Rotary Machine Vibration Monitoring with Operating-State Thresholds

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing state monitoring systems for electrical rotary machines struggle to accurately distinguish between different operating points and load states, leading to inadequate recognition of minor changes in vibration amplitude over time.

Innovation Solution

A computer-implemented process that uses historical data to identify operating point clusters, determine threshold values for spatial vibration components specific to each operating state, and monitor actual data against these thresholds to issue warnings for exceeding recommended vibration levels.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If vibration measurement is used for analysis without considering operating point, then analysis simplicity is maintained, but measurement precision deteriorates because minor changes at individual operating points cannot be detected

Engineering Contradiction:
Improveanalysis simplicityVSAvoidvibration amplitude detection accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The patent segments the continuous vibration signal into discrete segments corresponding to different operating points. Each segment is analyzed separately with its own threshold, enabling precise detection of vibration changes at specific operating conditions while maintaining automated analysis simplicity.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent implements dynamic threshold adjustment based on operating point identification. The threshold value changes dynamically according to the detected operating point, allowing the system to adapt to varying vibration characteristics at different operating conditions without manual intervention.

Inventive Principle:
Principle #15Dynamics

2Measurement precision

If operating point differentiation is implemented to improve vibration analysis accuracy, then measurement precision improves, but device complexity increases due to additional processing requirements

Engineering Contradiction:
Improvevibration amplitude detection accuracyVSAvoidprocessing system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent performs preliminary identification of operating points and determination of appropriate thresholds before actual vibration assessment. This preliminary action organizes the complex processing requirements into structured phases, making the system more manageable and implementable.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent employs feedback mechanisms where vibration measurements are continuously compared against operating-point-specific thresholds, and results feed back into ongoing monitoring. This feedback loop enables accurate precision without requiring permanently complex processing architecture.

Inventive Principle:
Principle #23Feedback

3Ease of operation

If threshold checks are performed without operating point consideration, then ease of operation is maintained, but reliability deteriorates due to false alarms and missed detections

Engineering Contradiction:
Improvethreshold check simplicityVSAvoidcondition monitoring reliability
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The patent makes the threshold dynamic by linking it to identified operating points. The threshold automatically adjusts based on the current operating condition, maintaining ease of automated operation while significantly improving reliability by reducing false alarms and missed detections through context-aware assessment.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP4178101B1Vibration-based state monitoring of electric rotary machines
Publication Date: 2025.05.07 SIEMENS AG
  • EP4178101B1 patent drawingFigure 1
  • EP4178101B1 patent drawingFigure 2
  • EP4178101B1 patent drawingFigure 3

AI summary

The invention relates to a computer-implemented method for training a model to recommend threshold values ​​of at least one spatial vibration component of an electric rotary machine, wherein: - historical data are provided, the historical data comprising time series of at least two operating parameters and of at least one spatial vibration component of the electric rotary machine; - operating plateaus are detected in the historical data, wherein an operating plateau is defined by the fact that the at least two operating parameters are constant over a predefinable period; - a cluster analysis is performed on the detected operating plateaus to identify clusters of operating points, wherein different clusters of operating points define different operating states of the electric rotary machine.- Threshold values ​​recommended for the defined operating conditions for which at least one spatial vibration component is determined, - the defined operating conditions and the threshold values ​​recommended for the defined operating conditions are provided.