accompanying drawings so that those skilled in the art can easily implement these embodiments. The present invention can be implemented in a variety of different forms and is not limited to the embodiments described herein. In order to clearly explain the present invention, parts that are not related to the description are omitted in the accompanying drawings, and the same or similar parts are represented by the same reference numerals throughout the specification.

[0053] The words and terms used in this specification and claims should not be interpreted as limited to the commonly used meanings or meanings in dictionaries, but should be interpreted as having meanings and concepts consistent with the technical scope of the present invention, based on the principle that inventors can define terms and concepts in order to explain their own inventions in the best manner.

[0054] In this specification, terms such as "including" or "having" should be understood as describing the existence of features, numbers, steps, actions, constituent elements, parts or their combinations recorded in the specification, without excluding the existence or additional possibilities of one or more other features or numbers, steps, actions, constituent elements, parts or their combinations in advance.

[0055] Figure 1 is a diagram schematically showing the configuration of an electromechanical brake system of a vehicle.

[0056] The electromechanical brake system 200, namely an electromechanical brake (EMB) system, is configured in the vehicle and performs braking of the vehicle. Different from the conventional hydraulic disc brake, the electromechanical brake system 200 utilizes an actuator driven by a brake motor and a mechanical operation principle to perform braking.

[0057] The electromechanical brake system 200 has a faster braking response speed than a conventional hydraulic disc brake and can accurately and independently control each wheel, thereby improving braking safety performance.

[0058] Reference Figure 1The electronic mechanical braking system 200 may include a brake pedal 210, a pedal simulator 220, a pedal displacement sensor 230, an electronic control unit 240, a vehicle speed sensor 250, an acceleration sensor 260, a first braking device 270a configured at the front left wheel, a second braking device 270b configured at the front right wheel, a third braking device 270c configured at the rear left wheel, a fourth braking device 270d configured at the rear right wheel, a first wheel speed sensor 280a configured at the front left wheel, a second wheel speed sensor 280b configured at the front right wheel, a third wheel speed sensor 280c configured at the rear left wheel, and a fourth wheel speed sensor 280d configured at the rear right wheel.

[0059] When the driver's pedal force is input to the brake pedal 210, the brake pedal 210 is displaced to one side (for example, the front of the vehicle). The pedal simulator 220 provides a reaction force to the brake pedal 210. Thus, the driver can feel an appropriate pedal feel.

[0060] The pedal displacement sensor 230 detects an input depth of the brake pedal 210 , that is, detects an input displacement of the brake pedal 210 . The input displacement of the brake pedal detected by the pedal displacement sensor 230 may be transmitted to the electronic control unit 240 .

[0061] The electronic control unit 240 generates a control signal to be transmitted to the first braking device 270a, the second braking device 270b, the third braking device 270c, or the fourth braking device 270d based on the input displacement of the brake pedal detected by the pedal displacement sensor 230.

[0062] At this time, the speed of the vehicle detected by the vehicle speed sensor 250 and the lateral acceleration of the vehicle detected by the acceleration sensor 260 may also be transmitted to the electronic control unit 240. The electronic control unit 240 may apply the speed of the vehicle and the lateral acceleration of the vehicle together with the input displacement of the brake pedal in generating the control signal.

[0063] The first brake device 270a, the second brake device 270b, the third brake device 270c and the fourth brake device 270d can brake the wheels configured by each brake device according to the control signal. The first brake device 270a, the second brake device 270b, the third brake device 270c and the fourth brake device 270d can operate independently.

[0064] Figure 2 FIG. 1 is a diagram showing the arrangement of a braking device arranged at each wheel in an electromechanical brake system.

[0065] Reference Figure 2 , the first brake device 270a may include a first controller 271a, a first brake motor 272a and a first friction member 273a. The first controller 271a controls the first brake motor 272a so as to generate a required braking force according to the control signal. The first brake motor 272a is driven by the first controller 271a and provides a driving force for displacement to the first friction member 273a. The first friction member 273a can be displaced by the driving force provided by the first brake motor 272a, so that a braking force can be generated by friction. For example, the first friction member 273a can be a brake pad, and the brake pad can pressurize a brake disc that is arranged on the front left wheel of the vehicle and rotates with the wheel.

[0066] The motor torque T, the position information W of the motor, and the angular velocity θ of the motor generated by the driving of the first brake motor 272a can be fed back to the first controller 271a. The first controller 271a receives feedback about the motor torque T, the position information W of the motor, and the angular velocity θ of the motor and calculates the friction force, and can calculate the brake clamping force generated according to the displacement of the first friction member 273a.

[0067] The second brake device 270b may include a second controller 271b, a second brake motor 272b, and a second friction member 273b. Also, the third brake device 270c may include a third controller 271c, a third brake motor 272c, and a third friction member 273c. Also, the fourth brake device 270d may include a fourth controller 271d, a fourth brake motor 272d, and a fourth friction member 273d.

[0068] Operations of the second to fourth controllers 271b to 271d, the second to fourth brake motors 272b to 272d, and the second to fourth friction members 273b to 273d may be performed in the same manner as described with respect to the first controller 271a, the first brake motor 272a, and the first friction member 273a.

[0069] On the other hand, the first wheel speed sensor 280a detects the wheel speed of the front left wheel, the second wheel speed sensor 280b detects the wheel speed of the front right wheel, the third wheel speed sensor 280c detects the wheel speed of the rear left wheel, and the fourth wheel speed sensor 280d detects the wheel speed of the rear right wheel.

[0070] Each wheel speed detected by the first to fourth wheel speed sensors 280a to 280d may be fed back to the electronic control unit 240. The electronic control unit 240 may apply the vehicle wheel speed together with the input displacement of the brake pedal, the speed of the vehicle, and the lateral acceleration of the vehicle to generate the control signal.

[0071] Figure 3 1 is a diagram showing a configuration of a brake motor abnormality detection device according to an embodiment of the present invention. Figure 4 : is a diagram showing a model for acquiring an estimated value or for detecting abnormality in a brake motor abnormality detection device according to one embodiment of the present invention.

[0072] According to an embodiment of the present invention, a brake motor abnormality detection device 100 is used to detect an abnormality of a brake motor, which generates a driving force for displacing a friction member to generate a braking force generated by friction when the friction member configured on the wheel side of the vehicle is displaced. More specifically, the brake motor abnormality detection device 100 can detect a reduction in the output torque of the brake motor before the brake motor fails.

[0073] The brake motors may include all the first brake motors 272 a to the fourth brake motors 272 d included in the electronic mechanical brake system 200 .

[0074] According to an embodiment of the present invention, the brake motor abnormality detection device 100 can predict the function reduction of the brake motor before the brake motor fails by using an artificial intelligence-based digital twin algorithm. The digital twin algorithm can virtually construct an electronic mechanical brake system of the vehicle.

[0075] Reference Figure 3 , a brake motor abnormality detection device 100 according to an embodiment of the present invention may include a memory 110 and a processor 120 .

[0076] The memory 110 stores one or more instructions that can be executed by the processor 120 .

[0077] The memory 110 may include a hardware device configured to store and execute program instructions. For example, the memory 110 may include storage media such as a read-only memory (ROM), a random access memory (RAM), a flash memory, etc. In addition, the memory 110 may also include magnetic media such as floppy disks and magnetic tapes, optical recording media such as compact disk read only memory (CD-ROM), digital video disks (DVD), and magneto-optical media such as floptical disks.

[0078] The processor 120 executes the one or more instructions. For example, the processor 120 may be a hardware unit that performs calculations and controls in a computer. The processor 120 may include at least one arithmetic logic unit (ALU) and a register.

[0079] The processor 120 inputs the input data into the artificial neural network model 20 and obtains the estimated value of the output variable by executing the one or more instructions, wherein the artificial neural network model 20 receives the input data and outputs the estimated value of the output variable related to the output value of the brake motor 260.

[0080] The input data may include any one or more of the speed of the vehicle, the lateral acceleration of the vehicle, the input displacement of the brake pedal, or the wheel speed of the vehicle. For example, the input data may include the speed of the vehicle, the lateral acceleration of the vehicle, the input displacement of the brake pedal, and the wheel speed of the vehicle.

[0081] At this time, the wheel speed of the vehicle may be acquired for each of the plurality of wheels of the vehicle. In other words, the wheel speed of the vehicle may include the wheel speed of the front left wheel, the wheel speed of the front right wheel, the wheel speed of the rear left wheel, and the wheel speed of the rear right wheel detected by the first wheel speed sensor 280a to the fourth wheel speed sensor 280d, respectively.

[0082] The input data may be obtained from a Controller Area Network (CAN) 300 of the vehicle. For example, the input data may be transmitted to the memory 110 via the CAN 300 .

[0083] As described above, the input data may be acquired through the vehicle's controller area network 300. Thus, according to the present invention, there is no need to use an additional sensor to detect abnormality of the brake motor.

[0084] In this regard, the memory 110 may be directly or indirectly connected to the controller area network 300 of the vehicle. The memory 110 may receive the input data from the controller area network 300. Thus, the processor 120 may obtain the input data from the memory 110.

[0085] The output variable may include a brake clamping force generated according to the displacement of the friction member. In one embodiment of the present invention, the output variable may be the brake clamping force.

[0086] The brake clamping force may be obtained for each of the plurality of wheels of the vehicle. In other words, the brake clamping force may include: the brake clamping force of the first brake device 270a generated by the first friction member 273a; the brake clamping force of the second brake device 270b generated by the second friction member 273b; the brake clamping force of the third brake device 270c generated by the third friction member 273c; and the brake clamping force of the fourth brake device 270d generated by the fourth friction member 273d.

[0087] The artificial neural network model 20 receives the input data and outputs an estimated value of an output variable related to the output value of the brake motor. More specifically, the artificial neural network model 20 may receive the input data and output an estimated value of a brake clamping force generated according to the displacement of the friction member.

[0088] The estimated value of the brake clamping force may include: an estimated value of the brake clamping force of the first brake device 270a generated by the first friction member 273a; an estimated value of the brake clamping force of the second brake device 270b generated by the second friction member 273b; an estimated value of the brake clamping force of the third brake device 270c generated by the third friction member 273c; and an estimated value of the brake clamping force of the fourth brake device 270d generated by the fourth friction member 273d.

[0089] The estimated value of the output variable is obtained for comparison with the measured value of the output variable. As described above, the output variable may be the brake clamping force, and the measured value of the output variable may include: a measured value of the brake clamping force of the first brake device 270a generated by the first friction member 273a; a measured value of the brake clamping force of the second brake device 270b generated by the second friction member 273b; a measured value of the brake clamping force of the third brake device 270c generated by the third friction member 273c; and a measured value of the brake clamping force of the fourth brake device 270d generated by the fourth friction member 273d.

[0090] At this time, the measured value of the brake clamping force can be calculated by each controller of the brake device configured at each wheel of the vehicle receiving feedback about the operation information of each brake motor. For example, the operation information may include the motor torque T of the brake motor, the position information W of the motor, and the angular velocity θ of the motor.

[0091] In one embodiment of the present invention, the artificial neural network model 20 may be composed of a generative adversarial network (GAN).

[0092] In one embodiment of the present invention, the artificial neural network model 20 may be a deep learning based neural twin model for the vehicle's electronic mechanical brake system 200. In other words, the artificial neural network model 20 may function as a virtual twin model of the electronic mechanical brake system.

[0093] Figure 5 is a diagram showing a detailed configuration of an artificial neural network model.

[0094] Reference Figure 5 , the artificial neural network model 20 may include a generator 21 and a discriminator 22.

[0095] The artificial neural network model 20 can be constructed by alternately performing learning with each other by the generator 21 and the discriminator 22. At this time, the data used when performing learning can be data obtained when the vehicle and the electronic mechanical brake system are in a normal state. Thus, the estimated value of the output variable can follow the measured value of the output variable obtained when the vehicle and the electronic mechanical brake system are in a normal state.

[0096] The generator 21 receives the input data and generates an estimated value of the output variable. The generator 21 may include a neural network. The generator 21 may be composed of a multivariate transformer. That is, the artificial neural network model 20 may be a generative adversarial network (GAN) based on a multivariate transformer.

[0097] In one embodiment of the present invention, the generator 21 may receive the input data. As described above, the input data may include any one or more of the vehicle speed, the vehicle lateral acceleration, the brake pedal input displacement, or the vehicle wheel speed.

[0098] The generator 21 may calculate the input data and output an estimated value of the output variable. In this case, the output variable may be a brake clamping force generated according to the displacement of the friction member. In one embodiment of the present invention, when the electronic mechanical brake system of the vehicle is in a normal state, the estimated value of the output variable estimated by the generator 21 follows the measured value of the output variable output in response to the input data.

[0099] Figure 6 is a diagram showing a detailed configuration of a generator of an artificial neural network model.

[0100] Reference Figure 6 , the generator 21 may include an encoder 21a and a decoder 21b.

[0101] The encoder 21a and the decoder 21b constitute a network for obtaining the estimated value of the output variable. In other words, the generator 21 can be composed of a network of an encoder 21a-decoder 21b structure trained in an end-to-end manner to obtain the estimated value of the output variable.

[0102] The encoder 21a may be designed to extract high-level features from input data using a transformer block and linear operations. At this time, the transformer block may include an embedding layer, a self-attention layer, and a feed-forward layer.

[0103] First, the embedding layer in the Transformer block can use a trainable embedding matrix to encode spatiotemporal information into the input sequences.

[0104] Next, deep features can be extracted through a self-attention layer, and refinement can be performed using a feed-forward layer.

[0105] At this time, the self-attention layer can utilize a scaled dot-product attention mechanism. The self-attention layer can be a major component in the Transformer-based Deep Neural Network (DNN) architecture, which enables the model to process and understand dependencies in the input sequence.

[0106] The scaled inner product attention first applies layer normalization to the input sequence and processes the result into three intrinsic vectors of query (Q) vector, key (K) vector and value (V) vector through linear operation.

[0107] Next, an attention score AS for each position in the input sequence may be calculated based on the derived vector. The calculation formula of the attention score AS may be as follows:

[0108] [Formula 1]

[0109]

[0110] Among them, σ(·) represents the softmax operation, ∥x input ∥ dim represents the feature dimension of the input, and (·) represents the inner product.

[0111] The attention score quantifies the relative importance of each position in the input sequence with respect to a given query. That is, higher scores are assigned to more appropriate positions.

[0112] The output of the transformer block can be fed into two different linear operations to compute the query, key vector and initial input value for decoder 21b

[0113] The decoder 21b may use the acquired values ​​to compute one or more estimated values ​​in an autoregressive manner similar to a Sequence-to-Sequence Recurrent Neural Networks (SNRNNs).

[0114] Similar to the encoder 21a, the decoder 21b may include a transformer block and a linear operation. In addition, the decoder 21b may also include a cross-attention layer within the transformer block.

[0115] The cross-attention layer can use the query vector and key vector of encoder 21a to perform scaled inner product attention to learn the dynamic correlation between the input signal and the estimated signal.

[0116] The discriminator 22 receives the input data and the measured value of the output variable and outputs a discriminator value. The discriminator value output by the discriminator 22 for the input data and the measured value of the output variable may be defined as a measurement-dependent discriminator value.

[0117] The discriminator 22 may determine a conditional probability. The discriminator 22 determines the probability that the corresponding data is true or false based on the input features. The discriminator 22's discriminator value may be a classification label. For example, the discriminator 22's discriminator value may be 0 or 1.

[0118] On the other hand, the discriminator 22 can also receive the input data and the estimated value of the output variable and output the discrimination value. The discrimination value of the discriminator 22 output for the input data and the estimated value of the output variable can be defined as the estimation-related discrimination value. This process can be implemented when the generator 21 and the discriminator 22 are learning.

[0119] As described above, the discriminator 22 outputs a discriminant value for the input data and the measured value of the output variable in the operation for detecting abnormality. On the other hand, the discriminator 22 may output a discriminant value for the input data and the estimated value of the output variable in the operation for learning.

[0120] The discriminator 22 may be formed by a discriminator network used in adversarial training of a generative adversarial network (GAN). In other words, the generator 21 and the discriminator 22 may be trained by adversarial training to improve estimation performance and establish a generative adversarial network (GAN) model.

[0121] More specifically, the discriminator 22 may perform optimization alternately with the generator 21 to solve a Wasserstein min-max problem such as Equation 2.

[0122] [Formula 2]

[0123]

[0124] Among them, x D,Real represents the actual data set consisting of input data and measurement values, x D,Fake represents a virtual data sample consisting of the input data and the estimated values.

[0125] In the artificial neural network model 20, the generator 21 is trained to deceive the D,Real and xD,Fake The generator 21 can thereby generate an estimation value for following the electronic mechanical brake system in a normal state.

[0126] In this regard, the loss function for generating adversarial network training can be defined as the following formula 3.

[0127] [Formula 3]

[0128]

[0129] Where N is the batch size, L G is the loss function of the generator, L D is the loss function of the discriminator.

[0130] The first term of the loss of generator 21 corresponds to the mean absolute error loss L for supervised training MAE The remaining items of the loss of the generator 21 together with the loss of the discriminator 22 constitute the generative adversarial network loss function L GAN .

[0131] Furthermore, the processor 120 detects whether an abnormality occurs in the brake motor using a difference between an estimated value of the output variable and a measured value of the output variable. As described above, the output variable may be a brake clamping force generated by the friction member displaced according to the operation of the brake motor. In other words, the processor 120 may detect whether an abnormality occurs in the brake motor by comparing the estimated value of the brake clamping force with the measured value.

[0132] The processor 120 can input the error data related to the difference between the estimated value of the output variable and the measured value of the output variable to the abnormality detection module 30 by executing the one or more instructions, and thereby determine whether the brake motor is abnormal. For example, the abnormality detection model 30 can use a one-class support vector machine (OCSVM) algorithm.

[0133] There may be a plurality of data sets including the input data, the measured values ​​of the output variables, and the estimated values ​​of the output variables. The error data may include the mean and standard deviation of the errors between the measured values ​​of the output variables obtained from each of the plurality of data sets and the estimated values ​​of the output variables, the maximum absolute error between the measured values ​​of the output variables obtained from each of the plurality of data sets and the estimated values ​​of the output variables, and the discriminator values ​​for the measured values ​​of the input data and the output variables included in the plurality of data sets.

[0134] A plurality of data sets including the input data, the estimated values ​​of the output variables, and the measured values ​​of the output variables may be considered as a batch. For example, 100 to 150 data sets (as a specific example, 128 data sets) may be considered as a batch, and the error data of each batch may be obtained.

[0135] The error data obtained for one batch may be input to the abnormality detection module 30. And, the abnormality level of the brake motor (performance degradation of the brake motor) may be detected based on the output (feature) obtained from the abnormality detection module 30 that received the error data.

[0136] Regarding the anomaly detection metric, the F1 score given by the following formula 4 can be considered.

[0137] [Formula 4]

[0138]

[0139] Among them, TP is true positive, FP is false positive, FN is false negative, and positive indicates that the performance of the brake motor is reduced.

[0140] On the other hand, as described above, the discriminator 22 can calculate not only the discriminant value associated with the measured value of the input data and the output variable included in the data set, but also the discriminant value associated with the estimated value of the input data and the output variable included in the data set. The discriminant value of the discriminator 22 for the estimated value of the data set can be provided as feedback to the generator 21 of the artificial neural network model 20, thereby being used in training.

[0141] So far, the configuration of the brake motor abnormality detection device 100 according to one embodiment of the present invention has been described in detail. Next, the operation of the brake motor abnormality detection device 100 will be described in detail.

[0142] Figure 7 1 is a diagram showing the operation of the brake motor abnormality detection device according to one embodiment of the present invention.

[0143] Reference Figure 7 , the brake motor abnormality detection device 100 according to an embodiment of the present invention can perform the following operations.

[0144] First, the memory 110 stores input data and the measured value Fm of the output variable. At this time, the output variable may be the brake clamping force generated by the friction member of the electromechanical brake system. That is, the measured value of the output variable may include the measured value of the brake clamping force.

[0145] As mentioned above, input data The input data may include any one or more of the vehicle speed, the vehicle lateral acceleration, the brake pedal input displacement, or the vehicle wheel speed. A plurality of the measured data of the measurement value Fm can be regarded as a batch. That is, in one embodiment of the present invention, the data batch can be used as a unit for data processing and calculation.

[0146] Next, the processor 120 converts the input data into The processor 120 can input the input data into the artificial neural network model 20, and obtain the estimated value Fe of the output variable output by the artificial neural network model 20. More specifically, the processor 120 can The estimated value of the brake clamping force output by the generator 211 is input to the generator 211 of the artificial neural network model 20, and the estimated value of the brake clamping force output by the generator 211 is obtained.

[0147] Furthermore, the processor 120 converts the input data into and the measured value Fm of the output variable are input to the artificial neural network model 20, and the discrimination value DS is obtained. More specifically, the processor 120 can input the data The measured values ​​of the brake clamping force are input to the discriminator 22, and a discriminator value DS is obtained.

[0148] Next, the processor 120 outputs the error data D Error The error data D can be output according to each data batch Error .

[0149] More specifically, there may be a plurality of data sets, the data values ​​including the input data, the estimated value Fe of the output variable, and the measured value Fm of the output variable.

[0150] At this time, the error data D Error The discriminator 22 may include a discriminator value DS for a value of an average value μ of the error between the estimated value Fe and the measured value Fm obtained from each of the plurality of data sets. E and standard deviation σ E The maximum absolute error Max between the estimated value Fe and the measured value Fm obtained from the plurality of said data sets E ; and for input data and the measured value Fm.

[0151] Finally, the processor 120 converts the error data D into Error The anomaly detection model 30 is inputted, and the output of the anomaly detection model 30 is obtained. As described above, the anomaly detection model 30 may include a one-class support vector machine (OCSVM) algorithm.

[0152] Based on the received error data D Error Based on the output (features) obtained by the abnormality detection module 30, the processor 120 can detect the abnormality level of the brake motor (the performance of the brake motor is reduced).

[0153] The above is a detailed description of the brake motor abnormality detection device 100 according to an embodiment of the present invention. Next, a brake motor abnormality detection method will be described in detail.

[0154] Figure 8 is a sequence diagram of a brake motor abnormality detection method according to an embodiment of the present invention.

[0155] According to a brake motor abnormality detection method (step S100) according to an embodiment of the present invention, abnormality of a brake motor that generates a driving force for displacing a friction member is detected to generate a braking force caused by friction when a friction member arranged on a wheel side of a vehicle is displaced.

[0156] Reference Figure 8 , the brake motor abnormality detection method (step S100) according to an embodiment of the present invention can be performed as follows.

[0157] First, the processor 120 inputs the input data into the artificial neural network model and obtains the estimated value of the output variable by executing one or more instructions. The artificial neural network model receives the input data and outputs the estimated value of the output variable related to the output value of the brake motor (step S110).

[0158] The input data may include any one or more of the speed of the vehicle, the lateral acceleration of the vehicle, the input displacement of the brake pedal, or the wheel speed of the vehicle. In one embodiment of the present invention, the input data may include the speed of the vehicle, the lateral acceleration of the vehicle, the input displacement of the brake pedal, and the wheel speed of the vehicle.

[0159] On the other hand, the input data may be obtained from a controller area network (CAN) 300 of the vehicle.

[0160] The output variable may be a brake clamping force generated by the displacement of the friction member when the brake motor is driven. In other words, the estimated value of the output variable may be an estimated value of the brake clamping force. At this time, the estimated value of the brake clamping force may be obtained for each wheel of the vehicle.

[0161] The estimated value of the output variable is obtained for comparison with the measured value of the output variable. In this case, the measured value of the output variable may be a measured value of the brake clamping force generated by the displacement of the friction member when the brake motor is driven. The measured value of the brake clamping force may be obtained for each wheel of the vehicle.

[0162] In one embodiment of the present invention, the artificial neural network model 20 may include a generative adversarial network (GAN). In other words, the artificial neural network model 20 may be a deep learning-based neural twin model for the electronic mechanical braking system of the vehicle.

[0163] The artificial neural network model 20 may include a generator 21 and a discriminator 22. The generator 21 receives the input data and generates an estimated value of the output variable. The generator 21 may be composed of a multivariate transformer. Furthermore, the discriminator 22 may receive the input data and the measured value of the output variable and output a measurement-related discriminant value.

[0164] In the step of acquiring the estimated value of the output variable (step S110 ), the processor 120 may input the input data into the generator 21 , and acquire the estimated value of the output variable generated by the generator 21 .

[0165] On the other hand, the artificial neural network model 20 is constructed by learning the generator 21 and the discriminator 22, and the input data and the measured values ​​used in the learning can be obtained when the vehicle and the electronic mechanical brake system are in a normal state. Thus, the estimated value of the output variable can follow the measured value of the output variable obtained when the electronic mechanical brake system is in a normal state.

[0166] Next, the processor 120 detects whether an abnormality occurs in the brake motor by using the difference between the estimated value of the output variable and the measured value of the output variable (step S120 ).

[0167] The processor 120 inputs the error data related to the difference between the estimated value and the measured value into the abnormality detection module 30 by executing one or more instructions, and determines whether the brake motor has an abnormality. For example, the abnormality detection model 30 can use a one-class support vector machine (OCSVM) algorithm.

[0168] Fig. 9 It is a detailed sequence diagram of the steps of detecting whether an abnormality occurs in a brake motor according to a brake motor abnormality detection method according to an embodiment of the present invention.

[0169] Reference Fig. 9 The step of detecting whether an abnormality occurs in the brake motor (step S120) can be performed as follows.

[0170] First, the processor 120 inputs the input data and the measured value of the output variable to the discriminator 22, and acquires a measurement-related discriminant value generated by the discriminator 22 (step S121).

[0171] The discrimination value output by the discriminator 22 for the input data and the measured value of the output variable may be defined as a measurement-related discrimination value.

[0172] Next, the processor 120 inputs the measurement-related identification value and the error data including the numerical value related to the difference between the estimated value of the output variable and the measured value of the output variable to the abnormality detection module 30, and obtains the output of the abnormality detection module 30 (step S122).

[0173] There may be a plurality of data sets, the data sets including the input data, the measured values ​​of the output variables and the estimated values ​​of the output variables. The error data may include: the mean value and standard deviation of the error between the measured values ​​of the output variables obtained from each of the plurality of data sets and the estimated values ​​of the output variables; the maximum absolute error between the measured values ​​of the output variables obtained from each of the plurality of data sets and the estimated values ​​of the output variables; and the discriminator's discriminator for the input data and the measured values ​​of the output variables included in the plurality of data sets.

[0174] In one embodiment of the present invention, the error data may include: the average value and standard deviation of the error between the estimated value and the measured value of the brake clamping force obtained from each of the multiple data sets; the maximum absolute error between the estimated value and the measured value of the brake clamping force obtained from each of the multiple data sets; and the identification value of the identifier 22 for the input data and the measured value of the brake clamping force included in the multiple data sets.

[0175] A plurality of data sets including the input data, the estimated values ​​of the output variables, and the measured values ​​of the output variables may be considered as a batch. For example, 100 to 150 data sets (as a specific example, 128 data sets) may be considered as a batch, and the error data of each batch may be obtained.

[0176] The error data obtained for one batch may be input to the abnormality detection module 30. And, the abnormality level of the brake motor (deterioration in performance of the brake motor) may be detected based on the output (feature) obtained from the abnormality detection module 30 that received the error data.

[0177] On the other hand, the present invention also provides a non-transitory computer-readable storage medium storing a program for executing the brake motor abnormality detection method. Specifically, the present invention can provide a non-transitory computer-readable storage medium storing a program including at least one instruction for executing the brake motor abnormality detection method.

[0178] At this time, the instruction may include a machine code generated by a compiler, and the instruction may also include a high-level language code executable by a computer.

[0179] The storage medium may include a hardware device configured to store and execute program instructions such as magnetic media (Magnetic Media) such as hard disks, floppy disks and magnetic tapes, optical recording media (Optical Media) such as compact disk read only memory (CD-ROM), digital video disk (Digital Video Disk, DVD), magneto-optical media (Magneto-Optical Media) such as floptical disks (Floptical Disk), read-only memory (ROM), random access memory (RAM), flash memory, etc.

[0180] As for an anomaly detection metric showing the effect of the present invention, the F1 score as described above may be considered.

[0181] As a result of the simulation, according to the present invention, it is possible to predict the performance of the F1 score of 0.85 or more until the maximum output of the brake motor is reduced to 10%. In other words, according to the present invention, before the brake motor completely fails, the deterioration level of the brake motor that generates the driving force for displacing the friction member to generate the braking force by friction when the friction member arranged on the wheel side of the vehicle is displaced can be accurately predicted.

[0182] According to the present invention, the reduction of the output torque of the brake motor can be detected sensitively. As a result, preventive measures can be taken before the brake motor fails, thereby effectively preventing the failure of the brake motor.

[0183] As described above, the present invention provides an estimate of the future behavior and remaining useful life of the system and predictive diagnostics suitable for predictive maintenance applications. Thus, preventive measures and maintenance can be effectively prompted before the brake motor fails.

[0184] Although the embodiments of the present invention have been described, the technical idea of ​​the present invention is not limited to the embodiments described in the specification, and those skilled in the art who understand the spirit of the present invention will be able to easily propose other embodiments within the scope of the same spirit by adding, changing, deleting or adding components. However, this is also included in the spirit of the present invention.

Claims

1. A brake motor abnormality detection device, which detects abnormality of a brake motor, wherein the brake motor generates a driving force for displacing a friction member, so as to generate a braking force by friction when the friction member arranged on the wheel side of a vehicle is displaced, characterized in that include: memory for storing one or more instructions, and A processor, executing the one or more instructions; The processor inputs the input data into the artificial neural network model and obtains the estimated value of the output variable by executing the one or more instructions, and uses the difference between the estimated value of the output variable and the measured value of the output variable to detect whether the brake motor has an abnormality. The artificial neural network model receives the input data and outputs the estimated value of the output variable related to the output value of the brake motor.

2. The brake motor abnormality detection device according to claim 1, wherein: The input data includes one or more of the speed of the vehicle, the lateral acceleration of the vehicle, the input displacement of the brake pedal, or the wheel speed of the vehicle.

3. The brake motor abnormality detection device according to claim 1, wherein: The output variable includes a brake clamping force generated according to a displacement of the friction member.

4. The brake motor abnormality detection device according to claim 1, wherein: The input data is obtained via a controller area network of the vehicle.

5. The brake motor abnormality detection device according to claim 1, wherein: The artificial neural network model is composed of a generative adversarial network. The generative adversarial network comprises: a generator that receives the input data and generates an estimate of the output variable; and A discriminator receives the input data and the measured value of the output variable and outputs a measurement-related discriminant value.

6. The brake motor abnormality detection device according to claim 5, wherein: The discriminator also receives the input data and an estimated value of the output variable and outputs an estimated associated discriminant value.

7. The brake motor abnormality detection device according to claim 5, wherein: The processor inputs error data to the abnormality detection module by executing the one or more instructions and determines whether the brake motor has an abnormality, wherein the error data is related to a difference between an estimated value of the output variable and a measured value of the output variable.

8. The brake motor abnormality detection device according to claim 7, wherein: There are a plurality of data sets, the data sets comprising the input data, measured values ​​of the output variables, and estimated values ​​of the output variables, The error data includes: a mean and a standard deviation of errors between measured values ​​of the output variable and estimated values ​​of the output variable obtained from each of a plurality of the data sets; a maximum absolute error between a measured value of the output variable and an estimated value of the output variable obtained from each of a plurality of the data sets; and The discriminator is for discriminant values ​​of the input data and the measured values ​​of the output variables included in the plurality of the data sets.

9. A brake motor abnormality detection method for detecting abnormality of a brake motor, wherein the brake motor generates a driving force for displacing a friction member, so as to generate a braking force by friction when the friction member arranged on the wheel side of a vehicle is displaced, characterized in that: include: The processor inputs input data to an artificial neural network model and obtains an estimated value of the output variable by executing one or more instructions, wherein the artificial neural network model receives the input data and outputs an estimated value of the output variable related to the output value of the brake motor; as well as The processor detects whether an abnormality occurs in the brake motor by using a difference between the estimated value of the output variable and the measured value of the output variable.

10. The brake motor abnormality detection method according to claim 9, wherein: The input data includes one or more of the speed of the vehicle, the lateral acceleration of the vehicle, the input displacement of the brake pedal, or the wheel speed of the vehicle.

11. The brake motor abnormality detection method according to claim 9, wherein: The output variable includes a brake clamping force generated according to a displacement of the friction member.

12. The brake motor abnormality detection method according to claim 9, wherein: The artificial neural network model is composed of a generative adversarial network. The generative adversarial network comprises: a generator that receives the input data and generates an estimate of the output variable; and A discriminator receives the input data and the measured value of the output variable and outputs a measurement-related discriminant value.

13. The brake motor abnormality detection method according to claim 12, wherein: The step of detecting whether the brake motor is abnormal comprises: The processor inputs the input data and the measured value of the output variable to the discriminator and obtains the measurement-dependent discriminant value generated by the discriminator; and The processor inputs the measurement-related identification value and error data including a numerical value related to the difference between the estimated value of the output variable and the measured value of the output variable into an anomaly detection module and obtains an output of the anomaly detection module.

14. The brake motor abnormality detection method according to claim 13, wherein: There are a plurality of data sets, the data sets comprising the input data, measured values ​​of the output variables, and estimated values ​​of the output variables, The error data includes: a mean and a standard deviation of errors between measured values ​​of the output variable and estimated values ​​of the output variable obtained from each of a plurality of the data sets; a maximum absolute error between a measured value of the output variable and an estimated value of the output variable obtained from each of a plurality of the data sets; and The discriminator is for discriminant values ​​of the input data and the measured values ​​of the output variables included in the plurality of the data sets.

15. A computer-readable storage medium storing a program, wherein: The program includes at least one instruction for executing the brake motor abnormality detection method according to claim 9.

Images