The General Motors Variation-Reduction Adviser: A Deployed System for Experience Management

نویسندگان

  • Alexander P. Morgan
  • John A. Cafeo
  • Kurt Godden
  • Ronald M. Lesperance
  • Andrea M. Simon
  • Deborah L. McGuinness
  • James L. Benedict
چکیده

The General Motors Variation-Reduction Adviser (VRA) is an experience-management system currently in use in most GM assembly centers. Its purpose is to capture and communicate problem-solving events from various quality-control activities. The most important prerequisite to the success of the VRA project was having a community that was already sharing problem-solving experiences, mostly via written logs (within in plants) and weekly telephone conferences (between plants). The key insight for success of the VRA was to realize that nobody is motivated to “author cases” for future use, but everybody is motivated to communicate with peers during an investigative activity. The case-capture mechanism for the VRA evolved from its original concept (authoring structured cases) to the final design that focuses on recording communications during the problem-solving process. The resulting “textual case-based reasoning” (TCBR) system leverages smart search (ontology-guided search) to counterbalance the loss of structure in the case descriptions. A formal return-on-investment business analysis was created to justify the project, but the most convincing justification has been its current widespread daily use.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

The General Motors Variation-Reduction Adviser: Deployment Issues for an AI Application

The General Motors Variation-Reduction Adviser is a knowledge system built on case-based reasoning principles that is currently in use in a dozen General Motors Assembly Centers. This paper reviews the overall characteristics of the system and then focuses on various AI elements critical to support its deployment to a production system. A key AI enabler is ontology-guided search using domain-sp...

متن کامل

Deployment Issues for an AI Application

The Variation-Reduction Adviser (VRA) is a knowledge system for automotive assembly plants whose goal is to support quality improvement activities for assembly line processes (Cafeo et al. 2001, Morgan et al. 2001). The primary use of VRA is to improve communication in the plants and between plants to assist with problem solving necessary to keep the line producing the highest quality products....

متن کامل

An indirect adaptive neuro-fuzzy speed control of induction motors

This paper presents an indirect adaptive system based on neuro-fuzzy approximators for the speed control of induction motors. The uncertainty including parametric variations, the external load disturbance and unmodeled dynamics is estimated and compensated by designing neuro-fuzzy systems. The contribution of this paper is presenting a stability analysis for neuro-fuzzy speed control of inducti...

متن کامل

Fuzzy Logic Based Life Estimation of PWM Driven Induction Motors

Pulse-width modulated (PWM) adjustable frequency drives (AFDs) are extensively used in industries for control of induction motors. It has led to significant advantages in terms of the performance, size, and efficiency but the output voltage waveform no longer remains sinusoidal. Hence, overshoots, high rate of rise, harmonics and transients are observed in the voltage wave. They increase voltag...

متن کامل

Product Development Decision Support System Customer-Based

Quality Function Deployment (QFD) has been traditionally used as a planning tool primarily for product development and quality improvement. In this context, many people have used QFD for making decisions on how to prioritize critical product areas from a customer perspective. However, it is the position of the author that the QFD process can be viewed as a decision support system that would enc...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • KI

دوره 21  شماره 

صفحات  -

تاریخ انتشار 2007