Automated Quality Review Rules for Manufacturing Exception Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Quality review in manufacturing processes is inefficient due to the need for manual and time-consuming analysis of batch log files to identify exceptions, which requires extensive knowledge and data access across multiple systems, leading to potential errors and inconsistencies in quality control.

Innovation Solution

A quality review management system that automatically detects exceptions using configurable rules and an exception engine, storing data in an organized manner and providing a user-friendly interface for quality engineers to review and handle exceptions, with features like live feedback and metadata display for context.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual analysis of batch log files is used to identify exceptions, then quality review personnel can detect process deviations, but the process requires extensive time and effort

Engineering Contradiction:

Improvequality control accuracyVSAvoidexception identification time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent replaces the manual mechanical review process with an automated computer-based system that uses machine learning models and algorithms to analyze batch log files, process data, and identify exceptions automatically, eliminating the time-consuming manual analysis while maintaining or improving detection accuracy

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces an intermediary automated quality review system that acts as a bridge between raw manufacturing data and quality decisions, using trained machine learning models to process and interpret data, thereby reducing the time burden on quality personnel while preserving reliable exception detection

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If quality review personnel manually access multiple systems to gather process data, then comprehensive quality analysis can be performed, but the complexity of data access increases

Engineering Contradiction:

Improvequality review completenessVSAvoidsystem integration complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent merges multiple data sources and systems into a single integrated automated quality review platform that automatically accesses and consolidates process data from various manufacturing systems, eliminating the need for personnel to manually navigate multiple systems while ensuring comprehensive data collection

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The patent creates a universal automated quality review system capable of interfacing with multiple different data sources and manufacturing systems through standardized protocols, providing comprehensive quality analysis through a single multi-functional platform that reduces operational complexity

Inventive Principle:

Principle #6Universality (Multi-functionality)

3Measurement precision

If extensive knowledge of manufacturing processes and quality standards is required for quality review, then accurate exception detection can be achieved, but the difficulty of operation increases

Engineering Contradiction:

Improveexception detection accuracyVSAvoidquality review accessibility

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The patent replaces the need for human expert knowledge with automated machine learning models that have been trained on historical manufacturing data and quality standards, encoding specialized knowledge into algorithms that automatically perform accurate exception detection without requiring operators to possess extensive domain expertise

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent performs preliminary action by pre-training machine learning models with extensive manufacturing process knowledge and quality standards before deployment, so that when the system operates, this embedded knowledge automatically guides accurate exception detection without requiring users to have specialized expertise

Inventive Principle:

Principle #10Preliminary action

4Adaptability or versatility

If manual quality review processes are used, then flexibility in handling different quality standards can be maintained, but productivity decreases

Engineering Contradiction:

Improvequality standard flexibilityVSAvoidquality review throughput

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The patent implements a dynamic automated quality review system where machine learning models can be retrained and reconfigured to adapt to different quality standards and manufacturing processes, allowing the system to maintain flexibility and versatility while operating at high automated speeds that greatly exceed manual review productivity

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS11442428B2Quality review management system

Publication Date: 2022.09.13 FISHER ROSEMOUNT SYST INC

AI summary

A quality review management system may be used to analyze the operation of manufacturing processes within a plant based on data collected by various data sources in the plant, such as batch executive applications, to automatically detect, store, and display exceptions within those processes for use by a quality review engineer to determine if the process operation meets certain quality standards. The quality review management system includes a configuration application that enables a user to create one or more exception rules, an exception engine that analyses process data using the rules to detect one or more exceptions within the process, and a review application that enables quality review personnel to review each determined exception for resolution purposes.