Motor Electrical Signature Analysis for Mechanical Failure Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for predicting mechanical failures in electric motors of vehicles are costly and prone to false positives due to external noise interference, making it difficult to accurately identify impending failures without significant maintenance or sensor additions.
Innovation Solution
A method that generates motor electrical signatures from the characteristics of electrical energy supplied to the motors, compares fault measures across motors, and predicts mechanical failures based on these comparisons, using a system comprising an I/O module, signature generation module, and analysis module to identify impending failures without additional costly sensors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If additional sensors are added to detect motor failures, then detection capability is improved, but device complexity and cost increase
Solution Approach 1:
The patent replaces mechanical vibration sensors with electrical signature analysis. By monitoring electrical parameters (current, voltage, frequency) already present in the motor system and analyzing their spectral characteristics, the system detects bearing faults without adding mechanical sensors. This substitution maintains detection capability while reducing device complexity.
Solution Approach 2:
The patent creates an electrical signature (a type of copy or representation) of the motor's operational state through spectral analysis of electrical signals. This electrical signature serves as a proxy for mechanical conditions, allowing fault detection through electrical measurements rather than direct mechanical sensing, thereby avoiding additional hardware complexity.
2Reliability
If sensors are added to predict motor failure, then reliability is improved, but manufacturing cost increases
Solution Approach 1:
The motor system uses its own electrical signals for self-diagnosis. The electrical parameters generated during normal motor operation are analyzed to detect bearing faults, eliminating the need for separate sensing systems. This self-service approach improves reliability through failure prediction without increasing manufacturing costs, as it utilizes existing electrical infrastructure.
Solution Approach 2:
The patent substitutes expensive mechanical vibration sensing systems with electrical signature analysis using readily available electrical measurements. This replacement maintains or improves failure prediction accuracy while significantly reducing manufacturing costs by avoiding additional sensor hardware and associated installation complexities.
3Measurement precision
If vibration-based sensors are used to detect bearing faults, then detection capability is improved, but false positive rate increases due to external noise
Solution Approach 1:
The patent replaces vibration-based detection (which is susceptible to external mechanical noise from tracks and uneven surfaces) with electrical signature analysis. Electrical signals generated by the motor itself are used to detect bearing faults, making the system immune to external mechanical disturbances. This substitution maintains fault detection accuracy while eliminating false positives caused by environmental noise.
Solution Approach 2:
The patent introduces electrical spectral analysis as an intermediary between the motor's operational state and fault detection. By analyzing the spectral characteristics of electrical signals (particularly sideband frequencies around the supply frequency), the system indirectly detects bearing conditions without being directly exposed to external mechanical noise that would interfere with vibration-based sensing.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method for predicting mechanical failure of a traction motor in a vehicle includes monitoring first characteristics of an electrical signal supplied to a traction motor of a vehicle during a first detection window. The First characteristics represent a First motor electrical signature for the traction motor. The method also includes deriving one or more signature values from a first mathematical model of the first motor electrical signature and predicting a mechanical failure of the traction motor based on the one or more signature values.