Steer-by-Wire Motor Abnormality Detection via Neural Network Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing steer-by-wire systems in vehicles face challenges in detecting output torque reduction of wheel actuating motors due to demagnetization or degradation, which can lead to steering errors and accidents.
Innovation Solution
A wheel actuating motor abnormality detection device and method that utilizes an artificial neural network model, specifically a generative adversarial network (GAN), to detect performance degradation of the wheel actuating motor by comparing estimation data with actual measurement data without requiring additional sensors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional sensor-based detection methods are used, then abnormality detection capability is limited, but additional sensors increase device complexity and cost
Solution Approach 1:
The patent creates a virtual model (digital twin) of the wheel actuating motor that replicates its normal operational characteristics. This virtual model generates expected parameter values under various operating conditions, which are then compared against actual sensor readings to detect abnormalities. This approach enhances detection capability without adding physical sensors to the motor itself.
Solution Approach 2:
The patent introduces an artificial intelligence model as an intermediary between the physical motor and the detection system. This AI model processes existing sensor data and predicts motor behavior, acting as a mediator that transforms ordinary operational data into actionable diagnostic information, thereby improving detection precision without direct modification to the motor hardware.
2Measurement precision
If additional sensors are installed to detect output torque reduction, then detection accuracy improves, but device complexity and cost increase
Solution Approach 1:
The patent creates a virtual model (digital twin) of the wheel actuating motor that replicates its normal operational characteristics. This virtual model generates expected parameter values under various operating conditions, which are then compared against actual sensor readings to detect abnormalities. This approach enhances detection capability without adding physical sensors to the motor itself.
Solution Approach 2:
The patent replaces direct mechanical measurement of output torque with an intelligent estimation system. Instead of using physical torque sensors that would add complexity, the system uses AI algorithms to estimate torque based on electrical parameters and operational data, substituting a mechanical measurement approach with an information-processing approach.
3Loss of time
If post-diagnosis of motor failure is performed, then response time is delayed, but real-time monitoring increases system complexity
Solution Approach 1:
The patent performs preliminary diagnostic actions by continuously comparing actual motor parameters against the virtual model's predictions during normal operation. This allows the system to detect deviations and predict potential failures before they occur, enabling proactive maintenance and reducing response time without requiring complex real-time intervention systems.
Solution Approach 2:
The patent implements a feedback mechanism where the AI model continuously monitors motor performance and compares it against expected behavior from the virtual model. This closed-loop feedback system provides real-time diagnostic information, allowing the system to detect and respond to abnormalities as they develop, significantly reducing the time loss associated with post-failure diagnosis.
Data Source
AI summary
Disclosed are a wheel actuating motor abnormality detection device and method and a non-transitory computer-readable storage medium in which a program for performing the method is stored. The wheel actuating motor abnormality detection device detects abnormality of a steering motor disposed in a steer-by-wire system of a vehicle and configured to provide a reaction force against manipulation of a steering wheel, and includes a memory in which one or more instructions are stored and a processor configured to execute the one or more instructions, wherein the processor executes the one or more instructions to input input value related to driving of a rack, obtain one or more estimation values related to steering output by the artificial neural network model, and compare the one or more estimation values with one or more actual measurement values related to steering to detect whether the steering motor is abnormal, wherein the rack receives a driving force from a wheel actuator driven to correspond to the manipulation of the steering wheel and moves a wheel of the vehicle.