Rotating Machine Abnormality Detection via Chronological Frequency Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional abnormality detection systems for rotating machines, such as turbines and compressors, fail to promptly detect rotor abnormalities due to a lack of chronological change analysis in operating state data, leading to delayed detection and potential machine shutdown.

Innovation Solution

An abnormality detection device equipped with vibration sensors, amplifiers, and a sampling unit that samples and processes data using AE sensors and accelerometers, performing real-time frequency analysis and displaying results chronologically to facilitate early detection of rotor abnormalities.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional AE sensor-based detection is used, then abnormality presence/position/degree can be determined, but chronological change in operating state cannot be displayed

Engineering Contradiction:
Improveabnormality detection accuracyVSAvoidchronological change information
Core Design Contradiction:
Measurement precisionVSLoss of information

Solution Approach 1:

The patent combines AE sensors with accelerometers and integrates their detection results into a unified display system. This merging allows simultaneous acquisition of both abnormality characteristics and chronological operating state changes, resolving the contradiction between detection accuracy and information completeness.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent adds a temporal dimension to the display by showing frequency analysis results in chronological order. This transforms the detection system from providing only static abnormality assessment to providing dynamic temporal evolution information, thereby recovering the lost chronological change information.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Reliability

If only determination results are displayed, then abnormality information is provided, but prompt detection is difficult

Engineering Contradiction:
Improveabnormality detection reliabilityVSAvoiddetection response time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent implements continuous feedback by displaying frequency analysis results in real-time chronological order. This allows operators to observe the evolution of vibration characteristics over time and immediately identify when abnormality patterns emerge, significantly reducing detection response time while maintaining reliable detection.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

By displaying chronological changes in frequency analysis results, the system enables preliminary detection of abnormality trends before they develop into critical failures. Operators can identify early signs of rotor abnormalities through temporal pattern recognition, allowing earlier intervention.

Inventive Principle:
Principle #10Preliminary action

3Loss of time

If chronological change analysis is added, then prompt abnormality detection is enabled, but device complexity increases

Engineering Contradiction:
Improvedetection response timeVSAvoiddetection system complexity
Core Design Contradiction:
Loss of timeVSDevice complexity

Solution Approach 1:

The patent makes the display section multi-functional by enabling it to show both traditional abnormality determination results and chronological frequency analysis results. This universal display capability provides temporal analysis functionality without requiring separate dedicated hardware, thereby limiting the increase in device complexity.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The control section serves as an intermediary that processes and integrates data from multiple sensors (AE sensors and accelerometers) and coordinates the chronological display of frequency analysis results. This central coordination enables complex temporal analysis functionality while maintaining a relatively simple overall system architecture.

Inventive Principle:
Principle #24Intermediary (Mediator)

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 prompt detection of rotor abnormalities by displaying chronological changes in operating state data, allowing operators to recognize and address issues before they cause machine failure.

Implementation Method 1

an abnormal sliding diagnostic device disclosed in Patent Literature 1 uses an AE (Acoustic Emission) sensor to detect an AE signal from a rotating machine

Methodology Applied
Scientific EffectAcoustic Emission: Acoustic Emission

Implementation Method 2

a sampling unit configured to sample a vibration of the rotating machine

Methodology Applied
Scientific EffectVibration: Vibration

Data Source

PatentEP3193153B1Rotating machine abnormality detection device, method and system, and rotating machine
Publication Date: 2023.10.04 KOBE STEEL LTD
  • EP3193153B1 patent drawingFigure 1
  • EP3193153B1 patent drawingFigure 2
  • EP3193153B1 patent drawingFigure 3

AI summary

An abnormality detection device, an abnormality detection method and an abnormality detection system for a rotating machine according to the present invention sample a vibration of a rotating machine at a predetermined sampling frequency, output for each predetermined period of time a set of a plurality of samples detected within the predetermined period of time, store the set of samples in a storage section, perform frequency analysis on the set of samples, and display in real time frequency analysis results in chronological order. A rotating machine according to the present invention includes the abnormality detection device.