Engine Fault Detection via Operational Signature Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for detecting mechanical faults in complex machinery, such as engine systems, are unreliable and often lead to significant service time losses and increased labor costs, with a need for more accurate and preventative fault detection to avoid catastrophic failures.

Innovation Solution

An automatic fault detection system that uses sensors to monitor operational aspects of engine components, processes sensor signals through a signal processing system, and adjusts engine operation based on detected faults, incorporating learning capabilities to improve accuracy and prevent mechanical failures.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If routine monitoring of components is performed to detect potential failures, then early detection of mechanical faults is achieved, but significant service time loss and increased labor costs occur

Engineering Contradiction:
Improveearly detection of mechanical faultsVSAvoidservice time loss
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent replaces manual inspection methods with an automated sensor-based monitoring system that continuously collects and analyzes operational data from engine components. This substitution eliminates the need for periodic manual disassembly and inspection, achieving early fault detection without service time loss.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables the engine to self-diagnose its own condition through embedded sensors and processing units that continuously monitor component health parameters. The automated nature of the system allows the equipment to detect and report its own faults without requiring external intervention or shutdown for inspection.

Inventive Principle:
Principle #25Self-service

2Measurement precision

If current in situ detection methods are used to identify mechanical failures, then some fault detection is achieved, but reliability and accuracy are limited due to inconsistency and error

Engineering Contradiction:
Improvefault detection accuracyVSAvoiddetection consistency
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The system incorporates continuous feedback loops where sensor data is constantly analyzed, compared against threshold values, and used to adjust monitoring parameters. The processed information feeds back to update the diagnostic algorithms, improving detection accuracy and consistency over time through adaptive learning from operational patterns.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The monitoring system is designed to detect multiple types of faults across different engine components using a unified platform. The same sensor array and processing unit can identify various failure modes including cracks, wear, and performance degradation, providing consistent and reliable detection across diverse mechanical conditions.

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

3Reliability

If components are over-designed to prevent failures, then system reliability is improved, but additional cost is incurred for the supplier and customer

Engineering Contradiction:
Improvesystem reliabilityVSAvoidcomponent design complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system performs preliminary detection of developing faults before they progress to catastrophic failure. By identifying early signs of component degradation through continuous monitoring, the system enables preventive maintenance actions that protect standard-designed components from failure, eliminating the need for over-engineering.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS9429092B2Fault detection and response techniques
Publication Date: 2016.08.30 ROSERO CARLOS A
  • US9429092B2 patent drawing
  • US9429092B2 patent drawing
  • US9429092B2 patent drawing

AI summary

Systems and methods for detecting, predicting and/or responding to faults are disclosed. In one form, a sensor can be operatively coupled to an engine system having a component and a control system is coupled to the sensor. The sensor can be structured to monitor the engine system and generate corresponding sensor information. The control system can be structured to: generate an operational signature based on the sensor information, estimate whether a fault (e.g., a mechanical fault of the component and/or a performance fault of the engine system) exists based on the operational signature, determine an engine operating mode adjustment if the fault exists and output the engine operating mode adjustment to an output device. Systems and methods for increasing the accuracy by which faults are detected and/or predicted are also disclosed. The engine operating mode adjustment can be applied to protect engine system components from being undesirably damaged to faults.