Production Assessment Using a Knowledge Transfer Framework and Evidence Theory

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.

Adaptive Information Fusion Using Evidence Theory and Uncertainty Quantification

“…Architectures of decision assistance systems commonly contemplate the components: data collection, a fault detection system, a knowledge base, and an (interactive) user interface [12]. In a previous work [13], we address these components within a knowledge transfer framework for a decision assistance system. The knowledge base plays a crucial role in decision assistance systems because it provides the information that supports the user when a (faulty) condition is active [12].…”

“…The knowledge base plays a crucial role in decision assistance systems because it provides the information that supports the user when a (faulty) condition is active [12]. There are different ways to build a knowledge base, namely using ontologies [12] [14] [15], knowledge graphs [11] [16], failure mode and effects analysis (FMEA) and engineering knowledge [13] [17], and knowledge-based frameworks for multi-modal and multi-structured data [18] [19] [20] [21]. Notable examples of knowledge-based frameworks can be found in industrial applications for (prescriptive) maintenance [22] [23], machine condition assessment [13], providing work instructions [24], life cycle engineering [18], product lifecycle management [19] [25], and cyber-physical production systems [26] [27].…”

“…The fault detection system (FDS) is vital to identify the current state of the machinery or process. The fault detection system is usually powered either by a data-based model [13] or a knowledge-centered model [12]. Industrial applications of FDS are reported in the detection of safety equipment [1], fault diagnosis in machines [3] [28], and prescriptive maintenance [23].…”

“…However, no contribution addresses the fusion of n number of FDS within a general framework regardless of the model type. Moreover, there are approaches to quantify the uncertainty of data-based models [31] [28] and knowledge-based models [13] [32], respectively. However, no contribution addresses the uncertainty quantification within a general framework regardless of the model type.…”

“…Moreover, we provide a methodology to quantify the uncertainty of the individual fault detection systems, as well as the uncertainty of the resulting system. For this purpose, we present an improved architecture of the decision assistance system presented in [13]. We provide a detailed description of the architecture regarding components and their relationships, focusing on the fusion of fault detection systems and the role of uncertainty.…”