Steering Motor Abnormality Detection Without Added Sensors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Steering motors in steer-by-wire systems experience performance degradation due to demagnetization, leading to reduced output torque and potential steering errors, which can cause accidents, necessitating a proactive detection method without additional sensors.
Innovation Solution
A steering motor abnormality detection device using an artificial neural network model, specifically a generative adversarial network (GAN) with a multivariate transformer, compares input values related to rack propulsive force with actual measurement values to detect abnormalities, employing a one-class support vector machine (OCSVM) algorithm for predictive maintenance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If additional sensors are installed to detect steering motor abnormalities, then detection accuracy is improved, but device complexity and cost increase
Solution Approach 1:
The steering motor abnormality detection device utilizes data from existing sensors already present in the steer-by-wire system to detect motor abnormalities. The system performs self-diagnosis by analyzing relationships between steering wheel angle, steering torque, and motor current without requiring additional sensors, thereby maintaining detection accuracy while avoiding increased device complexity
Solution Approach 2:
The detection device uses existing sensors that serve multiple functions in the steer-by-wire system for abnormality detection purposes. The steering wheel angle sensor and steering torque sensor, originally designed for normal steering operation, are also utilized to detect motor abnormalities, making the system multi-functional without adding dedicated detection sensors
2Reliability
If post-diagnosis of motor failure is performed, then diagnostic simplicity is maintained, but system reliability and safety decrease
Solution Approach 1:
The system performs preliminary detection of steering motor abnormalities by continuously analyzing the relationship between steering wheel angle, steering torque, and motor current during normal operation. This allows early identification of performance degradation trends before complete failure occurs, enabling proactive maintenance and improving system reliability
Solution Approach 2:
The detection device implements a feedback mechanism that continuously monitors steering parameters and compares actual values with expected values based on the relationship model. When deviations indicate abnormality, the system provides feedback alerts, enabling timely intervention while maintaining overall system simplicity
Data Source
AI summary
Disclosed are a steering 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 steering motor abnormality detection device 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 an input value related to driving of a rack to an artificial neural network model, 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 the 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.