Rotating Machine Anomaly Detection Using Current-Based Speed Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional anomaly detection methods for rotating machines are limited in their ability to accurately detect faults across different types of machines and applications, particularly in the absence of voltage measurements, and often require specific sensors or conditions, which can lead to inaccurate speed estimation and fault detection.
Innovation Solution
The proposed system improves motor speed estimation by using either the torque component of current or inherent machine asymmetries, even without voltage measurements, and optimizes search bands for fault detection based on the type of machine and speed estimation method, allowing for more accurate fault index computation and real-time anomaly detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If standard settings are used in intelligent electronic devices for anomaly detection, then device complexity is reduced and ease of operation is improved, but measurement precision and reliability deteriorate because the settings do not adapt to different types of machines and applications
Solution Approach 1:
The system dynamically adapts detection parameters and search bands based on the specific machine type and operating conditions. The processor automatically adjusts frequency search bands, threshold values, and detection algorithms according to the identified machine category (induction motor, synchronous motor, pump, compressor, etc.), transforming static standard settings into dynamic adaptive parameters that maintain both ease of operation and measurement precision.
Solution Approach 2:
The system changes detection parameters including frequency search bands, threshold values, and analysis methods based on the specific machine type and operating mode. For example, different search bands are used for different machine types, and detection thresholds are adjusted according to the expected fault signatures of specific equipment, enabling precise detection without requiring manual parameter tuning for each application.
2Extent of automation
If conventional speed estimation methods using frequency domain analysis are used, then speed estimation can be performed, but measurement precision deteriorates in the absence of voltage measurements or when specific sensors are not available
Solution Approach 1:
The system introduces alternative measurement pathways using current signal processing as an intermediary when voltage measurements are unavailable. By analyzing current harmonics, sidebands, and spectral features through advanced signal processing techniques, the system estimates speed and detects faults with precision comparable to methods using direct voltage measurements, eliminating the need for additional sensors.
Solution Approach 2:
The system changes the input parameters for speed estimation based on available measurements. When voltage measurements are available, traditional voltage-based methods are used; when unavailable, the system switches to current-based parameter extraction, adjusting the analysis focus from voltage harmonics to current spectral features, thereby maintaining measurement precision across different sensor configurations.
3Device complexity
If fixed search bands are used for fault detection, then device complexity is reduced, but measurement precision deteriorates because the bands cannot be optimized for different machine types and failure modes
Solution Approach 1:
The system implements dynamic search band adjustment where frequency search bands are automatically expanded or contracted based on the specific failure mode being detected and the machine operating conditions. For example, bearing fault detection uses different band widths than rotor bar fault detection, and the bands are further adjusted according to speed and load variations, optimizing detection precision without requiring complex manual configuration.
4Adaptability or versatility
If conventional anomaly detection methods are used, then compatibility with existing systems is maintained, but adaptability deteriorates because the methods cannot accurately detect faults across different types of machines and applications
Solution Approach 1:
The system achieves universal applicability across different machine types (induction motors, synchronous motors, pumps, compressors, fans, blowers) through a unified detection platform that automatically identifies the machine category and applies appropriate detection parameters. The same processor and algorithm framework handle diverse machine types by adapting search bands, threshold values, and analysis methods to each specific application, ensuring reliable fault detection across the entire range of rotating machinery without requiring separate specialized systems.
Data Source
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; determining, using a frequency domain transform of a signal, a frequency domain signal; determining, based on the rotational speed, a first frequency band within the frequency domain signal for identifying a fault frequency; determining a fault frequency within the first frequency band; determining, based on the fault frequency, a second frequency band within the first frequency band, wherein the second frequency band includes the fault frequency; determining, based on the second frequency band, a first fault index and a baseline of the first fault index; determining, based on a deviation of a second fault index from the baseline, a fault condition; and providing an alert based on the fault condition.