Abnormality Detection System for Semiconductor Manufacturing

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

In semiconductor device manufacturing, existing abnormality detection systems require engineers to manually determine and register new detection algorithms for new detection targets, leading to increased workload and reduced manufacturing efficiency, as they often necessitate isolating manufacturing devices from the mass production line for prototyping.

Innovation Solution

An abnormality detection system with an algorithm storage unit, abnormality detection unit, detection target identification unit, and algorithm generation unit that automatically generates detection algorithms based on identification information, reducing the need for manual registration and enabling continuous operation of manufacturing devices.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If engineers manually determine and register new detection algorithms for new detection targets, then detection accuracy can be ensured, but engineer workload increases and manufacturing efficiency decreases

Engineering Contradiction:

Improvedetection accuracyVSAvoidmanufacturing efficiency

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The system enables self-service by allowing the manufacturing device to automatically generate and register detection algorithms for new detection targets without engineer intervention. The algorithm generation unit creates algorithms based on monitor signals from the detection target, and the storage unit automatically stores them, eliminating the need for manual engineer work while maintaining detection accuracy.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system performs preliminary action by pre-generating detection algorithms through the algorithm generation unit before they are needed for actual detection. The algorithms are created in advance based on monitor signals and stored in the storage unit, so when new detection targets appear, the algorithms are already ready for immediate use, improving manufacturing efficiency.

Inventive Principle:

Principle #10Preliminary action

2Reliability

If engineers manually prototype new detection algorithms using isolated manufacturing devices, then reliable detection algorithms can be developed, but time losses and costs increase

Engineering Contradiction:

Improvealgorithm reliabilityVSAvoidprototyping time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system replaces the mechanical prototyping process with an automated information processing system. Instead of physically isolating manufacturing devices for manual prototyping, the algorithm generation unit automatically generates algorithms using monitor signals from the detection target, and the storage unit stores them for immediate use, eliminating time losses and costs associated with manual prototyping while maintaining algorithm reliability.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The algorithm generation unit acts as an intermediary between the monitor signals and the detection algorithm requirements. It automatically processes monitor signals from the detection target to generate reliable detection algorithms, eliminating the need for manual engineer intervention and isolated prototyping, thereby reducing time losses and costs.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Ease of manufacture

If manufacturing devices are isolated from mass production line for prototyping, then new detection algorithms can be developed, but production continuity is disrupted

Engineering Contradiction:

Improvealgorithm development easeVSAvoidproduction continuity

Core Design Contradiction:

Ease of manufactureVSProductivity

Solution Approach 1:

The system ensures continuity of useful action by allowing the algorithm generation unit to automatically generate detection algorithms using monitor signals from the detection target without isolating the manufacturing device from the mass production line. The storage unit stores these algorithms for immediate use, maintaining production continuity while enabling easy algorithm development.

Inventive Principle:

Principle #20Continuity of useful action

Data Source

PatentUS10409260B2Abnormality detection system, semiconductor device manufacturing system and semiconductor device manufacturing method

Publication Date: 2019.09.10 RENESAS ELECTRONICS CORP

AI summary

To provide an abnormality detection system capable of reducing work load of an engineer. An algorithm storage unit stores therein a detection algorithm corresponding to identification information of a detection target. An abnormality detection unit detects an abnormality in a detection target signal obtained from a monitor signal of the detection target using a corresponding detection algorithm in the algorithm storage unit. A detection target identification unit determines whether the detection algorithm corresponding to the identification information of the detection target is stored in the algorithm storage unit, and issues a generation request when it is not stored therein. An algorithm generation unit generates the detection algorithm using a corresponding detection target signal according to the generation request.