Motor abnormality detection device and method for column-type electric power steering gear, and non-transitory computer-readable storage medium having stored therein program for executing method

Abstract

Disclosed are an apparatus and a method for detecting a motor abnormality of a tubular column type electric power steering gear, and a non-transitory computer-readable storage medium storing a program for executing the method. The motor abnormality detection device for a column-type electric power steering gear for detecting abnormality of a motor of a column-type electric power steering gear for providing an auxiliary steering force to a steering column of an electric power steering system of a vehicle, includes: a memory in which one or more commands are stored; and a processor executing the one or more instructions, the processor inputting operation data associated with a steering wheel operation by a driver of the vehicle and state data representing a state of the vehicle to an artificial neural network model by executing the one or more instructions, and an output estimation value of the motor output by the artificial neural network model is acquired, and whether the motor is abnormal or not is detected by comparing the estimation value with an output measurement value of the motor.

Description

Technical Field

[0001] The present invention relates to a motor abnormality detection device and method for a column-type electric power steering (Electric Power Steering, EPS) and a non-transitory computer-readable storage medium storing a program for executing the method. More specifically, the present invention relates to a motor abnormality detection device and method for a column-type electric power steering that can detect reduced motor performance and a non-transitory computer-readable storage medium storing a program for executing the method, wherein the motor is configured on a steering column connected to a steering wheel to provide auxiliary force when a driver operates the steering wheel. Background Art

[0002] The Electric Power Steering (EPS) system uses a motor to assist the driver in steering. Among them, the column-type electric power steering system is configured to provide the steering assist force generated by the motor to a steering column connected to the vehicle steering wheel.

[0003] If the motor that generates the steering assist force in the column electric power steering system fails, it will be difficult for the driver to steer the vehicle. As a result, the driver cannot steer as intended, which may lead to an accident.

[0004] As described above, the motor of the column electric power steering system is a very important factor in vehicle safety. Therefore, in order to improve the safety of a vehicle equipped with the column electric power steering system, it is necessary to predict the output reduction of the motor before the motor of the column electric power steering system fails.

[0005] However, the current approach to the fail-safety of the motor of a column-type electric power steering system focuses more on post-failure diagnosis and follow-up measures after a failure occurs than on preventing the failure in advance. In addition, the existing column-type electric power steering system uses a fail-safety based on the motor current, but has the limitation of being unable to directly respond to a drop in output.

[0006] Patent document: Korean authorized patent No. 2098049 "EPS control device and method for cutting off motor drive power supply when overcurrent occurs", the authorization announcement date is 2020.04.01. Summary of the invention

[0007] Problem that the invention aims to solve

[0008] The present invention is used to solve the above-mentioned problem. The purpose of the present invention is to provide a motor abnormality detection device and method for a column-type electric power steering device, which can predict the performance degradation of the motor in advance, and a non-temporary computer-readable storage medium storing a program for executing the method, wherein the motor is configured in the vehicle's column-type electric power steering system to generate steering assist force.

[0009] Another object of the present invention is to provide a motor abnormality detection device and method for a column-type electric power steering device and a non-temporary computer-readable storage medium storing a program for executing the method, which can utilize the controller area network (CAN) signal in the vehicle to effectively detect the output reduction of the motor of the column-type electric power steering device in advance.

[0010] The technical problems of the present invention are not limited to the technical problems mentioned above, and ordinary technicians in the technical field to which the present invention belongs can clearly understand other technical problems not mentioned through the following description.

[0011] Means used to solve problems

[0012] According to one aspect of the present invention, a motor abnormality detection device for a column-type electric power steering device is provided, which is used to detect the abnormality of the motor of the column-type electric power steering device that provides auxiliary steering force to the steering column of the electric power steering (EPS) system of a vehicle, and comprises: a memory storing one or more instructions; and a processor executing the one or more instructions, wherein the processor inputs operation data associated with the steering wheel operation of the driver of the vehicle and status data representing the status of the vehicle into an artificial neural network model by executing the one or more instructions, obtains an output estimated value of the motor output by the artificial neural network model, and detects whether the motor is abnormal by comparing the estimated value with the output measurement value of the motor.

[0013] According to the motor abnormality detection device for a column type electric power steering according to one aspect of the present invention, the operation data may include one or more of a steering angle, a steering angular velocity, and a steering torque.

[0014] According to the motor abnormality detection device of a column type electric power steering device according to one aspect of the present invention, the status data may include one or more of the vehicle speed, the vehicle lateral acceleration, the vehicle yaw rate and the vehicle wheel speed.

[0015] According to the motor abnormality detection device for a column type electric power steering device according to one aspect of the present invention, the operation data and the status data are constituted by signals that can be acquired through a Controller Area Network (CAN) of the vehicle.

[0016] According to the motor abnormality detection device of a column-type electric power steering device according to one aspect of the present invention, the artificial neural network model may include: a generative adversarial network (GAN), including a generator that receives the operation data and the state data to generate the inference value.

[0017] According to the motor abnormality detection device for a column-type electric power steering device according to one aspect of the present invention, the artificial neural network model may further include: a discriminator, which receives measurement data including the operation data, the state data and the measurement value, and outputs an identification value for the measurement data.

[0018] According to the motor abnormality detection device for a column type electric power steering device according to one aspect of the present invention, the generator may be composed of a multivariate transformer.

[0019] According to the motor abnormality detection device of a column-type electric power steering device of one aspect of the present invention, the processor can input the error data associated with the difference between the estimated value and the measured value into the abnormality detection model by executing one or more instructions to determine whether the motor is abnormal.

[0020] According to the motor abnormality detection device of a column-type electric power steering device according to one aspect of the present invention, the abnormality detection model may use a One-Class Support Vector Machine (OCSVM) algorithm.

[0021] According to one aspect of the present invention, a motor abnormality detection device for a column-type electric power steering device includes a plurality of data sets including the operation data, the status data, the measurement values ​​and the inferred values, and the error data may include an average and a standard error of the error between the measurement values ​​and the inferred values ​​obtained from each of the plurality of data sets, a maximum absolute error between the measurement values ​​and the inferred values ​​of the plurality of data sets, and identification values ​​of the measurement data of the data sets by the plurality of identifiers.

[0022] According to the motor abnormality detection device for a column type electric power steering device according to one aspect of the present invention, the discriminator may additionally receive inference data including the operation data, the state data and the inference value, and additionally output an identification value for the inference data.

[0023] According to the motor abnormality detection device of a column-type electric power steering device according to one aspect of the present invention, the artificial neural network model is constructed by alternately performing learning by the generator and the discriminator, and the operation data, the state data and the measurement values ​​used during the learning can be obtained when the motor is in a normal state.

[0024] According to another aspect of the present invention, a method for detecting abnormality of a motor of a column-type electric power steering device is provided, which is used to detect abnormality of a motor of a column-type electric power steering device that provides auxiliary steering force to a steering column of an electric power steering (EPS) system of a vehicle, and comprises: a step in which a processor inputs operation data associated with a steering wheel operation of a driver of the vehicle and status data representing a status of the vehicle into an artificial neural network model, and obtains an output estimated value of the motor output by the artificial neural network model; and a step in which the processor detects whether the motor is abnormal by comparing the estimated value with an output measurement value of the motor.

[0025] According to the method for detecting abnormality of a motor of a column type electric power steering according to one aspect of the present invention, the operation data may include at least one of a steering angle, a steering angular velocity and a steering torque.

[0026] According to the motor abnormality detection method of a column-type electric power steering device according to one aspect of the present invention, the status data may include one or more of the vehicle speed, the vehicle lateral acceleration, the vehicle yaw rate and the vehicle wheel speed.

[0027] According to the motor abnormality detection method of a column-type electric power steering device according to one aspect of the present invention, the artificial neural network model is composed of a generative adversarial network (GAN), and the generative adversarial network includes: a generator, which receives the operation data and the state data to generate the inferred value; and a discriminator, which receives measurement data including the operation data, the state data and the measurement value, and outputs a discrimination value for the measurement data.

[0028] According to the motor abnormality detection method of a column-type electric power steering device according to one aspect of the present invention, in the step of obtaining the inferred value, the processor can input the operation data and the status data to the generator and obtain the inferred value generated by the generator.

[0029] According to the motor abnormality detection method of a column-type electric power steering device according to one aspect of the present invention, the step of detecting whether the motor is abnormal includes: the processor inputs the measurement data including the operation data, the status data and the measurement value into the discriminator, and obtains the identification value for the measurement data generated by the discriminator; and the processor inputs the identification value for the measurement data, including error data of a numerical value associated with the difference between the inferred value and the measured value, into an abnormality detection model and obtains the output of the abnormality detection model.

[0030] According to the motor abnormality detection method of a column-type electric power steering device according to one aspect of the present invention, there may be multiple data sets including the operation data, the status data, the inferred value and the measured value, and the error data may include the average and standard error of the error between the measured value and the inferred value obtained from each of the multiple data sets, the maximum absolute error between the measured value and the inferred value of the multiple data sets, and the identification values ​​of the measurement data of the data sets by multiple identifiers.

[0031] According to the motor abnormality detection method of a column-type electric power steering device according to one aspect of the present invention, the artificial neural network model is constructed by alternately performing learning by the generator and the discriminator, and the operation data, the state data and the measurement values ​​used during the learning can be obtained when the motor is in a normal state.

[0032] According to another aspect of the present invention, there is provided a computer-readable storage medium which is a non-transitory computer-readable medium storing a program including at least one instruction for executing the motor abnormality detection method for a column-type electric power steering device.

[0033] Effects of the Invention

[0034] According to the above-mentioned structure, the motor abnormality detection device and method of the column electric power steering (Electric Power Steering) system according to one aspect of the present invention and the non-temporary computer-readable storage medium storing a program for executing the method, which is based on a digital twin algorithm based on artificial intelligence, can predict the performance degradation of the motor configured in the column electric power steering system before the failure occurs.

[0035] In addition, according to one aspect of the present invention, a motor abnormality detection device and method for a column-type electric power steering device and a non-temporary computer-readable storage medium storing a program for executing the method can utilize a vehicle's controller area network (CAN) signal to predict performance degradation of the motor of the column-type electric power steering device without the need for additional sensors.

[0036] 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 derived from the constitution of the invention described in the detailed description of the present invention or the appended claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 The diagram schematically shows the configuration of a column-type electric power steering (Electric Power Steering) system of a vehicle.

[0038] Figure 2 It is a diagram showing the structure of a motor abnormality detection device for a column type electric power steering according to one embodiment of the present invention.

[0039] Figure 3 This is a diagram showing a model used for obtaining an estimated value or detecting abnormality in a motor abnormality detection device for a column type electric power steering according to an embodiment of the present invention.

[0040] Figure 4 It is a diagram showing the detailed structure of the artificial neural network model.

[0041] Figure 5 This is a diagram showing the detailed structure of a generator of an artificial neural network model.

[0042] Figure 6 It is a diagram showing the operation of the motor abnormality detection device of the column type electric power steering according to one embodiment of the present invention.

[0043] Figure 7 The flowchart shows a method for detecting abnormality of a motor of a column type electric power steering device according to an embodiment of the present invention.

[0044] Figure 8 The present invention is a detailed flowchart showing the steps of detecting whether a motor is abnormal in a method for detecting abnormality of a motor of a column-type electric power steering device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0045] Hereinafter, embodiments of the present invention are described in detail with reference to the accompanying drawings so that a person skilled in the art can easily implement the present invention. The present invention can be implemented in various forms and is not limited to the embodiments described herein. In order to clearly explain the present invention, parts not related to the description are omitted in the accompanying drawings, and the same reference numerals are given to the same or similar components throughout the specification.

[0046] The words and terms used in this specification and the appended claims should not be interpreted as being limited to their usual or dictionary meanings, but in order to describe one's invention in the best way, they should be interpreted as meanings and concepts that are consistent with the technical ideas of the present invention in accordance with the principle that the inventor is able to define terms and concepts.

[0047] In this specification, the terms "include" or "have" are used to illustrate the existence of features, numbers, steps, actions, constituent elements, parts or their combinations recorded in the specification, rather than excluding the existence or additional possibilities of one or more other features, numbers, steps, actions, constituent elements, parts or their combinations in advance.

[0048] Figure 1 The diagram schematically shows the configuration of a column-type electric power steering (Electric Power Steering) system of a vehicle.

[0049] Figure 1 The column electric power steering system 10 , operation data associated with a steering wheel operation of a driver of a vehicle on which the column electric power steering system 10 is installed, and state data associated with a driving state of the vehicle are exemplarily shown.

[0050] Reference Figure 1 The column-type electric power steering system 10 of a vehicle may include: a steering wheel 11 operated by a driver, a steering column 12 connected to the steering wheel 11 to transmit steering force to the wheel side of the vehicle, a steering angle sensor 13, a steering torque sensor 14, and a vehicle state measurement module 15.

[0051] The steering angle sensor 13 measures the steering angle θ of the steering wheel 11. steering (steering angle) and steering angular velocity That is, the steering angle sensor information D measured by the steering angle sensor 13 is steering Including the steering angle θ steering and steering angular velocity

[0052] The steering torque sensor 14 measures the steering torque T steering More specifically, the steering torque sensor 14 may measure torque applied to the steering column 12 according to the operation of the steering wheel 11 .

[0053] Steering angle sensor information D measured by the steering angle sensor 13 steering (i.e., the steering angle θ steering and steering angular velocity ) and the steering torque T measured by the steering torque sensor 14steering May be defined as operational data associated with steering wheel operation of a driver of the vehicle.

[0054] The vehicle state detection module 15 includes one or more sensors for measuring information related to the state of the vehicle. The vehicle state detection module information D measured by the vehicle state detection module 15 vehicle May include: vehicle speed V x , the lateral acceleration of the vehicle a y (lateral acceleration), the vehicle's yaw rate (yaw rate), vehicle wheel speed V wheel (wheel velocity). Among them, the wheel velocity V wheel The measurement may be performed for each of a plurality of wheels of the vehicle.

[0055] Vehicle status detection module information D vehicle Can be defined as status data representing the status of the vehicle.

[0056] The steering angle θ measured by the steering angle sensor 13 steering and steering angular velocity The steering torque T measured by the steering torque sensor 14 steering , the speed V of the vehicle measured by the vehicle state detection module 15 x , lateral acceleration a y , yaw rate Wheel speed V wheel The signal is transmitted to an electronic controller 17 (ECU) via a controller area network 16 (CAN).

[0057] The electronic controller 17 receives the data transmitted through the controller area network 16, and generates a command for the motor 18 that generates the auxiliary torque that helps the steering by performing calculations. The command is transmitted to the motor 18. At this time, the command can be provided to the motor 18 in the form of current. At this time, the electronic controller 17 can perform feedback control for the motor 18.

[0058] The torque input through the steering wheel 11 and the torque generated by the motor 18 are transmitted to the steering device 19 connected to the wheels of the vehicle. The steering device 19 is driven by the torque input through the steering wheel 11 and the torque generated by the motor 18. By driving the steering device 19, the direction of the wheels of the vehicle can be adjusted and the steering of the vehicle can be achieved.

[0059] Figure 21 is a diagram showing the structure of a motor abnormality sensing device for a column-type electric power steering device according to an embodiment of the present invention. Figure 3 This is a diagram showing a model used for obtaining an estimated value or detecting abnormality in a motor abnormality detection device for a column type electric power steering according to an embodiment of the present invention.

[0060] The motor abnormality detection device 100 of a column electric power steering device according to an embodiment of the present invention detects abnormality of the motor 18 generating steering assist force in the column electric power steering system of a vehicle. More specifically, the motor abnormality detection device 100 of a column electric power steering device can detect a decrease in output or abnormality of the motor 18.

[0061] The motor abnormality detection device 100 of a column-type electric power steering device according to an embodiment of the present invention can detect the performance degradation of the motor 18 before the motor 18 fails by using a digital twin algorithm for the vehicle based on artificial intelligence. The digital twin algorithm can virtually construct a column-type electric power steering system of the vehicle.

[0062] For example, the motor abnormality detection device 100 of a column type electric power steering device according to an embodiment of the present invention can be configured in Figure 1 The electronic controller 17 of the column-type electric power steering system 10 is shown in FIG. Of course, this is only an example, and the motor abnormality detection device 100 of the column-type electric power steering device can also be configured in other positions.

[0063] Reference Figure 2 According to an embodiment of the present invention, a motor abnormality detection device 100 for a column-type electric power steering device may include a memory 110 and a processor 120 .

[0064] The memory 110 stores one or more instructions. The one or more instructions may constitute a program for detecting abnormality of a column electric power steering motor. The one or more instructions stored in the memory 110 may be executed by the processor 120 .

[0065] The memory 110 may include a hardware device configured to store the one or more instructions. For example, the memory 110 may include a storage medium such as a read-only memory (ROM), a random access memory (RAM), a flash memory, etc. In addition, the memory 110 may also include a magnetic medium (Magnetic Media) such as a floppy disk and a magnetic tape, an optical recording medium (Optical Media) such as a Compact Disk Read Only Memory (CD-ROM) and a Digital Video Disk (DVD), a magneto-optical medium (Magneto-Optical Media) such as a floppy disk (Floptical Disk), etc.

[0066] The processor 120 executes the one or more instructions. For example, the processor 120 may be a hardware unit that performs calculations and controls. The processor 120 may include one or more arithmetic logic units (ALUs) and registers.

[0067] The processor 120 inputs operation data associated with the steering wheel operation of the driver of the vehicle and state data representing the vehicle state into the artificial neural network model 20 by executing the one or more instructions, and obtains the output estimation value of the motor 18 output by the artificial neural network model 20.

[0068] The operating data may include a steering angle θ steering , Steering angular velocity and steering torque T steering As mentioned above, the steering angle θ steering and steering angular velocity The steering torque T can be measured by the steering angle sensor 13. steering The steering torque can be measured by the steering torque sensor 14 .

[0069] The status data may include the speed V of the vehicle x , lateral acceleration a y , yaw rate and the wheel speed V of the vehicle wheel In addition, when the vehicle has a plurality of wheels, the wheel speed may be acquired for each of the plurality of wheels.

[0070] The above-mentioned operation data and status data can be acquired through the controller area network (CAN) 200. In other words, the operation data and the status data can be composed of signals that can be acquired through the controller area network 200 of the vehicle. Therefore, according to the present invention, the abnormality of the motor can be effectively detected without using an additional sensor associated with the abnormality detection of the column electric power steering motor.

[0071] In association with this, the memory 110 may be directly or indirectly connected to the controller area network 200 of the vehicle. The memory 110 may receive the operation data and the status data from the controller area network 200. Therefore, the processor 120 may obtain the operation data and the status data from the memory 110.

[0072] The artificial neural network model 20 receives the operation data and the state data and outputs an output estimation value of the motor 18. In one embodiment of the present invention, the artificial neural network model 20 may include a Generative Adversarial Network (GAN).

[0073] In one embodiment of the present invention, the artificial neural network model 20 can be a deep learning-based neural twin model for a column-type electric power steering system of a vehicle. In other words, the artificial neural network model 20 can function as a virtual twin model of the column-type electric power steering system of the vehicle.

[0074] Figure 4 It is a diagram showing the detailed structure of the artificial neural network model.

[0075] Reference Figure 4 , the artificial neural network model 20 may include a generator 21 and a discriminator 22.

[0076] The artificial neural network model 20 is constructed by alternately performing learning with the generator 21 and the discriminator 22. At this time, the data used when performing the learning can be acquired when the motor 18 of the column electric power steering system 10 is in a normal state. Thus, the inferred value output by the artificial neural network model 20 can track the output measurement value of the motor 18 acquired when the motor 18 is in a normal state.

[0077] The generator 21 receives the operation data and the state data to generate an output estimation value of the motor 18. 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 based on a multivariate transformer.

[0078] The generator 21 calculates the operation data and the state data to output the estimated output value of the motor 18 of the column electric power steering system. The estimated output value estimated by the generator 21 tracks the motor output value outputted corresponding to the operation data and the state data when the column electric power steering system is in a normal state.

[0079] Figure 5 This is a diagram showing the detailed structure of a generator of an artificial neural network model.

[0080] Reference Figure 5 , the generator 21 may include an encoder 21a and a decoder 21b.

[0081] The encoder 21a and the decoder 21b constitute a network for obtaining the output estimation value of the motor output. In other words, the generator 21 can be composed of an encoder 21a-decoder 21b structure network trained in an end-to-end manner to estimate the estimation value.

[0082] The encoder 21a may be designed to extract high-level features from the operation data and the state data using a transformer block and linear operations.

[0083] At this time, the transformer block may include an embedding layer, a self-attention layer, and a feed-forward layer.

[0084] First, the embedding layer in the transformer block can encode spatiotemporal information into input sequences using a trainable embedding matrix.

[0085] Next, deep features are extracted through a self-attention layer and refined using a feed-forward layer.

[0086] At this time, the self-attention layer can use a scaled dot-product attention mechanism. The self-attention layer can be the main building block in the variable-based deep neural network (DNN) architecture that allows the model to process and understand dependencies within the input sequence.

[0087] The scaled dot product attention first applies layer normalization to the input sequence and processes its results into three intrinsic vectors of query vector Q, key vector K and value vector V through linear operation.

[0088] Next, based on the derived vector, the attention score AS for each position of the input sequence can be calculated. The calculation formula of the attention score AS can be given as shown in the following first formula:

[0089] First formula

[0090]

[0091] σ(·) represents the softmax operation, ∥xinput∥dim represents the feature dimension of the input, and (·) represents the dot product.

[0092] The attention score quantifies the relative importance of each position in the input sequence associated with a given query vector. That is, more appropriate positions will be assigned higher scores.

[0093] In order to calculate the query vector, key vector and initial input value of the decoder 21b, the output of the transformer block can be supplied to two different linear operations.

[0094] The decoder 21b may use the acquired values ​​to infer the inferred values ​​in an auto-regressive manner similar to Sequence-to-Sequence Recurrent Neural Networks.

[0095] Similar to the encoder 21a, the decoder 21b may include a transformer block and a linear operation. In addition, the decoder 21b may further include a cross-attention layer in the transformer block.

[0096] The cross-attention layer can use the query vector and key vector of encoder 21a to perform scaled dot-product attention to learn the dynamic correlation between the input signal and the inferred signal.

[0097] The discriminator 22 receives measurement data including the operation data, the state data, and output measurement values ​​of the motor, and outputs a discriminator value for the measurement data.

[0098] In addition, the discriminator 22 may also additionally receive the inference data including the operation data, the state data and the output inference value of the motor, and additionally output the identification value for the inference data. Such a process may be completed when the generator 21 and the discriminator 22 perform learning.

[0099] In this way, the discriminator 22 can output a discriminant value for the measurement data during the operation for abnormality detection, and at the same time, can output a discriminant value for the inferred data during the operation for learning.

[0100] The discriminator 22 may be composed of a discriminator network used for adversarial training of GAN. In other words, the generator 21 and the discriminator 22 may be trained in a manner of performing adversarial training in order to improve the inference performance and set the GAN model.

[0101] In more detail, the discriminator 22 may perform optimization alternately with the generator 21 to solve a Wasserstein min-max problem such as the second formula.

[0102] Second formula

[0103]

[0104] x D，Real represents the actual data set consisting of operation data, status data, and output measurement values ​​of the motor, x D，Fake A virtual data sample consisting of operation data, status data, and estimated motor output values.

[0105] In the artificial neural network model 20, the generator 21 is trained to deceive the D，Real and x D，Fake Therefore, the generator 21 can generate an estimated value for tracking the motor output of the column electric power steering system in a normal state.

[0106] In association with this, the loss function for GAN training can be defined as the following third formula:

[0107] The third formula

[0108]

[0109] N is the batch size, L G is the loss function of the generator, LD is the loss function of the discriminator.

[0110] The first term of the loss of generator 21 is equivalent 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 GAN loss function L GAN .

[0111] In one embodiment of the present invention, in order to reflect the mechanical characteristics of the column electric power steering system into the loss function, the following matters may be considered.

[0112] First, the output of the motor in the column-type electric power steering system can be obtained by the fourth formula.

[0113] The fourth formula

[0114] T motor =T Load -T Steering

[0115] T motor is the output of the motor, T Load is the force acting on the tire, T Steering is the steering force of the driver.

[0116] In addition, T in the fourth formula Load It can be defined as a function of the ECU input signal relying on the Dugoff tire model. Specifically, it can be defined as a function like the following fifth formula.

[0117] The fifth formula

[0118]

[0119] is the vehicle's ECU input signal, θ sw is the steering angle of the vehicle and n is a given value.

[0120] In the fifth formula, δ1 and δ2 represent model-related uncertainties, and δ3 represents system uncertainty. In addition, the input signal It is the data that the vehicle's ECU can receive or measure through the controller area network. Load If the driver's steering force (steering torque) is removed, the motor output value can be derived.

[0121] The mechanical characteristics of the column electric power steering system can be defined as the fourth and fifth formulas above. In this way, the mechanical characteristics of the column electric power steering system can be regarded as a physics-based loss function of the artificial neural network model 20.

[0122] Through the above-mentioned steps, the processor 120 can obtain the estimated output value of the motor of the column electric power steering system.

[0123] In addition, the processor 120 compares the estimated value thus obtained with the actual motor output measurement value. The processor 120 can detect whether the motor 18 is abnormal by comparing the estimated value with the measurement value.

[0124] The processor 120 can determine whether the motor of the column-type electric power steering device is abnormal by executing the one or more instructions and inputting the error data associated with the difference between the estimated value and the measured value into the abnormality detection model 30. For example, the abnormality detection model 30 can use a one-class support vector machine (OCSVM) algorithm.

[0125] There may be a plurality of data sets including the operation data, the state data, the measured values ​​and the inferred values. The error data may include an average and a standard error of the error between the measured values ​​and the inferred values ​​obtained from each of the plurality of data sets, a maximum absolute error between the measured values ​​and the inferred values ​​of the plurality of data sets, and a discriminator value of the measured data of the discriminator for the plurality of data sets.

[0126] As described above, the measurement data may include the operation data, the status data and the measurement values.

[0127] The plurality of data sets including the measured values ​​and the estimated values ​​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 may be acquired for each batch.

[0128] The error data acquired for one batch may be input to the abnormality detection model 30. In addition, the degree of abnormality (performance degradation of the motor) of the motor may be detected based on the output (feature) acquired from the abnormality detection model 30 receiving the error data.

[0129] Regarding the anomaly detection metric, the F1 score given by the following sixth formula may be considered.

[0130] Sixth formula

[0131]

[0132] TP is a true positive sample, FP is a false positive sample, and FN is a false negative sample. A positive sample indicates that the performance of the motor is reduced.

[0133] As described above, the discriminator 22 can calculate not only the discriminant value of the measured data in the data set, but also the discriminant value of the inferred data in the data set. The inferred data may include the operation data, the state data and the inferred value. The discriminant value of the inferred data of the data set by the discriminator 22 can be fed back to the generator 21 of the artificial neural network model 20 for training.

[0134] So far, the structure of the motor abnormality detection device 100 for a column type electric power steering according to an embodiment of the present invention has been described in detail. Next, the operation of the motor abnormality detection device 100 for a column type electric power steering will be described.

[0135] Figure 6 It is a diagram showing the operation of the motor abnormality detection device of the column type electric power steering according to one embodiment of the present invention.

[0136] Reference Figure 6 The motor abnormality detection device 100 of a column type electric power steering device according to an embodiment of the present invention operates as follows.

[0137] First, the memory 110 stores input signals obtained from the ECS system of the vehicle. and the output measurement value F of the motor of the column electric power steering m .

[0138] Among them, the input signal In one embodiment of the present invention, the input signal It may include a steering angle, a steering angular velocity, a steering torque, a speed of the vehicle, a lateral acceleration of the vehicle, a yaw rate of the vehicle, and a wheel speed of the vehicle.

[0139] In addition, multiple input signals can be and the output measurement value F of the motor of the column electric power steering m That is, in one embodiment of the present invention, data processing and calculation can be performed in units of data batches.

[0140] Then, the processor 120 converts the input signal into The artificial neural network model 20 is inputted to obtain the output estimation value F of the motor of the column electric power steering device outputted by the artificial neural network model 20. e More specifically, the processor 120 may convert the input signal The output value F of the motor of the column electric power steering device output by the generator 21 is obtained. e .

[0141] In addition, the processor 120 converts the input signal into and the output measurement value F of the motor of the column electric power steering m The processor 120 can input the input signal to the artificial neural network model 20 and obtain the identification value DS. and the output measurement value F of the motor of the column electric power steering m The measured data is input to the discriminator 22 of the artificial neural network model 20, and the discrimination value DS output by the discriminator 22 for the measured data is obtained.

[0142] Next, the processor 120 outputs the error data D Error The error data DError can be output in different data batches.

[0143] As described above, there are a plurality of data sets including the operation data, the state data, the measured values, and the estimated values, and the error data D Error The average μ of the errors between the measured values ​​and the estimated values ​​obtained from each of the multiple data sets may be included. E and standard error σ E , the maximum absolute error Max between the measured values ​​and the estimated values ​​of the multiple data sets E , a discrimination value DS of the discriminator 22 for the measurement data acquired from the plurality of said data sets.

[0144] 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.

[0145] Based on the received error data D Error The processor 120 can detect the degree of abnormality (performance degradation of the motor) of the motor of the column-type electric power steering device based on the output (features) obtained by the abnormality detection model 30.

[0146] The above has described in detail the motor abnormality detection device 100 of a column type electric power steering device according to an embodiment of the present invention. Next, a motor abnormality detection method for a column type electric power steering device will be described.

[0147] Figure 7 The flowchart shows a method for detecting abnormality of a motor of a column type electric power steering device according to an embodiment of the present invention.

[0148] The motor abnormality detection method S100 of a column-type electric power steering device according to an embodiment of the present invention detects an abnormality of a motor 18 of a column-type electric power steering system configured in a vehicle. More specifically, the motor abnormality detection method S100 of a column-type electric power steering device can detect an abnormality of a motor configured in a column-type electric power steering system of a vehicle to provide a steering assist force to a steering column side.

[0149] Reference Figure 7 The motor abnormality detection method S100 of a column-type electric power steering device according to an embodiment of the present invention may be performed as follows.

[0150] First, the processor 120 inputs operation data associated with the driver's steering wheel operation and state data indicating the vehicle state into the artificial neural network model 20, and obtains the output estimation value of the motor output by the artificial neural network model (step S110).

[0151] The operation data may include at least one of a steering angle, a steering angular velocity, and a steering torque. In addition, the state data may include at least one of a speed of the vehicle, a lateral acceleration of the vehicle, a yaw rate of the vehicle, and a wheel speed of the vehicle.

[0152] For example, the operation data may include a steering angle, a steering angular velocity, and a steering torque, and the state data may include a speed of the vehicle, a lateral acceleration of the vehicle, a yaw rate of the vehicle, and a wheel speed of the vehicle.

[0153] 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 neural twin model based on deep learning of a column-type electric power steering system of a vehicle.

[0154] The artificial neural network model 20 may include a generator 21 and a discriminator 22. The generator 21 receives the operation data and the state data to generate the inference value. The generator 21 may be composed of a multivariate transformer. In addition, the discriminator 22 receives the measurement data including the operation data, the state data and the measurement value, and outputs a discriminator value for the measurement data.

[0155] In the step S110 of acquiring the estimated value of the physical quantity, the processor 120 may input the operation data and the state data into the generator 21 , and acquire the estimated value generated by the generator 21 .

[0156] In addition, the artificial neural network model 20 is constructed by performing learning by the generator 21 and the discriminator 22, and the data used in the learning can be obtained when the motor 18 of the column electric power steering system 10 is in a normal state. Thus, the estimated value can track the motor output measurement value obtained when the motor 18 is in a normal state.

[0157] Next, the processor 120 detects whether the motor 18 is abnormal by comparing the estimated value with the measured value (step S120 ).

[0158] The processor 120 can input the error data associated with the difference between the estimated value and the measured value into the abnormality detection model 30 by executing one or more instructions, so as to determine whether the motor 18 is abnormal. For example, the abnormality detection model 30 can use a one-class support vector machine (OCSVM) algorithm.

[0159] Figure 8 The present invention is a detailed flowchart showing the steps of detecting whether a motor is abnormal in a method for detecting abnormality of a motor of a column-type electric power steering device according to an embodiment of the present invention.

[0160] Reference Figure 8 , step S120 of detecting whether the motor is abnormal or not can be performed as described below.

[0161] First, the processor 120 inputs the measurement data including the operation data, the state data, and the output measurement value of the motor to the discriminator 22, and obtains the discrimination value generated by the discriminator 22 for the measurement data (step S121).

[0162] Next, the processor 120 inputs the discrimination value for the measurement data and the error data including the numerical value associated with the difference between the inferred value and the measurement value into the abnormality detection model 30 and obtains the output of the abnormality detection model 30 (step S122 ).

[0163] There may be multiple data sets including the input data, the measured values, and the inferred values. The error data may include the average and standard error of the error between the measured values ​​and the inferred values ​​obtained from each of the multiple data sets, the maximum absolute error between the measured values ​​and the inferred values ​​of the multiple data sets, and the discriminator's ...

[0164] In more detail, a plurality of data sets including the measured values ​​and the estimated values ​​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 may be acquired for each batch.

[0165] The error data acquired for one batch may be input to the abnormality detection model 30. In addition, the degree of abnormality (performance reduction of the motor) of the motor may be detected based on the output (feature) acquired from the abnormality detection model 30 receiving the error data.

[0166] Regarding the anomaly detection metric, the F1 score as described above may be considered.

[0167] In addition, the present invention additionally provides a non-transitory computer-readable storage medium storing a program for executing the motor abnormality detection method of the column-type electric power steering device. More specifically, the present invention may provide a non-transitory computer-readable storage medium storing a program including at least one instruction for executing the motor abnormality detection method of the column-type electric power steering device.

[0168] At this time, the instructions may include not only the machine code generated by the compiler, but also the high-level language code executable by the computer.

[0169] The recording medium may also include 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) and digital video disk (DVD), magneto-optical media (Magneto-Optical Media) such as floppy disks, hardware devices such as read-only memory (ROM), random access memory (RAM), flash memory, etc., which are constructed in a manner of storing and executing program instructions.

[0170] The simulation execution structure shows that according to the present invention, the maximum output comparison of the motor of the EPS system can be predicted by using the performance of the F1 score of 0.85 or more. In other words, according to the present invention, the deterioration level of the motor configured in the column-type electric power steering system of the vehicle can be accurately predicted before the motor completely fails.

[0171] According to the present invention, it is possible to predict in advance before a motor failure of a column-type electric power steering device occurs, thereby enabling advance measures to be taken before the motor fails, thereby preventing the motor failure and the danger caused by the failure.

[0172] Thus, the present invention provides prediction of future behavior and remaining useful life of the system and predictive diagnosis suitable for predictive maintenance and repair applications, thereby effectively guiding advance measures and repairs before the motor of the vehicle's column-type electric power steering fails.

[0173] Although the embodiments of the present invention have been described, the technical concept of the present invention is not limited to the embodiments presented in this specification, and those skilled in the art who understand the technical concept of the present invention can easily propose other embodiments within the scope of the same technical concept by adding, changing, deleting, adding, etc. to the constituent elements. However, this will also be considered to fall within the scope of the present invention.

Claims

1. A motor abnormality detection device for a column-type electric power steering device, used for detecting abnormality of a motor of a column-type electric power steering device that provides auxiliary steering force to a steering column of an electric power steering system of a vehicle, characterized in that: include: memory, storing one or more instructions, and A processor, executing the one or more instructions; The processor inputs operation data associated with the steering wheel operation of the driver of the vehicle and status data representing the status of the vehicle into the artificial neural network model by executing the one or more instructions, obtains the output estimated value of the motor output by the artificial neural network model, and detects whether the motor is abnormal by comparing the output estimated value with the output measurement value of the motor.

2. The motor abnormality detection device for a column-type electric power steering device according to claim 1, wherein: The operation data includes one or more of a steering angle, a steering angular velocity, and a steering torque.

3. The motor abnormality detection device for a column-type electric power steering device according to claim 1, wherein: The state data includes one or more of a speed of the vehicle, a lateral acceleration of the vehicle, a yaw rate of the vehicle, and a wheel speed of the vehicle.

4. The motor abnormality detection device for a column-type electric power steering device according to claim 1, wherein: The operating data and the status data are constituted by signals that can be acquired via a controller area network of the vehicle.

5. The motor abnormality detection device for a column-type electric power steering device according to claim 1, wherein: The artificial neural network model comprises: A generative adversarial network includes a generator that receives the operation data and the state data to generate the output speculation value.

6. The motor abnormality detection device for a column type electric power steering device according to claim 5, wherein: The artificial neural network model also includes: A discriminator receives measurement data including the operation data, the state data, and the output measurement value, and outputs a discrimination value for the measurement data.

7. The motor abnormality detection device for a column type electric power steering device according to claim 6, wherein: The processor inputs error data associated with a difference between the output estimated value and the output measured value into an abnormality detection model by executing the one or more instructions to determine whether the motor has an abnormality.

8. The motor abnormality detection device for a column-type electric power steering device according to claim 7, wherein: There are a plurality of data sets including the operation data, the status data, the output measurement value, and the output inference value, The error data includes the average and standard error of the errors between the measured values ​​and the inferred values ​​obtained from each of the plurality of data sets, the maximum absolute error between the measured values ​​and the inferred values ​​of the plurality of data sets, and the identification value of the discriminator for the measured data of the plurality of data sets.

9. A method for detecting abnormality of a motor of a column-type electric power steering device, for detecting abnormality of a motor of a column-type electric power steering device that provides auxiliary steering force to a steering column of an electric power steering system of a vehicle, characterized in that: include: A step of inputting operation data associated with a steering wheel operation of a driver of the vehicle and state data indicating a state of the vehicle into an artificial neural network model by a processor, and acquiring an output estimation value of the motor output by the artificial neural network model; as well as The processor detects whether the motor has an abnormality by comparing the estimated output value with an output measurement value of the motor.

10. The method for detecting motor abnormality of a column-type electric power steering device according to claim 9, wherein: The operation data includes one or more of a steering angle, a steering angular velocity, and a steering torque.

11. The method for detecting motor abnormality of a column-type electric power steering device according to claim 9, wherein: The state data includes one or more of a speed of the vehicle, a lateral acceleration of the vehicle, a yaw rate of the vehicle, and a wheel speed of the vehicle.

12. The method for detecting motor abnormality of a column-type electric power steering device according to claim 9, wherein: The artificial neural network model is composed of a generative adversarial network. The generative adversarial network comprises: a generator, receiving the operation data and the state data to generate the output speculation value, A discriminator receives measurement data including the operation data, the state data, and the output measurement value, and outputs a discrimination value for the measurement data.

13. The method for detecting motor abnormality of a column-type electric power steering device according to claim 12, wherein: In the step of acquiring the output presumed value, the processor inputs the operation data and the status data to the generator, and acquires the presumed value generated by the generator.

14. The method for detecting motor abnormality of a column-type electric power steering device according to claim 13, wherein: The step of detecting whether the motor is abnormal comprises: the processor inputting measurement data including the operation data, the state data and the output measurement value into the discriminator, and obtaining a discriminator value for the measurement data generated by the discriminator, and The processor inputs a discrimination value for the measurement data and error data including a numerical value associated with a difference between the output estimated value and the output measured value into an abnormality detection model and acquires an output of the abnormality detection model.

15. A non-transitory computer-readable storage medium, wherein: A program including at least one instruction for executing the motor abnormality detection method for a column-type electric power steering device according to any one of claims 9 to 14 is stored.

Images