DEVICE AND METHOD FOR DETECTING ANOMALIES OF A REAR-WHEEL STEERING MOTOR, AND COMPUTER-READABLE STORAGE MEDIUM FOR STORED A PROGRAM FOR PERFORMING THE METHOD

Abstract

A device and a method for detecting an anomaly in a rear-wheel steering motor and a non-transient, computer-readable storage medium that stores a program for carrying out the method are disclosed. The device comprises a memory configured to store one or more instructions and a processor configured to execute one or more instructions.The processor executes one or more instructions to input data relating to the vehicle's rear-wheel steering into an artificial neural network model, to obtain estimated data relating to the vehicle's rear-wheel steering as output data from the artificial neural network model, to obtain measured data relating to the vehicle's rear-wheel steering from a sensor, to compare the estimated data and the measured data, and to detect the rear-wheel steering motor anomaly based on the result of comparing the estimated data and the measured data.

Description

CROSS-REFERENCE TO A RELATED APPLICATION

[0001] This application claims priority to and the benefit of Korean Patent Application No. 10-2023-0106182, filed on August 14, 2023, and Korean Patent Application No. 10-2024-0089573, filed on July 8, 2024, the disclosures of which are incorporated herein by reference in their entirety. BACKGROUND 1. Field of technology

[0002] The present disclosure relates to an apparatus and a method for detecting an abnormality of a rear wheel steering motor and a non-transitory computer-readable storage medium storing a program for carrying out the method, and more particularly, to a method for detecting an abnormality of a rear wheel steering motor capable of detecting the abnormality of the rear wheel steering motor that generates a driving force for driving a rack that performs rear wheel steering of a vehicle and a non-transitory computer-readable storage medium storing a program for carrying out the method. 2. Discussion of the state of the art

[0003] A vehicle's rear-wheel steering system actively controls the steering angle of the rear wheels, which corresponds to the steering angle of the front wheels depending on the vehicle's driving situation. The rear-wheel steering system makes it possible to reduce a vehicle's turning circle and improve driving stability and ride comfort.

[0004] A rear-wheel steering system includes a rack that adjusts the angle of the vehicle's rear wheels and a rear-wheel steering actuator that drives the rack. Generally, a rear-wheel steering actuator includes a motor. Therefore, the rear-wheel steering actuator may be a rear-wheel steering motor.

[0005] The output torque of a rear-wheel steering motor can decrease due to demagnetization, insulation corrosion, etc., caused by its deterioration. If the output torque of the rear-wheel steering motor is reduced, the driver receives feedback of an unpleasant driving feeling that does not correspond to their steering intention. This unpleasant driving feeling feedback can lead to accidents due to steering errors.

[0006] Generally, the output torque of a rear-wheel steering motor gradually decreases. Therefore, to improve the safety of a rear-wheel steering system, it is desirable to predict motor abnormalities. However, conventional approaches to detecting rear-wheel steering motor abnormalities are limited to post-failure diagnosis. SUMMARY OF THE INVENTION

[0007] The present disclosure relates to an apparatus and a method for detecting an abnormality of a rear wheel steering motor and a non-transitory computer-readable storage medium storing a program for carrying out the method, and more particularly, to a method for detecting an abnormality of a rear wheel steering motor capable of detecting the abnormality of the rear wheel steering motor that generates a driving force for driving a rack that performs rear wheel steering of a vehicle and a non-transitory computer-readable storage medium storing a program for carrying out the method.

[0008] The present disclosure is directed to providing an apparatus and method for detecting an abnormality of a rear wheel steering motor capable of efficiently detecting a decrease in performance of the rear wheel steering motor in advance by using an existing sensor disposed on a vehicle in the vehicle without an additional sensor, and a non-transferable computer-readable storage medium storing a program for performing the method.

[0009] The objects of the present disclosure are not limited to the objects described above, and other objects not mentioned will become apparent to one skilled in the art to which the present disclosure belongs from the following description.

[0010] According to one aspect of the present disclosure, an apparatus for detecting an abnormality of a rear-wheel steering motor is provided, comprising a memory configured to store one or more instructions and a processor configured to execute one or more instructions. The processor executes one or more instructions to input input data related to the rear-wheel steering of the vehicle into an artificial neural network model, obtain estimated data related to the rear-wheel steering of the vehicle as output data from the artificial neural network model, obtain measurement data related to the rear-wheel steering of the vehicle from a sensor, compare the estimated data and the measured data, and detect the abnormality of the rear-wheel steering motor based on a result of the comparison of the estimated data and the measured data.

[0011] According to another aspect of the present disclosure, there is provided a method for detecting an abnormality of a rear-wheel steering motor of a vehicle, comprising: inputting, by a processor, input data related to the rear-wheel steering of the vehicle into an artificial neural network model; obtaining, by the processor, estimated data related to the rear-wheel steering of the vehicle from the artificial neural network model as output data; acquiring, by the processor, measured data relating to the rear-wheel steering of the vehicle from a sensor; comparing the estimated data and the measured data by the processor; and detecting, by the processor, abnormalities of the rear-wheel steering motor based on a result of the comparison of the estimated data and the measured data.

[0012] According to another aspect of the present disclosure, a non-transferable, computer-readable storage medium is provided in which a program having at least one instruction for performing the method for detecting an abnormality of a rear wheel steering motor is stored. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The above and other objects, features and advantages of the present disclosure will become more apparent to those skilled in the art by describing exemplary embodiments thereof with reference to the accompanying drawings. Fig. 1 is a diagram schematically showing a configuration of a rear wheel steering motor of a vehicle; Fig. 2 is a diagram showing a detailed configuration of a control device for the rear wheel steering motor of the rear wheel steering system; Fig. 3 is a diagram showing the configuration of an apparatus for detecting an abnormality of a rear wheel steering motor according to an embodiment of the present disclosure; Fig. 4 is a diagram illustrating models used to obtain an estimated value or detect an abnormality in the device for detecting the abnormality of the rear wheel steering motor according to an embodiment of the present disclosure; Fig. 5 is a diagram showing a detailed configuration of an artificial neural network model; Fig. 6 is a diagram showing a detailed configuration of a generator of the artificial neural network model; Fig. 7 is a diagram showing the operation of the rear wheel steering motor abnormality detecting apparatus according to an embodiment of the present disclosure; Fig. 8 is a flowchart of a method for detecting an abnormality of a solenoid valve of a rear wheel steering motor according to an embodiment of the present disclosure; and Fig. 9 is a detailed flowchart of a process for detecting the abnormality of the rear wheel steering motor in the method for detecting the abnormality of the rear wheel steering motor according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0014] In the following, embodiments of the present disclosure will be described in detail so that a person skilled in the art to which the present disclosure belongs can easily practice the embodiments. The present disclosure may be implemented in many different forms and is not limited to the embodiments described herein. To clearly describe the present disclosure, parts that are not related to the description are omitted from the accompanying drawings, and the same or similar components are denoted by the same reference numerals throughout the description.

[0015] The words and terms used in the specification and claims are not to be understood merely in their ordinary or dictionary meaning, but should be interpreted in their meaning and concept consistent with the technical spirit of the present disclosure, in accordance with the principle that inventors may define terms and concepts to best describe their disclosure.

[0016] It should be noted that in the description, terms such as "comprise" or "have" are intended to specify the presence of features, a respective number, steps, operations, components, parts or combinations thereof described in the description, but are not intended to exclude the possibility of the presence or addition of one or more other features, a respective different number, one or more other steps, operations or components, parts or combinations thereof.

[0017] Fig. 1 is a diagram schematically showing a configuration of a rear wheel steering motor of a vehicle;

[0018] A rear-wheel steering system of a vehicle 200 actively controls a steering angle of the rear wheels that corresponds to a steering angle of the front wheels depending on the driving situation of the vehicle. Depending on the driving situation, the rear-wheel steering system 200 can control the steering angle of the rear wheels RW in the same phase as the steering angle of the front wheels of the vehicle or in the opposite phase to the steering angle of the front wheels of the vehicle.

[0019] In particular, at medium or low speeds, the rear wheels (RW) can be steered in the opposite phase to the front wheels, thereby reducing the vehicle's turning radius. When the vehicle is traveling at high speeds, the rear wheels (RW) can be steered in the same phase as the front wheels, improving cornering stability and thus turning stability.

[0020] With reference to Fig. 1, the rear-wheel steering system 200 includes a sensor unit 210 that detects information about the driving state of the vehicle. The sensor unit 210 may include a vehicle speed sensor 211 that detects the speed of the vehicle, a gearshift position sensor 212 that detects the gearshift position of the vehicle, and a steering angle sensor 213 that detects the steering angle and steering angular velocity of a steering wheel of the vehicle.

[0021] The information detected by the sensor unit 210 can be transmitted to an electronic control unit 250. The sensor unit 210 can include a vehicle speed sensor 211 that detects the speed of the vehicle, a gearshift position sensor 212 that detects the gearshift position of the vehicle, and a steering angle sensor 212 that detects the steering angle and steering angular velocity of a steering wheel of the vehicle.

[0022] The electronic control unit 250 generates input data for the rear-wheel steering based on the acquired information. The input data generated by the electronic control unit 250 can be transmitted to a rear-wheel steering motor control unit 260, which controls a rear-wheel steering motor 270 that generates a drive force for the rear-wheel steering.

[0023] The rear-wheel steering motor control unit 260 can control the rear-wheel steering motor 270 based on the rear-wheel steering information. The rear-wheel steering motor 270 moves a rack 280 connected to the rear wheels RW of the vehicle. When the rack 280 is moved according to the movement of the rear-wheel steering motor 270, the angle of the rear wheels RW of the vehicle can be changed, and rear-wheel steering can be achieved.

[0024] Fig. 2 is a diagram showing a detailed configuration of a rear wheel steering motor control unit of the rear wheel steering system;

[0025] With reference to Fig. 2, the rear wheel steering motor control unit 260 may include a command generator 261, a rack position controller 262, a rear wheel steering motor torque controller 263, and a rear wheel steering motor current controller 264.

[0026] The command generator 261 generates a command for a rack position Pd, which is a rack position where the rack 280 should be located according to the input data. In this case, the input data may include at least one of a vehicle wheel speed, a vehicle shift lever position, a vehicle steering angle, and a vehicle steering angular velocity.

[0027] The rack position controller 262 receives a difference between the rack position command Pd and a measured rack position P m and generates a command for a torque T d of the rear wheel steering motor, which is a torque that should be generated by the rear wheel steering motor 270.

[0028] The difference between the command for the rack position Pd and the measured rack position P m may be a difference between a command and a measured value for the rack position and may be defined as the first residual value. In other words, the rack position controller 262 may receive the first residual value and command the torque T d of the steering motor for the rear wheels.

[0029] The rear wheel steering motor torque controller 263 receives a difference between the torque T command dof the rear wheel steering motor and a measured torque T m of the rear wheel steering motor measured at the rear wheel steering motor 270 and generates a command for a current Id, which is a current that should be supplied to the rear wheel steering motor 270.

[0030] The difference between the torque command T d of the rear wheel steering motor and a measured torque T m of the rear-wheel steering motor may be a difference between a command and a measured value for the rack position and may be defined as a second residual value. In other words, the torque controller 263 of the rear-wheel steering motor may receive the second residual value and command the current I d generate.

[0031] The rear wheel steering motor current controller 264 receives an input current that provides the feedback of the current I command. d and a measured current I mand controls a current supplied to the rear wheel steering motor 270. Accordingly, a voltage V d which is input to the rear wheel steering motor 270.

[0032] In the meantime, the measured current I m of the motor from an angle θ m (position) of the rear wheel steering motor 270 can be calculated. In addition, the measured torque T m of the rear wheel steering motor from the measured current I m of the rear wheel steering motor 270 can be estimated.

[0033] Fig. 3 is a diagram showing the configuration of an apparatus for detecting an abnormality of a rear wheel steering motor according to an embodiment of the present disclosure. Fig. 4 is a diagram illustrating models used to obtain an estimated value or detect an abnormality in the device for detecting the abnormality of the rear wheel steering motor according to an embodiment of the present disclosure.

[0034] A rear-wheel steering motor abnormality detection device 100 according to the embodiment of the present disclosure detects an abnormality of a rear-wheel steering motor 270 that generates a driving force for driving a rack 280 that performs rear-wheel steering of a vehicle. Specifically, the rear-wheel steering motor abnormality detection device 100 according to the present disclosure can predict a functional deterioration of the rear-wheel steering motor 270 before a failure of the rear-wheel steering motor 270 occurs, in which the rear-wheel steering motor 270 becomes difficult to operate.

[0035] The rear-wheel steering motor abnormality detection device 100 according to the present disclosure can predict functional deterioration of the rear-wheel steering motor 270 before failure of the rear-wheel steering motor 270 occurs by using an artificial intelligence-based digital twin algorithm. The digital twin algorithm can virtually construct the rear-wheel steering system of the vehicle.

[0036] As in Fig. 3, the rear wheel steering motor abnormality detection apparatus 100 according to the present disclosure may include a memory 110 and a processor 120.

[0037] Memory 110 stores one or more instructions. The one or more instructions can be executed by processor 120.

[0038] Memory 110 may include a hardware device configured to store and execute instructions. Memory 110 may include, for example, a storage medium such as read-only memory (ROM), random access memory (RAM), flash memory, etc. Furthermore, memory 110 may include a magnetic medium such as a floppy disk or magnetic tape, an optical medium such as a compact disc read-only memory (CD-ROM) or a digital video disc (DVD), a magneto-optical medium such as a floppy disk, etc.

[0039] Processor 120 executes the one or more instructions. For example, processor 120 may be a hardware unit that performs calculations and control in a computer. Processor 120 may include at least one arithmetic logic unit (ALU) and one register.

[0040] The processor 120 may execute one or more instructions to input data related to the steering of the vehicle to an artificial neural network model 20 and obtain estimated data related to the rear wheel steering output from the artificial neural network model 20.

[0041] The input data may include at least one of a vehicle speed, a vehicle gearshift position, a vehicle steering angle, and a vehicle steering angular velocity. For example, the input data may include the vehicle speed, a vehicle gearshift position, a vehicle steering angle, and a vehicle steering angular velocity.

[0042] The input data can be retrieved via a controller area network (CAN) 300 of the vehicle. For example, the input data can be transmitted to the memory 110 via the CAN 300.

[0043] In this way, the input data can be retrieved via a controller area network (CAN) 300 of the vehicle. Accordingly, according to the present disclosure, there is no need to use an additional sensor related to detecting the anomaly of the rear wheel steering motor 270.

[0044] In this context, memory 110 may be connected directly or indirectly to the vehicle's CAN 300. Memory 110 may receive input data from CAN 300. Accordingly, processor 120 may receive the input data from memory 110.

[0045] The estimated data may include a first estimate of a first residual value, which is a difference between a command and a measured value for a position of the steering rack determined to correspond to the input data. The estimated data may further include a second estimate of a second residual value, which is a difference between a command and a measured value for a motor torque to be produced by the rear wheel steering motor 270, which is determined to correspond to the input data.

[0046] The artificial neural network model 20 receives the input data and outputs the estimated value. Specifically, the artificial neural network model 20 receives the input data and outputs the first estimated value and the second estimated value.

[0047] The estimated data is compared with the actual measurement data related to the rear-wheel steering. In this case, the actual measurement data may include a first actual measurement value, which is an actual measurement value of the first residual value, and a second actual measurement value, which is an actual measurement value of the second residual value.

[0048] In one embodiment of the present disclosure, the artificial neural network model 20 may comprise a generative adversarial network (GAN).

[0049] In one embodiment of the present disclosure, the artificial neural network model 20 may be a deep learning-based neural twin model for the rear-wheel steering system of the vehicle. In other words, the artificial neural network model 20 may serve as a virtual twin model of the rear-wheel steering system of the vehicle.

[0050] Fig. Figure 5 is a diagram showing a detailed configuration of the artificial neural network model.

[0051] Referring to Fig. 5, the artificial neural network model 20 may comprise a generator 21 and a discriminator 22.

[0052] The artificial neural network model 20 can be constructed by alternately learning the generator 21 and the discriminator 22, and the data used during the learning process can be obtained when the vehicle and the rear-wheel steering system are in a normal state. Accordingly, the first estimated value and the second estimated value included in the estimated data can follow the first actual measured value and the second actual measured value obtained when the vehicle and the rear-wheel steering system are in a normal state.

[0053] The generator 21 receives the input data and generates the estimated data. The generator 21 may include a neural network. The generator 21 may include a multivariate transformer. That is, the artificial neural network model 20 may be a GAN based on a multivariate transformer.

[0054] In one embodiment of the present disclosure, generator 21 may receive input data related to the rear-wheel steering of the vehicle. As described above, the input data may include, for example, the vehicle speed, the steering angle of the steering wheel, and a driving force of rack 280, which moves the rear wheels RW of the vehicle by receiving driving force from rear-wheel steering motor 270.

[0055] The generator 21 receives the input data and outputs the estimated data. Specifically, the generator 21 can output the first estimated value for the first residual and the second estimated value for the second residual.

[0056] The estimated data output from the generator 21 follows the first actual measurement value of the first residual value and the second actual measurement value of the second residual value, which are output to correspond to the input data when the vehicle and the rear wheel steering system are in a normal state.

[0057] Fig. Figure 6 is a diagram showing a detailed configuration of the generator of the artificial neural network model.

[0058] As in Fig. 6, the generator 21 may comprise an encoder 21a and a decoder 21b.

[0059] Encoder 21a and decoder 21b form a network for estimating the damping force of the vehicle's rear-wheel steering system. In other words, generator 21 can be configured as a structured network of encoder 21a and decoder 21b, which is continuously trained to estimate the estimation data.

[0060] The encoder 21a can be designed to extract high-quality features from the input data using a transformer block and a linear operation. In this case, the transformer block can include an embedding layer, a self-attention layer, and a feedforward layer.

[0061] First, the embedding layer in the transformer block can encode spatio-temporal information in input sequences using a trainable embedding matrix.

[0062] Next, deep features can be extracted by the self-attention layer, and refinement can be done using the feedforward layer.

[0063] In this case, the self-attention layer can use a scaled dot-product attention mechanism. The self-attention layer can be a key component in transformer-based deep neural network (DNN) architectures, enabling the model to process and understand dependencies within the input sequence.

[0064] Scaled Dot-Product Attention can first apply layer normalization to the input sequence and process the layer normalization results through linear operations into three unique vectors: a query vector (Q), a key vector (K), and a value vector (V).

[0065] An attention value AS can then be calculated for each position in the input sequence based on the derived vectors. A calculation formula for the attention value AS can be given as follows: Formula 1. AS=σ(Q⋅K||xinput||dim)⋅V (σ() denotes a softmax operation, ||x input || dim denotes a feature dimension of an input, and denotes a dot product)

[0066] An attention score quantifies the relative importance of each position in the input sequence relevant to a particular query. This means that higher scores are assigned to more appropriate positions.

[0067] An output of the transformer block can be fed to two different linear operations to calculate a query, a key vector and an initial input value ŷ1 of the decoder 21b.

[0068] The decoder 21b can estimate the estimated value from the obtained values ​​in an autoregressive manner, similar to recurrent neural networks from sequence to sequence.

[0069] Like the encoder 21a, the decoder 21b may also include a transformer block and linear operations. Furthermore, the decoder 21b may include a cross-attention layer within the transformer block.

[0070] The cross-attention layer may perform scaled dot-product attention using the query vector and the key vector of the encoder 21a to learn a dynamic correlation between input signals and estimated signals.

[0071] The discriminator 22 receives the input data and the actual measurement data and outputs a discrimination value. The discrimination value output by the discriminator 22 for the input data and the actual measurement data can be defined as a discrimination value with respect to the actual measurement.

[0072] Discriminator 22 is a classifier designed to determine conditional probability. Discriminator 22 determines the probability that an example is genuine or fake, given a set of input features. The discrimination values ​​of discriminator 22 are classification labels. The discrimination value of discriminator 22 is, for example, 0 or 1.

[0073] Meanwhile, the discriminator 22 may additionally receive estimation data containing the input data and the estimation value, and additionally output a discrimination value for the estimation data. The discrimination value output by the discriminator 22 for the input data and the estimation data may be defined as an estimation-related discrimination value. Such a process can be implemented when the generator 21 and the discriminator 22 perform a learning process.

[0074] In this way, the discriminator 22 can output the discrimination value for the input data and the actual measurement data during an anomaly detection operation. Meanwhile, the discriminator 22 can output the discrimination value for the input data and the estimated data during an operational learning process.

[0075] The discriminator 22 may consist of a discriminator network used for adversarial training of a GAN. In other words, the generator 21 and the discriminator 22 may be trained using an adversarial training method to improve estimation performance and create a GAN model.

[0076] More specifically, the discriminator 22 can perform an optimization alternately with the generator 21 to solve a Wasserstein min-max problem such as formula 2. minGmaxDExD,Real[D(xD,Real)]−ExD,Fake[D(xD,Fake)] (x D,Real denotes a real data set consisting of the input data and the actual measurement data related to the rear wheel steering, and x D,Fake refers to a virtual data sample consisting of the input data and the estimated value related to the rear-wheel steering.)

[0077] In the artificial neural network model 20, the generator 21 is trained to deceive the discriminator 22, which uses the spatial-temporal features of x D,Real and x D,Fake Accordingly, the generator 21 can generate the estimated value for the rear wheel steering system in a normal state.

[0078] In this context, a loss function for GAN training can be defined as follows: Formula 3. LG=1N∑|yG−y^G|+0.001×1N∑|−D(xD,Fake)|, LD=1N∑[D(xD,Fake)−D(xD,Real)]+10×1N∑[(||∇xD,FakeD(xD,Fake)||2−1)2] (N denotes the size of a batch, L G denotes the loss function of the generator and L D the loss function of the discriminator)

[0079] The first term of a loss function of the generator 21 corresponds to a loss L MAEa mean absolute error of the supervised training. The remaining term of the loss function of the generator 21, together with a loss of the discriminator 22, forms a loss function L GAN of the GAN.

[0080] Further, the processor 120 compares the estimated data with the actual measurement data and detects the abnormality of the rear wheel steering motor 270. As described above, the estimated data may include the first estimated value for the first residual value and the second estimated value for the second residual value. Furthermore, the actual measurement data may include a first actual measurement value that is the actual measurement value of the first residual value and a second actual measurement value that is an actual measurement value of the second residual value.

[0081] Processor 120 may execute one or more instructions to input error data related to a difference between the estimated data and the actual measurement data into an anomaly detection model 30 and determine whether the rear wheel steering motor is abnormal. Anomaly detection model 30 may, for example, use a one-class support vector machine (OCSVM) algorithm.

[0082] There may be a plurality of data sets containing the input data, the estimated data, and the actual measurement data. The error data may include a mean and standard deviation of the errors between the measurement data and the estimated data of the plurality of data sets, a maximum absolute error between the actual measurement data and the estimated data of the plurality of data sets, and the discrimination value of the discriminator 22 relative to an actual measurement for the input data and the actual measurement data included in the plurality of data sets.

[0083] In one embodiment of the present disclosure, the error data may include a mean value of errors between the first estimated value and the first actual measured value, a standard deviation between the first estimated value and the first actual measured value, a maximum absolute error between the first estimated value and the first actual measured value, a mean value of errors between the second estimated value and the second actual measured value, a standard deviation between the second estimated value and the second actual measured value, a maximum absolute error between the second estimated value and the second actual measured value, and a discrimination value of the discriminator for the input data, the first actual measured value, and the second actual measured value.

[0084] There can be multiple data sets, including input data, estimated data, and actual measurement data, which can be treated as a single batch. For example, 100 to 150 data sets (128 data sets as a specific example) can be treated as a single batch, and the error data can be determined for each batch.

[0085] The failure data obtained for a batch can be input to the anomaly detection model 30. Furthermore, the degree of the rear wheel steering motor failure (rear wheel steering motor performance degradation) can be determined based on an output (characteristic) of the anomaly detection model 30 that receives the failure data.

[0086] Regarding an anomaly detection metric, an F1 score according to Formula 4 can be considered. F1=2×TP2×TP+FP+FN (TP stands for true positive, FP for false positive, and FN for false negative, with a positive indicating deterioration in the performance of the rear wheel steering motor.)

[0087] Meanwhile, as described above, the discriminator 22 can calculate not only the discrimination value for the input data and actual measurement data contained in the data set, but also the discrimination value for the input data and estimated data contained in the data set. The discrimination value of the discriminator 22 for the estimated data of the data set can be provided as feedback to the generator 21 of the artificial neural network model 20 and used for training.

[0088] So far, the configuration of the rear wheel steering motor abnormality detection device 100 according to the embodiment of the present disclosure has been described in detail. The operation of the rear wheel steering motor abnormality detection device 100 will be described in detail below.

[0089] Fig. 7 is a diagram showing the operation of the rear wheel steering motor abnormality detecting apparatus according to an embodiment of the present disclosure.

[0090] As in Fig. 7, the rear wheel steering motor abnormality detection apparatus 100 according to the present disclosure may operate as follows: First, the memory 110 stores the input data Ø ECU and the actual measurement data. In this case, the actual measurement data can provide a first actual measurement value R1 mobtained by the actual measurement of a first residual value, and a second actual measured value R2 m , obtained by actually measuring a second residual value.

[0091] As described above, the input data Ø ECU at least one of a speed of the vehicle, a gear lever position of the vehicle, a steering angle of the vehicle, and a steering angle speed of the vehicle. Furthermore, a plurality of pieces of actual measurement data, including the input data Ø ECU , of the first actual measured value R1 m and the second actual measured value R2 m , be treated as one batch. That is, in one embodiment of the present disclosure, the data processing and calculations may be performed in units of data batches.

[0092] Next, the processor 120 may execute one or more instructions to process the input data Ø ECU into the artificial neural network model 20 and obtain the estimated data output by the artificial neural network model 20. More specifically, the processor 120 may input the input data Ø ECU into the generator 21 of the artificial neural network model 20 and obtain the estimated value, which is a first estimated value R1 e , which is an estimate of the first residual value output by the generator 21, and a second estimate R2 e , which includes estimated data of the second residual value.

[0093] Further, the processor 120 may execute one or more instructions to process the input data Ø ECU , the first actual measured value R1 m , and the two actual measured values ​​R2 minto the artificial neural network model 20 and obtain a discrimination value DS. More specifically, the processor 120 can input the input data Ø ECU , the first actual measured value R1 m , and the two actual measured values ​​R2 m into the artificial neural network model 22 and obtain a discrimination value DS.

[0094] The processor 120 then outputs the error data D Error The error data D Error can be issued for each data batch.

[0095] More specifically, there are a plurality of data sets, including the input value, one or more estimated values, and one or more actual measured values.

[0096] In this case, the error data D Error a mean value µ E(R1) the error between the first estimate R1 e and the first actual measured value R1 m, a standard deviation σ E(R1) between the first estimate R1 e and the first actual measured value R1 m , a maximum absolute error Max E(R1) between the first estimate R1 e and the first actual measured value R1 m , a mean value µ E(R2) the error between the second estimate R2 e and the second actual measured value R2 m , a standard deviation σ E(R2) between the second estimate R2 e and the second actual measured value R2 m , a maximum absolute error Max E(R2) between the second estimate R2 e and the second actual measured value R2 m and a discrimination value DS of the discriminator for the input data Ø ECU , the first actual measured value R1 m and the second actual measured value R2 m .

[0097] Finally, the processor 120 may execute one or more instructions to retrieve the error data D Error to input into the anomaly detection model 30 and obtain an output of the anomaly detection model 30. As described above, the anomaly detection model 30 may include an OCSVM algorithm.

[0098] Based on the output (characteristic) of the anomaly detection model 30, which uses the fault data D Error receives, the processor 120 can detect the degree of abnormality (rear wheel steering motor performance degradation) of the rear wheel steering motor of the rear wheel steering system.

[0099] As described above, the configuration of the rear-wheel steering motor abnormality detection device 100 according to the present disclosure has been described in detail. A method for detecting an abnormality of a rear-wheel steering motor will be described below.

[0100] Fig. 8 is a flowchart of a method for detecting an abnormality of a rear wheel steering motor according to an embodiment of the present disclosure.

[0101] In a method S100 of detecting the abnormality of the rear wheel steering motor according to the embodiment of the present disclosure, the abnormality of a rear wheel steering motor that generates a driving force for driving a rack that performs rear wheel steering of a vehicle is detected.

[0102] Referring to Fig. 8, the process S100 for detecting the abnormality of the rear wheel steering motor according to the embodiment of the present disclosure may be performed as follows.

[0103] First, the processor 120 inputs input data related to the rear wheel steering of the vehicle to an artificial neural network model 20 and obtains estimated data related to the rear wheel steering output from the artificial neural network model 20 (S110).

[0104] The input data may include at least one of a speed of the vehicle, a gearshift position of the vehicle, a steering angle of the vehicle, and a steering angular velocity of the vehicle. In one embodiment of the present disclosure, the input data may include the speed of the vehicle, the gearshift position information of the vehicle, a steering angle of the vehicle, and a steering angular velocity of the vehicle.

[0105] Meanwhile, the input data can be retrieved via a Controller Area Network (CAN) 300 of the vehicle.

[0106] The estimated data may include a first estimate for a first residual value, which is a difference between a command and a measured value for a position of the rack 280 determined to correspond to the input data. The estimated data may further include a second estimate for a second residual value, which is a difference between a command and a measured value for a motor torque to be transmitted to the rear wheel steering motor 270, which is determined to correspond to the input data.

[0107] The estimated data is obtained to be compared with the actual measurement data for the steering. In this case, the actual measurement data may include a first actual measurement value, which is an actual measurement value of the first residual value, and a second actual measurement value, which is an actual measurement value of the second residual value.

[0108] In one embodiment of the present disclosure, the artificial neural network model 20 may comprise a GAN. In other words, the artificial neural network model 20 may be a deep learning-based neural twin model for the rear-wheel steering system of the vehicle.

[0109] The artificial neural network model 20 may include a generator 21 and a discriminator 22. The generator 21 receives the input data and generates the estimated data. The generator 21 may include a multivariate transformer. Furthermore, the discriminator 22 may receive the input data and the actual measurement data and output a discrimination value relative to the actual measurement.

[0110] In the process S110 of obtaining the estimated data, the processor 120 may input the input data to the generator 21 and obtain the estimated value generated by the generator 21.

[0111] Meanwhile, the artificial neural network model 20 is constructed by the generator 21 and the discriminator 22 that performs learning. The input data and the actual measurement data used during learning can be obtained when the vehicle and the rear-wheel steering system are in a normal state. Accordingly, the estimated data can follow the actual measurement data related to the rear-wheel steering obtained when the rear-wheel steering system is in a normal state.

[0112] Finally, the processor 120 compares the estimated data with the actual measured data and detects the anomaly of the rear wheel steering motor (120).

[0113] Processor 120 may execute one or more instructions to input error data related to a difference between the estimated value and the measured value into an anomaly detection model 30 and determine whether the rear wheel steering motor is abnormal. Anomaly detection model 30 may, for example, use an OCSVM algorithm.

[0114] Fig. 9 is a detailed flowchart of a process for detecting the abnormality of the rear wheel steering motor in the method for detecting the abnormality of the rear wheel steering motor according to an embodiment of the present disclosure.

[0115] With reference to Fig. 9, the process S120 for detecting the abnormality of the rear wheel steering motor can be performed as follows.

[0116] First, the input data and the actual measurement data are input to the discriminator 22 by the processor 120, which receives a discrimination value with respect to the actual measurement data generated by the discriminator (22) (S121).

[0117] Next, the processor 120 inputs error data including a discrimination value related to the actual measurement data and numerical values ​​related to the difference between the estimated value and the measured value to the anomaly detection model 30 and obtains an output of the anomaly detection model 30 (S122).

[0118] There may be a plurality of data sets containing the input data, the estimated data, and the actual measurement data. The error data may include a mean and standard deviation of the errors between the actual measurement data and the estimated data of the plurality of data sets, a maximum absolute error between the actual measurement data and the estimated data of the plurality of data sets, and the discrimination value of the discriminator 22 for the input data and the actual measurement data included in the plurality of data sets.

[0119] In one embodiment of the present disclosure, the error data may include a mean value of errors between the first estimated value and the first actual measured value, a standard deviation between the first estimated value and the first actual measured value, a maximum absolute error between the first estimated value and the first actual measured value, a mean value of errors between the second estimated value and the second actual measured value, a standard deviation between the second estimated value and the second actual measured value, a maximum absolute error between the second estimated value and the second actual measured value, and a discrimination value of the discriminator for the input data, the first actual measured value, and the second actual measured value.

[0120] The plurality of data sets comprising the estimated data and the actual measurement data can be treated as a batch. For example, 100 to 150 data sets (as a specific example, 128 data sets) can be treated as a batch, and the error data can be determined for each batch.

[0121] The failure data obtained for a batch can be input to the anomaly detection model 30. Furthermore, the degree of the rear wheel steering motor failure (rear wheel steering motor performance degradation) can be determined based on an output (characteristic) of the anomaly detection model 30 that receives the failure data.

[0122] Meanwhile, the present disclosure additionally provides a non-transitory computer-readable storage medium storing a program for executing the method for detecting the abnormality of the rear wheel steering motor. Specifically, the present disclosure may provide a non-transferable computer-readable storage medium storing a program including at least one instruction for executing the method for detecting an abnormality of a rear wheel steering motor.

[0123] In this case, the instruction may include not only the machine code generated by a compiler, but also the high-level language code executable by a computer.

[0124] The non-transitory, computer-readable storage medium may comprise a magnetic medium such as a hard disk, a floppy disk, or a magnetic tape, an optical medium such as a CD-ROM or a DVD, a magneto-optical medium such as a floppy disk, or a hardware device configured to store and execute program instructions, such as a ROM, a RAM, a flash memory, etc.

[0125] Regarding an anomaly detection metric, an F1 score as specified above can be considered.

[0126] As a result of a simulation, it was determined that, according to the present disclosure, a reduction in the maximum power of the rear-wheel steering motor of up to 10% can be predicted when the power reaches an F1 value of 0.85 or higher. In other words, according to the present disclosure, the degree of degradation of the rear-wheel steering motor can be accurately predicted before the rear-wheel steering motor, which is arranged in the rear-wheel steering system and generates the driving force for steering the rear wheels, completely fails.

[0127] In other words, according to the present disclosure, the degree of degradation of the rear-wheel steering motor, which is arranged in the rear-wheel steering system and generates the driving force for steering the rear wheels, can be accurately predicted before the rear-wheel steering motor, which is located in the rear-wheel steering system and generates the driving force for steering the rear wheels, completely fails. This makes it possible to take proactive measures before the rear-wheel steering motor fails to prevent the rear-wheel steering motor from failing.

[0128] In this way, the present disclosure enables the estimation of the future function and remaining service life of the system, as well as prognostic diagnosis suitable for predictive maintenance applications. This allows preventive measures and maintenance to be effectively controlled before a failure of the rear-wheel steering motor of the vehicle's rear-wheel steering system occurs.

[0129] According to the above configuration, in the apparatus and method for detecting the abnormality of the rear wheel steering motor and the non-transitory computer-readable storage medium storing a program for performing the method according to one aspect of the present disclosure, it is possible to predict performance deterioration of the rear wheel steering motor before failure of the rear wheel steering motor that generates the driving force for driving the rack that performs the rear wheel steering of the vehicle occurs based on an artificial intelligence-based digital twin algorithm.

[0130] It is further possible, in the apparatus and method for detecting the abnormality of the rear wheel steering motor and the non-transitory computer-readable storage medium storing a program for performing the method according to one aspect of the present disclosure, to predict performance deterioration of the rear wheel steering motor using signals of a CAN of the vehicle without a separate additional sensor.

[0131] It should be understood that the effects of the present disclosure are not limited to the effects described above, and include all effects that can be derived from a configuration of the invention described in detailed descriptions or claims of the present disclosure.

[0132] Although embodiments of the present disclosure have been described, the spirit of the present disclosure is not limited to the embodiments set forth in the description. A person skilled in the art who understands the spirit of the present disclosure can easily propose other embodiments by supplementing, changing, removing, or adding components within the scope of this spirit, but these embodiments are also within the spirit of the present disclosure. QUOTES CONTAINED IN THE DESCRIPTION

[0000] This list of documents submitted by the applicant was generated automatically and is included solely for the convenience of the reader. This list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions. Cited patent literature

[0000] KR 10-2023-0106182

[0001] KR 10-2024-0089573

[0001]

Claims

[1] Device (100) comprising: a memory (110) configured to store one or more instructions; and a processor (120) configured to detect an abnormality of a rear-wheel steering motor (270) that generates a drive force for driving a rack (280) that performs the rear-wheel steering of a vehicle by executing one or more commands stored in the memory (110), wherein the processor (120) is configured to: inputting input data to an artificial neural network model (20) relating to the rear wheel steering of the vehicle; receive from the artificial neural network model (20) estimated data relating to the rear wheel steering of the vehicle as output data; To obtain measurement data from a sensor relating to the vehicle's rear wheel steering; to compare the estimated data and the measured data; and to compare the anomaly of the rear wheel steering motor (270) based on a comparison of the estimated data with the measured data. [2] The apparatus (100) of claim 1, wherein the input data includes at least one of a speed of the vehicle wheel, a gearshift lever position of the vehicle, a steering angle of the vehicle, and a steering angular velocity of the vehicle. [3] The apparatus (100) of claim 1 or 2, wherein the estimation data includes a first estimate for a first residual value that is a difference between a command and a measured value for a position of the rack (280) determined to correspond to the input data, and wherein the measured data includes a first actual measured value that is an actual measured value of the first residual value. [4] The apparatus (100) of claim 3, wherein the estimation data further comprises a second estimate for a second residual value that is a difference between a command and a measured value for a motor torque to be produced by the rear wheel steering motor (270) determined to correspond to the input data, and wherein the measured data further comprises a second actual measured value that is an actual measured value of the second residual value. [5] The device (100) of any one of claims 1 to 4, wherein the processor (120) is further configured to receive the input data via a controller area network (CAN, 300) of the vehicle. [6] The device (100) according to any one of claims 1 to 5, wherein the artificial neural network model (20) comprises a generative adversarial network (GAN) having a generator (21) configured to receive the input data and generate the estimation data and a discriminator (22) configured to receive the measurement data and output a discrimination value associated with the actual measurement. [7] The apparatus (100) of claim 6, wherein the processor (120) is further configured to input error data relating to a difference between the estimated value and the measurement data into an anomaly detection model (30) to detect the anomaly of the rear wheel steering motor (270). [8] Device (100) according to claim 7, wherein: the estimated data include a variety of estimates; the measurement data includes a large number of measured values; the input data comprises a plurality of input values; and the error data comprises a mean and a standard deviation of errors between the plurality of estimated values ​​and the plurality of measured values, a maximum absolute error among the errors, and the discrimination value of the discriminator (22) for the plurality of input values ​​and the plurality of measured values. [9] A method for detecting an abnormality of a rear wheel steering motor (270) of a vehicle, executed by a processor (120), the method comprising: Inputting, by the processor (120), input data into an artificial neural network model (20) relating to the rear wheel steering of the vehicle; Obtaining, by the processor (120), estimate data from the artificial neural network model (20) relating to the rear wheel steering of the vehicle; Obtaining, by the processor (120), measurement data from a sensor relating to the rear wheel steering of the vehicle; Comparing, by the processor (120), the estimated data and the measured data; and Comparing, by the processor (120), the abnormality of the rear wheel steering motor (270) based on a result of comparing the estimated data with the measured data. [10] The method of claim 9, wherein the input data includes information about at least one of a speed of the vehicle wheel, a steering angle of the vehicle, and a steering angular speed of the vehicle. [11] The method of claim 9 or 10, wherein the estimation data includes a first estimate of a first residual value that is a difference between a command and a measured value for a position of the rack (280) determined to correspond to the input data, and wherein the measured data includes a first actual measured value that is an actual measured value of the first residual value. [12] The method of claim 11, wherein the estimation data further comprises a second estimate of a second residual value that is a difference between a command and a measured value for motor torque to be produced by the rear wheel steering motor (270) determined to correspond to the input data, and wherein the measured data further comprises a second actual measured value that is an actual measured value of the second residual value. [13] The method of any one of claims 9 to 12, wherein the artificial neural network model (20) comprises a generative neural network (GAN) including: a generator (21) arranged to receive the input data and generate the estimated value, and a discriminator (22) arranged to receive the input data and the measured data and output a discrimination value with respect to the actual measurement. [14] The method of claim 13, wherein detecting includes: Inputting, by the processor (120), the input data and the measurement data into the discriminator (22) and obtaining, by the processor (120), the discrimination value for the measurement data generated by the discriminator (22); and Inputting, by the processor (120), error data including the discrimination value and a value related to a difference between the estimation data into an anomaly detection model (30), and obtaining, by the processor (120), an output of the anomaly detection model (30). [15] A non-transitory computer-readable medium configured to store at least one instruction that, when executed by a processor (120), causes the processor (120) to perform operations for detecting an abnormality of a rear-wheel steering motor (270) configured to generate a drive force for driving a rack (280) that performs rear-wheel steering of a vehicle, the operations comprising: Inputting, by the processor (120), input data into an artificial neural network model (20) relating to the rear wheel steering of the vehicle; Obtaining, by the processor (120), estimate data from the artificial neural network model (20) relating to the rear wheel steering of the vehicle; Obtaining, by the processor (120), measurement data from a sensor relating to the rear wheel steering of the vehicle; Comparing, by the processor (120), the estimated data and the measured data; and Comparing, by the processor (120), the abnormality of the rear wheel steering motor (270) based on a result of comparing the estimated data with the measured data.

Images