Steering control apparatus and method

Abstract

The present disclosure relates to a steering control device and a method. Specifically, the steering control device according to the present disclosure includes an information acquisition unit that acquires raw data sensed from a plurality of sensors, a control unit that selects sensor data necessary for diagnosing the state of a specific device or specific part of a vehicle among the raw data, inputs at least one selected sensor data into a machine learning-based first state diagnosis model and a second state diagnosis model to derive respective state characteristic data for the specific device or specific part, and generates a diagnosis result for the specific device or specific part based on each state characteristic data.

Description

Technology Field

[0001] The present embodiments relate to a steering control device and method that assists a driver in steering. Background Technology

[0002] An automobile contains various parts, including consumables, as well as devices or systems implemented by these components. To manage a vehicle where these parts, devices, and systems must operate in a complex and organic manner, mechanics at a repair shop must individually inspect the condition of every single part. Consequently, this presents the disadvantage of being time-consuming and increasing maintenance costs.

[0003] Conventional vehicle management technologies include, for example, technology that detects the remaining fuel level or engine temperature through the vehicle's dashboard to indicate whether there is an engine malfunction, or technology that displays whether the airbag can operate normally.

[0004] However, most of these existing diagnostic technologies remain simple monitoring systems based on threshold comparisons, which makes them sensitive to sensor noise or changes in the external environment (temperature, humidity, road conditions, etc.) and poses a problem in that it is difficult to accurately determine actual component performance degradation or potential failures.

[0005] Furthermore, since most existing vehicle diagnostics are performed based on data collected at each maintenance interval, there are limitations in that it is difficult to monitor the condition of parts in real-time or immediately identify signs of abnormalities while the vehicle is in operation. Consequently, post-maintenance is common, with measures taken only after signs of failure occur; this approach can lead to increased accident risks and unnecessary maintenance costs. The problem to be solved

[0006] Against this backdrop, the present disclosure aims to provide a steering control device and method that acquire sensor data from sensors mounted on a vehicle in real time, perform a diagnosis of a specific device or specific part based thereon, and generate a control signal based on the diagnosis result. means of solving the problem

[0007] In order to solve the aforementioned problem, in one aspect, the present disclosure provides a steering control device comprising: an information acquisition unit that acquires raw data sensed from a plurality of sensors; a control unit that selects sensor data necessary for diagnosing the state of a specific device or specific part of a vehicle among the raw data, inputs at least one selected sensor data into a machine learning-based first state diagnosis model and a second state diagnosis model to derive respective state characteristic data for the specific device or specific part, and generates a diagnosis result for the specific device or specific part based on each state characteristic data.

[0008] In another aspect, the present disclosure provides a steering control method comprising: an information acquisition step of acquiring raw data sensed from a plurality of sensors; a data selection step of selecting sensor data necessary for diagnosing the state of a specific device or specific part of a vehicle among the raw data; and a diagnosis result generation step of inputting at least one selected sensor data into a machine learning-based first state diagnosis model and a second state diagnosis model to derive respective state characteristic data for the specific device or specific part, and generating a diagnosis result for the specific device or specific part based on each state characteristic data. Effects of the invention

[0009] As described above, according to the present disclosure, a steering control device and method can obtain an accurate sensor signal by removing noise through adaptive filtering.

[0010] In addition, the present disclosure can more accurately determine both short-term anomalies and long-term patterns by using a combination of Random Forest, a traditional machine learning technique, and LSTM, a deep learning technique.

[0011] In addition, the present disclosure can provide the user with information on the replacement time and the cause of part failure based on predicted lifespan data.

[0012] In addition, the present disclosure can automatically update model accuracy through data retraining linked to a cloud where vehicle sensor data is stored. Brief explanation of the drawing

[0013] FIG. 1 is a block diagram schematically illustrating a steering control system according to one embodiment. FIG. 2 is a block diagram for briefly explaining a steering control device according to one embodiment of the present disclosure. FIG. 3 is a block diagram of a steering control device according to another embodiment. FIG. 4 is a flowchart illustrating a steering control method according to one embodiment of the present disclosure. FIG. 5 is a drawing for explaining step S420 according to one embodiment in more detail. FIG. 6 is a flowchart illustrating the generation of a diagnostic result according to one embodiment. Specific details for implementing the invention

[0014] Hereinafter, some embodiments of the present disclosure will be described in detail with reference to the exemplary drawings. In assigning reference numerals to the components of each drawing, the same components may have the same reference numeral as much as possible, even if they are shown in different drawings. Furthermore, in describing the embodiments, if it is determined that a detailed description of related known components or functions may obscure the essence of the technical concept, such detailed description may be omitted. Where terms such as "comprising," "having," or "consisting of" are used in this specification, other parts may be added unless "only" is used. Where a component is expressed in the singular, it may include a plural unless otherwise specified.

[0015] Additionally, terms such as first, second, A, B, (a), (b), etc., may be used to describe the components of the present disclosure. These terms are used merely to distinguish the components from other components, and the nature, order, sequence, or number of the components are not limited by such terms.

[0016] In describing the positional relationship of components, where it is stated that two or more components are "connected," "combined," or "joined," it should be understood that while the two or more components may be directly "connected," "combined," or "joined," they may also be "connected," "combined," or "joined" with other components "intervened." Here, the other components may be included in one or more of the two or more components that are "connected," "combined," or "joined" with one another.

[0017] In describing the temporal flow relationship regarding components, methods of operation, or methods of production, for example, when the temporal or sequential relationship is described using "after," "following," "next," or "before," it may include cases where the relationship is not continuous unless "immediately" or "directly" is used.

[0018] Meanwhile, where numerical values ​​or corresponding information regarding a component (e.g., levels, etc.) are mentioned, even without separate explicit notation, the numerical values ​​or corresponding information may be interpreted as including a range of error that may occur due to various factors (e.g., process factors, internal or external shocks, noise, etc.).

[0019] Hereinafter, a steering control system (1) according to one embodiment will be described with reference to the attached drawings.

[0020] FIG. 1 is a block diagram schematically showing a steering control system (1) according to one embodiment.

[0021] Referring to FIG. 1, a steering control system (1) according to one embodiment may include a steering control device (10), an SFA (Steering Feedback Actuator) (20) and an RWA (Road Wheel Actuator) (30), etc.

[0022] A steering control system (1) according to one embodiment may mean a system that controls the steering of a vehicle equipped with the steering control system (1) to change according to the steering angle of the steering wheel (21) operated by the driver.

[0023] This steering control system (1) may be a Steer-by-Wire (SbW) system that transmits power by transmitting and receiving electrical signals through wires, cables, etc., in a mechanical connection member (or linkage) between a steering input actuator and a steering output actuator. Below, the steering control system (1) is described based on an SbW system, but is not limited thereto.

[0024] The steering control system (1) can determine the final steering direction of the vehicle based on steering information input by the sensor and steering module mounted in the SFA (20) and output a command current to the RWA (30) so that the vehicle is steered in the steering direction.

[0025] As described above, if the steering control system (1) is an SbW system, the SFA (20) and RWA (30) can be mechanically separated.

[0026] SFA (20) may refer to a device that inputs steering information intended by the driver. As described above, this SFA (20) may include a steering wheel (21), a steering shaft (22), and a reaction motor (23). Additionally, although not illustrated, it may further include a steering gear that transmits the rotational force of the reaction motor (23) to the steering shaft (22).

[0027] The steering wheel (21) can rotate between the left steering lock section and the right steering lock section with the steering shaft (22) as the axis of rotation. Here, the lock section may refer to the limit point at which the steering wheel can move. The lock section may be composed of a steering damper, etc.

[0028] The reaction motor (23) can receive a control signal (or command current) from the steering control device (10) and provide feedback torque to the steering wheel (21). In one embodiment, the reaction motor (23) receives a command current from the steering control device (10), drives at a rotational speed indicated by the command current to generate feedback torque, and can transmit the feedback torque to the steering wheel (21) through a worm and a worm wheel.

[0029] SFA (20) may include a steering angle sensor that detects the steering angle of the steering wheel, a torque sensor that detects the driver torque, a current sensor that detects the current of the reaction force motor (23), and a steering angle velocity sensor that detects the steering angle velocity of the steering wheel.

[0030] The steering control device (10) receives steering information from each sensor included in the SFA (20), calculates a control value, and outputs an electrical signal indicating the control value to the RWA (30). Here, the steering information may refer to information including at least one of the steering angle, steering angle velocity, and driver torque.

[0031] Meanwhile, the steering control device (10) receives feedback on actual power information (e.g., rack position information) output from the RWA (30), calculates a control value, and outputs an electrical signal indicating the control value to the SFA (20) to provide steering sensation to the driver.

[0032] RWA (30) may refer to a device that drives the actual vehicle to steer. This RWA (30) may include a steering motor (31), a rack (32), a wheel (33), a vehicle speed sensor, a rack position sensor, etc.

[0033] And, SFA (20) and RWA (30) may further include a motor torque sensor capable of detecting the motor torque of the reaction motor (23) and the steering motor (31).

[0034] The steering motor (31) can move the rack (32) in the axial direction. Specifically, the steering motor (31) is driven by receiving a command current from the steering control device (10) and can cause the rack (32) to move linearly in the axial direction. That is, the rack (32) can move linearly between the left lock end, which is the left movement limit point, and the right lock end, which is the right movement limit point.

[0035] The rack (32) can perform linear motion by driving the steering motor (31), and the wheel (33) can be steered left or right through the linear motion of the first rack (32).

[0036] Although not illustrated, the steering control system (1) may further include a clutch capable of separating or combining the SFA (20) and RWA (30), a reaction motor (23), a PCB board of the steering control device (10), and respective temperature sensors capable of detecting the temperature of the steering motor (31). Here, the clutch operates under the control of the steering control device (10), and the steering control device (10) can acquire sensor data from each temperature sensor.

[0037] FIG. 2 is a block diagram for briefly explaining a steering control device (10) according to one embodiment of the present disclosure.

[0038] Referring to FIG. 2, the steering control device (10) of the present disclosure may include an information acquisition unit (110) and a control unit (120), etc.

[0039] The steering control device (10) can acquire raw data sensed from a plurality of sensors, select sensor data required for diagnosing the state of a specific device or specific part of a vehicle among the raw data, input at least one selected sensor data into a machine learning-based first state diagnosis model and a second state diagnosis model to derive respective state characteristic data for a specific device or specific part, and generate a diagnosis result for a specific device or specific part based on each state characteristic data.

[0040] The information acquisition unit (110) can acquire raw data sensed from a plurality of sensors mounted on the vehicle.

[0041] Raw data is unprocessed raw data measured by each sensor and can be used as a basic input value to diagnose the condition of a vehicle's parts or devices. Raw data may include sensor data sensed by multiple sensors. The multiple sensors may include temperature sensors, steering angle sensors, torque sensors, wheel steering angle sensors, and current sensors.

[0042] The information acquisition unit (110) can acquire raw data in real time, and for example, the information acquisition unit (110) can acquire steering torque, steering angle, device temperature, and current data that are periodically sampled (at intervals of 1ms to 10ms).

[0043] The information acquisition unit (110) can transmit and receive data with each component of the vehicle using communication protocols such as CAN (Controller Area Network), LIN (Local Interface Network), FlexRay, MOST (Media Oriented Systems Transport), and Ethernet.

[0044] The control unit (120) can select sensor data required for diagnosing the state of a specific device or specific part of a vehicle from among raw data, input at least one selected sensor data into a machine learning-based first state diagnosis model and a second state diagnosis model to derive respective state characteristic data for the specific device or specific part, and generate a diagnosis result for the specific device or specific part based on each state characteristic data.

[0045] The control unit (120) can identify sensor data that is highly relevant to the device to be diagnosed among the acquired raw data and selectively extract them.

[0046] When diagnosing the state of the steering control system (1), the control unit (120) can select data such as steering input torque, steering angle, motor current, and motor temperature from raw data obtained from the steering torque sensor, angle sensor, current sensor, temperature sensor, etc., and when diagnosing the state of the brake system, it can selectively classify data such as brake pedal stroke, master cylinder pressure, and vehicle deceleration.

[0047] For example, the control unit (120) can reduce data throughput and improve computational efficiency by referring to a predetermined data mapping table or algorithm for each diagnostic target to extract only the necessary sensor data and excluding sensor data that has low correlation or is unnecessary for diagnosis.

[0048] As another example, the control unit (120) can select sensor data effective for diagnosing the condition of a specific device or specific part of a vehicle by utilizing a feature extraction technique.

[0049] Specifically, the control unit (120) may apply feature extraction algorithms such as PCA (Principal Component Analysis), CCA (Canonical Correlation Analysis), and LDA (Linear Discriminant Analysis) to identify sensor data that has a high correlation with the device to be diagnosed among the raw data obtained through the interface unit of the vehicle. These algorithms can analyze the statistical correlation or principal components between sensor data to prioritize the selection of sensor data that contributes significantly to diagnosis and automatically exclude unnecessary or duplicate data.

[0050] For example, the control unit (120) can prioritize selecting steering angle and current data that have a high contribution from PCA analysis results among a number of sensor data such as steering torque, steering angle, current, and temperature.

[0051] The control unit (120) can select sensor data based on whether an event trigger occurs for a specific device or a specific part.

[0052] Specifically, the control unit (120) monitors raw data collected from a plurality of sensors in real time and may be configured to prioritize the selection of sensor data related to the trigger when an event trigger occurs in a specific device or specific part. Here, an event trigger may refer to a situation in which a change occurs in the state of the device or part to be diagnosed or a specific threshold condition is exceeded.

[0053] For example, the control unit (120) can determine that an event trigger has occurred when the temperature of a specific device or a specific part is above a reference value.

[0054] As another example, the control unit (120) may determine that an event trigger has occurred when it detects that the current is increasing rapidly.

[0055] As another example, the control unit (120) can determine that an event trigger has occurred when the steering torque increases rapidly in the rate of change of the steering angle.

[0056] The control unit (120) can select sensor data acquired over a predetermined period. Additionally, the control unit (120) can perform pattern analysis-based diagnosis using the aforementioned sensor data. For example, the information acquisition unit (110) can store sensor data for the past 30 days inside the steering control device (10) or use AWS IoT Core or Microsoft Azure to transmit fault logs and long-term data to the cloud.

[0057] As described above, the control unit (120) can detect abnormal changes in sensor data over time and generate a diagnosis result accordingly.

[0058] To this end, the information acquisition unit (110) may store raw data for a predetermined period. Additionally, the information acquisition unit (110) may store the aforementioned raw data on an external server connected via a network, and if necessary, the control unit (120) may refer to the raw data on the external server.

[0059] Additionally, the information acquisition unit (110) may be configured to include a communication module and a memory to implement the transmission and storage of raw data.

[0060] Vehicle operating environments are prone to generating irregular noise in sensor signals due to various factors such as vibration, electromagnetic interference (EMI), and temperature fluctuations. If this noise is input into diagnostic algorithms or machine learning models without being removed, it leads to a decrease in diagnostic accuracy.

[0061] Accordingly, in order to improve the signal quality of sensor data in the present disclosure, the control unit (120) can remove sensor noise by applying a predetermined algorithm to the selected sensor data.

[0062] Specifically, the control unit (120) may apply an adaptive filtering method to the sensor data. A predetermined algorithm may include, for example, at least one of a Kalman filter and a wavelet transform. Additionally, the control unit (120) may remove noise from the sensor data by combining the Kalman filter and the wavelet transform.

[0063] As described above, the control unit (120) of the present disclosure can stably correct a signal containing noise by adjusting filter coefficients in real time to minimize the error between the output signal of the sensor and the predicted signal.

[0064] The control unit (120) can precisely determine the state of a specific device or specific part by operating a plurality of state diagnosis models in parallel using at least one selected sensor data.

[0065] Specifically, the control unit (120) can input selected sensor data into a machine learning-based first state diagnosis model and a second state diagnosis model, respectively.

[0066] For example, the first state diagnosis model may be a machine learning model trained with deep learning techniques, and the second state diagnosis model may be a machine learning model trained with random forest techniques.

[0067] The control unit (120) can derive state characteristic data based on the statistical characteristics of sensor data using a traditional machine learning algorithm, and can derive state characteristic data reflecting pattern changes over time using a deep learning-based time series learning model such as LSTM (Long Short-Term Memory) or CNN (Convolutional Neural Network).

[0068] The control unit (120) can generate a comprehensive diagnosis result of a specific device or specific part by comparing and correcting each state feature data derived from the first state diagnosis model and the second state diagnosis model.

[0069] Here, the diagnostic results may include whether a specific device or specific part is faulty, predictive maintenance, and recommended response measures. For example, the diagnostic results may perform real-time automatic diagnosis and, as a result, issue an error alarm, recommend visiting a service center, or perform an OTA update.

[0070] As another example, the diagnostic result may be calculated in the form of a judgment value regarding normal or abnormal, a probability of anomaly occurring, or a predicted value of remaining useful life (RUL).

[0071] The control unit (120) may assign weights based on the output reliability of the first state diagnosis model and the second state diagnosis model, or combine the two results to generate a final judgment value. For example, in situations where real-time performance (inference speed) is required, the results of the first state diagnosis model may be reflected first, and in the precise analysis stage, the results of the second state diagnosis model may be additionally considered to improve the accuracy of fault prediction.

[0072] As described above, the steering control device (10) of the present disclosure can reduce the possibility of misdiagnosis of a single model and simultaneously reflect the statistical characteristics and temporal patterns of sensor data, thereby enabling more reliable diagnosis of the condition of a vehicle part or device. The diagnosis result can be stored on an external server.

[0073] The steering control device (10) may further include an output unit that visualizes and outputs the diagnostic results so that the driver can recognize them. The output unit receives a control signal from the control unit (120) and can output the diagnostic results, key data, user feedback, and diagnostic report corresponding to the control signal to a display. Here, the key data may include, for example, a graph of temperature, current, and steering angle change, and a status indication (normal, caution, faulty state) of the device or part to be diagnosed. User feedback may include, for example, a detailed notification message such as 'Use restricted for 2 minutes due to motor overheating'. The diagnostic report may include an error code such as 'DTC XXXXX', a diagnostic code and cause when a fault occurs such as motor overheating or the need to check the cooling system, and may include a periodic system status report such as 'Average steering temperature over the past month: 65℃. No abnormalities'.

[0074] In one embodiment, the steering control device (10) may be implemented as a microcomputer or an ECU (Electric Controller Unit).

[0075] FIG. 3 is a block diagram of a steering control device (10) according to another embodiment.

[0076] The embodiments of the present invention described above may be implemented in a computer system, for example, on a computer-readable recording medium. Referring to FIG. 3, a computer system (300), such as a steering control device (10), may include at least one element among one or more processors (310), memory (320), storage unit (330), user interface input unit (340), and user interface output unit (350), and these may communicate with each other via a bus (360). Additionally, the computer system (300) may also include a network interface (370) for connecting to a network. The processor (310) may be a CPU or a semiconductor device that executes processing instructions stored in the memory (320) and / or storage unit (330). The memory (320) and storage unit (330) may include various types of volatile / non-volatile memory media. For example, the memory may include ROM (324) and RAM (325).

[0077] Hereinafter, a steering control method using a steering control device (10) capable of performing all of the above-described disclosures will be described.

[0078] FIG. 4 is a flowchart illustrating a steering control method according to one embodiment of the present disclosure.

[0079] Referring to FIG. 4, a steering control method according to one embodiment of the present disclosure may include an information acquisition step (S410) for acquiring raw data sensed from a plurality of sensors, a data selection step (S420) for selecting sensor data necessary for diagnosing the state of a specific device or specific part of a vehicle among the raw data, and a diagnosis result generation step (S430) for inputting at least one selected sensor data into a machine learning-based first state diagnosis model and a second state diagnosis model to derive state characteristic data for each specific device or specific part, and generating a diagnosis result for the specific device or specific part based on each state characteristic data.

[0080] The information acquisition step (S410) stores raw data for a predetermined period, and the data selection step (S420) can select sensor data acquired for a predetermined period.

[0081] The data selection step (S420) can select sensor data based on whether an event trigger occurs for a specific device or a specific part.

[0082] The data selection step (S420) can determine that an event trigger has occurred if the temperature of a specific device or a specific part is above a reference value.

[0083] The diagnostic result generation step (S430) can remove sensor noise by applying a predetermined algorithm to the selected sensor data. The predetermined algorithm may include at least one of a Kalman filter and a wavelet transform.

[0084] The first state diagnosis model is a machine learning model trained with deep learning techniques, and the second state diagnosis model may be a machine learning model trained with random forest techniques.

[0085] In one embodiment, the state characteristic data may not be merely the instantaneous value of a physical quantity measured by a sensor, but may be data that quantifies the current state, performance level, and degree of degradation of the device or component by reflecting the statistical characteristics, temporal patterns, and cross-correlation of the sensor data.

[0086] Specifically, state characteristic data may not be a simple physical quantity extracted from sensor data, but rather a high-dimensional feature vector that quantitatively expresses the state, degree of performance degradation, abnormal behavior characteristics, etc. of a specific device as a result of learning by a machine learning or deep learning model.

[0087] Here, the first state diagnosis model uses traditional machine learning algorithms such as Random Forest or Support Vector Machine (SVM) to analyze the correlation and statistical distribution characteristics between sensor data and can output statistically based state characteristic data that reflects whether a specific device is abnormal.

[0088] The second state diagnosis model learns the temporal patterns and change trends of time-series sensor data using deep learning algorithms such as LSTM (Long Short-Term Memory) or CNN (Convolutional Neural Network), and can output time-series-based state characteristic data that reflects signs of deterioration or failure of a specific device.

[0089] These two models independently generate state characteristic data representing the state of the corresponding component or device based on different analysis criteria (statistical / time-series perspectives), and each data point can output the state of a specific device in numerical or vector form as a result derived from the output layer of the model.

[0090] The diagnosis result generation step (S430) can generate a final diagnosis result of a specific device or specific part by mutually comparing, correcting, or weighting and combining multiple state characteristic data derived from the first state diagnosis model and the second state diagnosis model.

[0091] Accordingly, the diagnostic results may include whether a specific device or specific part is faulty, predictive maintenance, and recommended response measures.

[0092] FIG. 5 is a drawing for explaining step S420 according to one embodiment in more detail.

[0093] Referring to FIG. 5, the steering control device (10) can determine whether an event trigger occurs for a specific device or a specific part (S510). The data selection step (S420) can select sensor data based on whether an event trigger occurs for a specific device or a specific part.

[0094] For example, the data selection step (S420) may determine that an event trigger has occurred if the temperature of a specific device or a specific part is above a reference value.

[0095] Accordingly, if it is determined that an event trigger has occurred in a specific device or specific part (Yes in S510), the steering control device (10) can select sensor data necessary for diagnosing the state of the specific device or specific part corresponding to the event trigger (S520).

[0096] FIG. 6 is a flowchart illustrating the generation of a diagnostic result according to one embodiment.

[0097] Referring to FIG. 6, the steering control device (10) can determine whether a failure has occurred in a specific device or a specific part (S610).

[0098] If it is determined that a specific device or specific part has failed (Yes in S610), the steering control device (10) may output a failure alarm for the specific device or specific part and recommend inspection (S620).

[0099] For example, a sudden change in torque value occurs during steering, and the steering control device (10) performs an error diagnosis of the sensor related thereto to determine whether it is faulty, and if it is determined to be faulty, information such as steering angle sensor mismatch along with an error code can be provided through an output device in the vehicle.

[0100] If no malfunction occurs (No of S610), the steering control device (10) can determine whether maintenance is required for a specific device or a specific part (S630).

[0101] If it is determined that maintenance is needed (Yes in S630), the steering control device (10) may provide a recommended inspection date for a specific device or specific part (S640).

[0102] For example, if the motor temperature is maintained at 10% higher than the average over the past three months, the steering control device (10) determines that maintenance is required, and if maintenance is required, the motor replacement time calculated by the fatigue prediction model can be provided as a recommended inspection date.

[0103] In the case where no maintenance is required (No of S630), the steering control device (10) can provide the current status of a specific device or specific part of the diagnostic target (S650).

[0104] As described above, according to the present disclosure, a steering control device and method can obtain an accurate sensor signal by removing noise through adaptive filtering.

[0105] In addition, the present disclosure can more accurately determine both short-term anomalies and long-term patterns by using a combination of Random Forest, a traditional machine learning technique, and LSTM, a deep learning technique.

[0106] In addition, the present disclosure can provide the user with information on the replacement time and the cause of part failure based on predicted lifespan data.

[0107] In addition, the present disclosure can automatically update model accuracy through data retraining linked to a cloud where vehicle sensor data is stored.

[0108] Meanwhile, the object recognition device and / or object recognition method according to the present disclosure may be implemented by a vehicle control device.

[0109] For example, a vehicle control unit may include at least one memory containing computer program instructions and at least one processor that executes computer program instructions. The vehicle control unit may be an electronic control unit including semiconductor elements, such as an ECU or an MCU.

[0110] Here, at least one processor can acquire raw data sensed from a plurality of sensors, select sensor data required for diagnosing the state of a specific device or specific part of a vehicle among the raw data, input at least one selected sensor data into a machine learning-based first state diagnosis model and a second state diagnosis model to derive respective state characteristic data for the specific device or specific part, and generate a diagnosis result for the specific device or specific part based on each state characteristic data.

[0111] In addition, at least one processor can remove sensor noise by applying a predetermined algorithm to selected sensor data.

[0112] In addition, at least one processor can select sensor data based on whether an event trigger occurs for a specific device or a specific part.

[0113] In addition, at least one processor can determine that an event trigger has occurred if the temperature of a specific device or a specific part is above a threshold.

[0114] The foregoing description is merely an illustrative explanation of the technical concept of the present disclosure, and those skilled in the art to which the present disclosure pertains may make various modifications and variations within the scope of the essential characteristics of the technical concept. Furthermore, since these embodiments are intended to explain, not limit, the scope of the technical concept is not limited by these embodiments. The scope of protection of the present disclosure shall be interpreted by the claims below, and all technical concepts within an equivalent scope shall be interpreted as being included within the scope of rights of the present disclosure.

Claims

Claim 1 A steering control device comprising: an information acquisition unit for acquiring raw data sensed from a plurality of sensors; and a control unit for selecting sensor data necessary for diagnosing the state of a specific device or specific part of a vehicle among the raw data, inputting at least one selected sensor data into a machine learning-based first state diagnosis model and a second state diagnosis model to derive respective state characteristic data for the specific device or specific part, and generating a diagnosis result for the specific device or specific part based on the respective state characteristic data. Claim 2 In claim 1, the control unit is a steering control device that removes sensor noise by applying a predetermined algorithm to the selected sensor data. Claim 3 In paragraph 2, the above-mentioned predetermined algorithm comprises at least one of a Kalman filter and a wavelet transform, a steering control device. Claim 4 A steering control device according to claim 1, wherein the first state diagnosis model is a machine learning model trained using a deep learning technique, and the second state diagnosis model is a machine learning model trained using a random forest technique. Claim 5 In claim 1, the control unit is a steering control device that selects sensor data based on whether an event trigger occurs of the specific device or the specific part. Claim 6 In paragraph 5, the control unit is a steering control device that determines that the event trigger has occurred when the temperature of the specific device or the specific part is above a reference value. Claim 7 A steering control device according to claim 1, wherein the information acquisition unit stores the raw data for a predetermined period, and the control unit selects sensor data acquired during the predetermined period. Claim 8 In claim 1, the diagnostic result includes whether the specific device or the specific part is faulty, predictive maintenance, and recommended response measures for the steering control device. Claim 9 A steering control method comprising: an information acquisition step of acquiring raw data sensed from a plurality of sensors; a data selection step of selecting sensor data necessary for diagnosing the state of a specific device or specific part of a vehicle among the raw data; and a diagnosis result generation step of inputting at least one selected sensor data into a machine learning-based first state diagnosis model and a second state diagnosis model to derive respective state characteristic data for the specific device or specific part, and generating a diagnosis result for the specific device or specific part based on the respective state characteristic data. Claim 10 In claim 9, the diagnostic result generation step is a steering control method that removes sensor noise by applying a predetermined algorithm to the selected sensor data. Claim 11 In claim 10, the above-mentioned predetermined algorithm is a steering control method comprising at least one of a Kalman filter and a wavelet transform. Claim 12 A steering control method according to claim 9, wherein the first state diagnosis model is a machine learning model trained using a deep learning technique, and the second state diagnosis model is a machine learning model trained using a random forest technique. Claim 13 In claim 9, the data selection step is a steering control method that selects sensor data based on whether an event trigger occurs of the specific device or the specific part. Claim 14 In claim 13, the data selection step is a steering control method that determines that the event trigger has occurred when the temperature of the specific device or the specific part is above a reference value. Claim 15 In claim 9, the information acquisition step stores the raw data for a predetermined period, and the data selection step selects sensor data acquired during the predetermined period, a steering control method. Claim 16 In claim 9, the above diagnostic result is a steering control method including whether the specific device or the specific part is faulty, predictive maintenance, and recommended response measures. Claim 17 A vehicle control device comprising: at least one memory including computer program instructions; and at least one processor executing said computer program instructions, wherein the at least one processor acquires raw data sensed from a plurality of sensors, selects sensor data necessary for diagnosing the state of a specific device or specific part of a vehicle among the raw data, inputs the selected at least one sensor data into a machine learning-based first state diagnosis model and a second state diagnosis model to derive respective state characteristic data for said specific device or specific part, and generates a diagnosis result for said specific device or specific part based on said state characteristic data. Claim 18 In claim 17, the above at least one processor is a vehicle control device that removes sensor noise by applying a predetermined algorithm to the selected sensor data. Claim 19 In claim 17, the above-mentioned at least one processor is a vehicle control device that selects sensor data based on whether an event trigger occurs of the above-mentioned specific device or the above-mentioned specific part. Claim 20 In claim 19, the above-mentioned at least one processor is a vehicle control device that determines that the event trigger has occurred when the temperature of the above-mentioned specific device or the above-mentioned specific part is above a reference value.

Images