Storage Error Pattern Recognition for Fault Isolation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional computing systems fail to distinguish between faulty and healthy hardware components, leading to cascading errors and unnecessary shutdowns of otherwise operational components.

Innovation Solution

A system hardware error manager is trained to recognize error patterns using supervised learning, intelligently indict faulty components, and unindict dependent components to prevent cascading errors, utilizing a trained error analysis engine to analyze error messages and implement corrective actions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional error monitoring is used to detect hardware failures, then faulty components can be identified, but healthy components are falsely indicted due to cascading errors

Engineering Contradiction:

Improvecomponent failure detection accuracyVSAvoidfalse indictment of healthy components

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The system performs preliminary actions by training the error analysis engine with labeled training examples before deployment. The engine learns to distinguish between errors originating from faulty components versus cascading errors from healthy components through supervised learning, enabling accurate differentiation before actual failure detection occurs

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements feedback mechanisms where the error analysis engine continuously monitors error patterns, compares them against learned patterns from training, and refines its classification of faulty versus healthy components. The supervised learning process incorporates feedback from labeled examples to improve detection accuracy and reduce false indictments

Inventive Principle:

Principle #23Feedback

2Stability of the object's composition

If traditional error monitoring shuts down components upon error detection, then system stability is maintained, but operational components are unnecessarily stopped

Engineering Contradiction:

Improvesystem stabilityVSAvoidunnecessary shutdown of operational components

Core Design Contradiction:

Stability of the object's compositionVSProductivity

Solution Approach 1:

The system replaces traditional mechanical error response mechanisms (automatic shutdown upon error detection) with an intelligent software-based error analysis engine. This engine uses supervised learning to analyze error patterns and make informed decisions about component status, substituting rigid mechanical response with adaptive intelligent analysis

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system changes the parameter of error response from binary (shutdown/operate) to a nuanced classification system that distinguishes between faulty and healthy components based on learned error patterns. This parameter change enables differentiated responses that maintain stability while avoiding unnecessary shutdowns

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If manual analysis of error patterns is performed, then accurate component identification is possible, but system complexity and analysis time increase

Engineering Contradiction:

Improveerror pattern analysis accuracyVSAvoiderror analysis system complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The error analysis engine performs self-service by automatically learning from labeled training examples and independently analyzing error patterns without requiring manual intervention. The supervised learning process enables the system to serve itself in terms of pattern recognition and component classification, reducing the need for complex manual analysis procedures

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system uses copying by creating labeled training examples that replicate actual error scenarios. These training copies enable the error analysis engine to learn from simulated failures without requiring complex manual analysis of every actual error event, simplifying the overall system while maintaining accuracy

Inventive Principle:

Principle #26Copying

Data Source

PatentUS20250370873A1Intelligent Faulty Component Error Pattern Recognition and Fault Isolation

Publication Date: 2025.12.04 DELL PROD LP

AI summary

A method of intelligently recognizing faulty component error patterns to prevent cascading errors from causing indictment of healthy hardware components includes a system hardware error manager with a trained error analysis engine. The error analysis engine is trained using labeled training examples correlating storage system error patterns with component indictments and unindictable dependent components. The trained error analysis engine is deployed to monitor sequences of error messages to recognize error patterns generated by components of an operating storage system. In response to recognition of an error pattern, the trained error analysis engine indicts a system component associated with the recognized error pattern. Any errors that were generated by dependent components after the start of the recognized error pattern are reversed. Any dependent components that were indicted based on errors that were generated by the dependent components after the start of the recognized error pattern are also reversed.