Rotating Machine Fault Detection Using Current-Based Speed Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional anomaly detection methods for rotating machines are inadequate for various types of machines and applications, often relying on standard settings that do not account for different types of machines and environments, and struggle with the absence of voltage measurements, leading to inaccurate fault detection.
Innovation Solution
Improved anomaly detection systems that estimate motor speed using current measurements and inherent machine asymmetries, normalize input power based on operating frequency, and optimize search bands for fault detection, allowing for accurate fault identification even without voltage measurements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If standard settings are used in intelligent electronic devices for anomaly detection, then the device complexity is reduced and ease of operation is improved, but the measurement precision and reliability of fault detection deteriorate due to inability to account for different machine types and applications
Solution Approach 1:
The system dynamically adapts detection parameters and search bands based on the specific machine type, application, and operating conditions rather than using fixed standard settings. This allows the anomaly detection system to optimize its performance for each unique scenario while maintaining ease of operation through automated adaptation.
Solution Approach 2:
The system changes detection parameters, frequency search bands, and analysis methods based on the identified machine type and application. By automatically adjusting these parameters rather than using standard settings, the system achieves both ease of operation and high measurement precision across diverse rotating machines.
2Measurement precision
If conventional methods rely on voltage measurements for fault detection, then measurement precision may be improved under ideal conditions, but the reliability of fault detection deteriorates when voltage measurements are unavailable
Solution Approach 1:
The system extracts and utilizes current signal information that contains fault characteristics, removing the dependency on voltage measurements. By focusing on current measurements alone, the system achieves reliable fault detection even when voltage measurements are unavailable, while maintaining measurement precision through advanced signal analysis.
Solution Approach 2:
The system uses current measurements as an intermediary to infer fault conditions that would traditionally require voltage measurements. Through sophisticated signal processing and analysis of current harmonics, the system bridges the gap between available current data and fault detection objectives, ensuring reliability without voltage inputs.
3Device complexity
If linear speed estimation algorithms based on nameplate information are used, then the device complexity is reduced, but the measurement precision of speed estimation deteriorates due to inability to account for actual operating conditions
Solution Approach 1:
The system uses feedback from actual current measurements and operating conditions to continuously refine speed estimates. Rather than relying solely on nameplate information, the system compares estimated speed with actual performance indicators from current signals, adjusting estimates to match real-world operating conditions while maintaining reasonable system complexity.
Solution Approach 2:
The system performs preliminary speed estimation using nameplate information, then refines this estimate using actual operating data from current measurements. This two-stage approach maintains low initial complexity while achieving high measurement precision through subsequent refinement based on real operating conditions.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The present disclosure relates to systems and methods for improved anomaly detection for rotating machines. An example method may include determining a rotational speed of a rotating machine. The example method may also include determining, using a frequency domain transform of a signal of the rotating machine, a frequency domain signal. The example method may also include determining, based on the rotational speed of the rotating machine, a first frequency band within the frequency domain signal for identifying a fault frequency of the rotating machine. The example method may also include determining a fault frequency of the rotational machine within the first frequency band. The example method may also include determining, based on the fault frequency, a second frequency band within the first frequency band, wherein the second frequency band includes the fault frequency. The example method may also include determining, based on the second frequency band, a first fault index and a baseline of the first fault index. The example method may also include determining, based on a deviation of a second fault index from the baseline, a fault condition of the rotating machine. The example method may also include providing an alert based on the fault condition of the rotating machine.