Associative Memory for Manufacturing Non-Conformance Root Cause Analysis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current manufacturing systems face challenges in rapidly and accurately identifying the root cause of non-conformance instances due to large, diverse databases with extensive textual content, leading to inefficient analysis, long mitigation times, and high costs.

Innovation Solution

An associative memory system populated with entity types and an entity analytics engine that allows users to input free text queries, performing initial searches to generate relevant entities for investigating manufacturing non-conformance situations, enabling rapid correlation of multiple data sources and formats.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If traditional database systems are used to store and analyze manufacturing non-conformance data, then comprehensive data storage capability is achieved, but analysis time and computational complexity increase significantly

Engineering Contradiction:

Improvedata storage capabilityVSAvoidanalysis time

Core Design Contradiction:

Quantity of substanceVSLoss of time

Solution Approach 1:

The patent extracts and pre-processes textual content from manufacturing databases, extracting key entities, attributes, and relationships before they are stored in the associative memory. This extraction process transforms unstructured text into structured knowledge representations that can be rapidly queried without re-processing the entire database, thereby reducing analysis time while maintaining comprehensive data storage capability.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The system performs preliminary actions by pre-processing and indexing manufacturing data into the associative memory structure before actual analysis queries are executed. Entities, attributes, and their relationships are pre-organized in the associative memory, enabling fast retrieval and correlation during analysis without requiring time-consuming real-time processing of the entire database.

Inventive Principle:

Principle #10Preliminary action

2Loss of information

If free text data from multiple contributors is stored to capture all non-conformance details, then information completeness is improved, but data processing complexity and correlation difficulty increase

Engineering Contradiction:

Improveinformation completenessVSAvoiddata processing complexity

Core Design Contradiction:

Loss of informationVSDevice complexity

Solution Approach 1:

The patent introduces an intermediary processing layer between the free text data and the analysis queries. The associative memory acts as this intermediary by pre-processing and structuring the unstructured text data into standardized entity-attribute-value representations. This intermediary structure maintains the completeness of information from multiple contributors while providing a simplified, standardized interface for correlation and analysis operations.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system changes the parameters of data representation by transforming free text from multiple contributors into standardized structured formats. The associative memory re-represents the data using standardized entity types, attributes, and relationships, thereby maintaining information completeness while reducing the complexity of processing and correlation operations.

Inventive Principle:

Principle #35Parameter changes

3Productivity

If reductive algorithms are used to process large volumes of text data, then processing speed is improved, but information accuracy and subtlety are lost

Engineering Contradiction:

Improveprocessing speedVSAvoidinformation accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent replaces traditional reductive mechanical processing algorithms with an associative memory-based knowledge representation system. Instead of mechanically reducing text to predefined categories that may lose subtlety, the system uses natural language processing to create flexible entity-attribute relationships that preserve the original information's accuracy and nuance while enabling fast retrieval through associative memory lookup mechanisms.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS10410146B2Associative memory learning agent for analysis of manufacturing non-conformance applications

Publication Date: 2019.09.10 THE BOEING CO

AI summary

A system for assisting a user in determining a cause of a manufacturing non-conformance situation in a manufacturing application. The system may include an associative memory subsystem that is populated with a plurality of entity types, with each entity type including at least one entity, to form an associative memory. A user input device enables a user to input manufacturing non-conformance information into the associative memory subsystem that causes the associative memory subsystem to perform an initial search. The initial search generates a plurality of the entities that has a primary relevance useful for investigating the manufacturing non-conformance situation. An output device is responsive to the associative memory subsystem presents the plurality of entities found during the initial search to the user.