Gearbox Fault Detection via Frequency Decomposition and Baseline Comparison

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Gearbox failures in industries, such as aircraft and specific industrial settings, lead to significant downtime and financial losses due to the inability to detect incipient faults effectively, resulting in secondary damage and increased maintenance costs.

Innovation Solution

A system and method for gearbox health monitoring that includes an input interface to receive signals from sensors, a processor to identify faults by determining a family of frequencies related to failure modes, decomposing and reconstructing gear signals, and comparing them to baseline signals to provide indicators of potential failures.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional vibration analysis methods are used to monitor gearbox conditions, then the monitoring system can detect general vibration levels, but it cannot effectively identify incipient faults or classify specific failure modes

Engineering Contradiction:
Improvefault detection precisionVSAvoidsignal processing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the complex vibration signal into multiple frequency components using spectral analysis. By decomposing the signal into specific frequency bands associated with different gear elements (gear mesh frequency, bearing frequencies, tooth pass frequencies), the system can identify specific failure modes. This segmentation transforms a complex monitoring problem into manageable frequency-specific analyses, improving fault detection precision without requiring overly complex processing methods.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent transitions from time-domain vibration analysis to frequency-domain analysis by applying Fast Fourier Transform (FFT) and spectral analysis techniques. This dimensional change from time to frequency domain enables the system to distinguish between different failure modes that may produce similar time-domain signals. The frequency dimension provides additional diagnostic information that improves measurement precision for fault identification.

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

2Reliability

If advanced signal processing techniques are implemented to improve fault detection accuracy, then incipient faults can be identified earlier, but the computational requirements and system complexity increase

Engineering Contradiction:
Improvegearbox operation reliabilityVSAvoidcomputational energy consumption
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent establishes baseline vibration signatures for normal gearbox operation during an initial monitoring period. These baselines are stored and used for comparison with subsequent measurements, enabling the system to detect deviations that indicate incipient faults. This preliminary action reduces the need for complex real-time analysis by providing reference data for quick comparison, thereby improving reliability while managing computational energy consumption.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system continuously compares current vibration signals against established baselines and provides feedback when deviations exceed predefined thresholds. This feedback mechanism enables early detection of incipient faults by identifying patterns that deviate from normal operation. The feedback loop allows the system to maintain high reliability through continuous monitoring while using energy-efficient threshold-based comparisons rather than exhaustive analysis of every signal.

Inventive Principle:
Principle #23Feedback

3Reliability

If comprehensive monitoring of all gearbox components is performed, then all potential failure modes can be detected, but the cost and complexity of the monitoring system increase significantly

Engineering Contradiction:
Improvefault detection coverageVSAvoidmonitoring system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent employs a single vibration sensor and signal processing system that can detect multiple failure modes including gear tooth wear, bearing defects, and misalignment. By analyzing different frequency components of the vibration signal, the universal system can identify various failure types without requiring separate specialized sensors for each component. This multi-functionality achieves comprehensive fault detection coverage while avoiding the complexity and cost of multiple dedicated monitoring systems.

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

Solution Approach 2:

The patent uses spectral analysis and frequency domain techniques as intermediaries to translate complex multi-component vibration signals into interpretable diagnostic information. The signal processing acts as an intermediary that extracts meaningful features from the raw vibration data, enabling the detection of multiple failure modes through a single monitoring channel. This intermediary approach comprehensively monitors all gearbox components without requiring physically complex monitoring hardware.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP2414807B1System and method for gearbox health monitoring
Publication Date: 2018.02.14 HONEYWELL INTERNATIONAL INC
  • EP2414807B1 patent drawingFigure 1A~1D
  • EP2414807B1 patent drawingFigure 2A~2E
  • EP2414807B1 patent drawingFigure 3

AI summary

A system includes a plurality of sensors (322-324) configured to measure one or more characteristics of a gearbox. The system also includes a gearbox condition indicator device (300), which includes a plurality of sensor interfaces (320) configured to receive input signals associated with at least one stage of the gearbox from the sensors. The gearbox condition indicator device also includes a processor (330) configured to identify a fault in the gearbox using the input signals and an output interface (370) configured to provide an indicator identifying the fault. The processor is configured to identify the fault by determining a family of frequencies (640) related to at least one failure mode of the gearbox, decomposing the input signals using the family of frequencies, reconstructing a gear signal using the deconstructed input signals, and comparing the reconstructed gear signal to a baseline signal (328). The family of frequencies includes a gear mesh frequency and its harmonics.