Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Production Assessment using a Knowledge Transfer Framework and Evidence Theory

Fernando Arevalo N., Christian Alison M. Piolo, Tahasanul Ibrahim, Andreas Schwung

TL;DR

The paper tackles the challenge of converting tacit shop-floor knowledge into explicit, actionable rules while rigorously accounting for uncertainty. It introduces KLAFATE, a framework that combines an extended FMEA for knowledge extraction, Dempster-Shafer evidence theory for uncertainty quantification, and primitive recursive functions for knowledge representation, all embedded in an AR-enabled interactive system. Key contributions include a formalized taxonomy for knowledge transfer, a KPI-driven validation strategy, and an end-to-end use case on a laboratory Bulk Good System with HoloLens as the UI. The approach offers a structured, user-centered pathway to institutionalize operator expertise, enhance decision support on the factory floor, and enable robust knowledge transfer to broader process industries.

Abstract

Operational knowledge is one of the most valuable assets in a company, as it provides a strategic advantage over competitors and ensures steady and optimal operation in machines. An (interactive) assessment system on the shop floor can optimize the process and reduce stopovers because it can provide constant valuable information regarding the machine condition to the operators. However, formalizing operational (tacit) knowledge to explicit knowledge is not an easy task. This transformation considers modeling expert knowledge, quantification of knowledge uncertainty, and validation of the acquired knowledge. This study proposes a novel approach for production assessment using a knowledge transfer framework and evidence theory to address the aforementioned challenges. The main contribution of this paper is a methodology for the formalization of tacit knowledge based on an extended failure mode and effect analysis for knowledge extraction, as well as the use of evidence theory for the uncertainty definition of knowledge. Moreover, this approach uses primitive recursive functions for knowledge modeling and proposes a validation strategy of the knowledge using machine data. These elements are integrated into an interactive recommendation system hosted on a backend that uses HoloLens as a visual interface. We demonstrate this approach using an industrial setup: a laboratory bulk good system. The results yield interesting insights, including the knowledge validation, uncertainty behavior of knowledge, and interactive troubleshooting for the machine operator.

Production Assessment using a Knowledge Transfer Framework and Evidence Theory

TL;DR

The paper tackles the challenge of converting tacit shop-floor knowledge into explicit, actionable rules while rigorously accounting for uncertainty. It introduces KLAFATE, a framework that combines an extended FMEA for knowledge extraction, Dempster-Shafer evidence theory for uncertainty quantification, and primitive recursive functions for knowledge representation, all embedded in an AR-enabled interactive system. Key contributions include a formalized taxonomy for knowledge transfer, a KPI-driven validation strategy, and an end-to-end use case on a laboratory Bulk Good System with HoloLens as the UI. The approach offers a structured, user-centered pathway to institutionalize operator expertise, enhance decision support on the factory floor, and enable robust knowledge transfer to broader process industries.

Abstract

Operational knowledge is one of the most valuable assets in a company, as it provides a strategic advantage over competitors and ensures steady and optimal operation in machines. An (interactive) assessment system on the shop floor can optimize the process and reduce stopovers because it can provide constant valuable information regarding the machine condition to the operators. However, formalizing operational (tacit) knowledge to explicit knowledge is not an easy task. This transformation considers modeling expert knowledge, quantification of knowledge uncertainty, and validation of the acquired knowledge. This study proposes a novel approach for production assessment using a knowledge transfer framework and evidence theory to address the aforementioned challenges. The main contribution of this paper is a methodology for the formalization of tacit knowledge based on an extended failure mode and effect analysis for knowledge extraction, as well as the use of evidence theory for the uncertainty definition of knowledge. Moreover, this approach uses primitive recursive functions for knowledge modeling and proposes a validation strategy of the knowledge using machine data. These elements are integrated into an interactive recommendation system hosted on a backend that uses HoloLens as a visual interface. We demonstrate this approach using an industrial setup: a laboratory bulk good system. The results yield interesting insights, including the knowledge validation, uncertainty behavior of knowledge, and interactive troubleshooting for the machine operator.
Paper Structure (28 sections, 4 theorems, 72 equations, 12 figures, 14 tables, 1 algorithm)

This paper contains 28 sections, 4 theorems, 72 equations, 12 figures, 14 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Extraction of Tacit Knowledge and Uncertainty Quantification
  4. Knowledge Modeling and Validation
  5. Interactive Assessment Systems
  6. KLAFATE: Knowledge Transfer Framework and Evidence Theory
  7. Theoretical Background
  8. Boolean Logic Rules
  9. Dempster Shafer Evidence Theory
  10. Extraction of Tacit Knowledge and Uncertainty Quantification
  11. Knowledge Extraction
  12. Uncertainty Quantification of the knowledge rules
  13. Knowledge Modeling and Validation
  14. Knowledge Modeling
  15. Knowledge Validation
  16. ...and 13 more sections

Key Result

Proposition 1

The sum of BPAs from Equation (equation__DSET_3) can be transformed into: where $w_{m_{j}}$ is the $j_{th}$ confidence weight of the BPA $m_{i}$, and $U$ is the overall uncertainty. The confidence weight $w_{m_{j}}$ represents the confidence level of the evidence $m_{i}$, which can be quantified using a predefined criteria.

Figures (12)

  • Figure 1: Knowledge Stages
  • Figure 2: Knowledge Framework Overview
  • Figure 3: Relationship between templates
  • Figure 4: Overview of Confidence Weights
  • Figure 5: Sequence Diagram of the Interactive Assessment System
  • ...and 7 more figures

Theorems & Definitions (10)

  • Definition 1: Dempster-Shafer Shafer1976
  • Proposition 1
  • Definition 2
  • Lemma 1
  • proof
  • Remark 1
  • Proposition 2
  • Lemma 2
  • proof
  • Definition 3: Kleene Kleene1971