Industrial Drivetrain Anomaly Detection from Motor Waveform Spectra
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for monitoring industrial drivetrains require numerous sensors in potentially hazardous environments, which are inefficient and costly, and lack effective anomaly detection based on electrical signal analysis.
Innovation Solution
A system and method for anomaly detection in industrial drivetrains using a sensor system to capture electrical current and voltage waveforms, processing them into frequency spectra, forming a spectrogram, and detecting anomalies through enhanced traceability of frequency components using filtering, amplification, and machine learning models.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If vibration analysis using accelerometers is used to monitor rotating machinery, then anomaly detection capability is improved, but the number of sensors required increases and deployment complexity in hazardous environments worsens
Solution Approach 1:
The patent extracts the monitoring function from physical sensors deployed in hazardous environments and relocates it to electrical signal analysis at the motor control level. Electrical current and voltage waveforms already present in the system are processed to detect mechanical anomalies, eliminating the need for separate vibration sensors in dangerous locations.
Solution Approach 2:
The patent replaces mechanical vibration sensing with electrical signal analysis. Instead of using accelerometers to detect mechanical vibrations, the system analyzes electrical waveforms from the motor, substituting a mechanical measurement system with an electrical one that is already inherent to the motor control infrastructure.
2Device complexity
If electrical signal analysis is used to monitor drivetrain condition, then sensor deployment is reduced, but anomaly detection precision may be insufficient without proper signal processing
Solution Approach 1:
The patent applies preliminary signal processing actions to electrical waveforms before anomaly detection. Frequency spectra are calculated, frequency components are identified and traced, and spectral analysis is performed in advance to prepare the electrical signals for accurate anomaly detection, ensuring precision is achieved through preprocessing.
Solution Approach 2:
The patent applies comprehensive signal processing techniques including Fast Fourier Transform, frequency component tracing, and spectral analysis that may be more extensive than traditionally required. This excessive processing ensures that even subtle anomalies are detected by thoroughly analyzing all frequency components of the electrical signals.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables efficient detection and prediction of mechanical anomalies in drivetrains, reducing sensor deployment needs and enabling preventive maintenance, thereby minimizing downtime and costs.
Implementation Method 1
a sensor system for obtaining electrical current and voltage waveform data by measuring electrical currents and voltages at the three-phase motor
Implementation Method 2
processing the electrical current and voltage waveform data to obtain a number of frequency spectra related to the waveform data
Data Source
AI summary
A system for anomaly detection in an industrial drivetrain comprising various mechanical elements driven by a three-phase electrical motor. The system comprises a sensor system for obtaining electrical current and voltage waveform data by measuring electrical currents and voltages at the three-phase motor, and a computing system. The electrical waveform data contains frequency components relating to vibrations of mechanical elements of the drivetrain. The computing system performs the following steps: processing the electrical waveform data to obtain related frequency spectra, thereby enhancing traceability of the frequency components; combining the frequency spectra into a combined frequency spectrum, thereby further enhancing traceability of the frequency components; forming a spectrogram by monitoring the combined frequency spectrum over time; and tracing the frequency components in the spectrogram for anomaly detection of the related mechanical elements of the industrial drivetrain.


