Analysis and Optimization based on Reusable Knowledge Base of Process Performance Models

Abstract

Abstract:In this paper, we propose an architectural design and software framework for fast development of descriptive, diagnostic, predictive, and prescriptive analytics solutions for dynamic production processes. The proposed architecture and framework will support the storage of modular, extensible, and reusable Knowledge Base (KB) of process performance models. The approach requires developing automated methods that can translate the high-level models in the reusable KB into low-level specialized models required by a variety of underlying analysis tools, including data manipulation, optimization, statistical learning, estimation, and simulation. We also propose an organization and key structure for the reusable KB, composed of atomic and composite process performance models and domain-specific dashboards. Furthermore, we illustrate the use of the proposed architecture and framework by performing diagnostic tests on a composite process performance model.

A survey of the advancing use and development of machine learning in smart manufacturing

“…Brodsky et al [38] have developed a system for managing a repository and conducting analysis and optimization on manufacturing models in Brodsky et al [39] and Brodsky et al [38], respectively. The former work proposes an architectural design and framework for fast development of software solutions for descriptive, diagnostic, predictive, and prescriptive analytics of dynamic production processes.…”

Factory optima: a web-based system for composition and analysis of manufacturing service networks based on a reusable model repository

“…This unique capability of Factory Optima is achieved by machine generation of mathematical programming models, instead of manually crafting them – a demanding task which is typically outside the skill set of process engineers. This paper can be viewed as a significant extension of the authors’ conference publication (Brodsky et al 2017).…”

“…The proposed approach follows the idea of an architectural design of Brodsky et al (2017) proposed for the fast development of software solutions for descriptive (‘what happened?’), diagnostic (‘why did it happen?’), predictive (‘what will happen?’) and prescriptive (‘how to make it happen optimally?’) analytics of dynamic production processes based on a reusable, modular and extensible knowledge base (KB) of simulation-like process performance models, and machine translatable into MP models. However, Brodsky et al (2017) lacked a systematic design of a UMP repository and its architecture, and an ecosystem around it. Furthermore, the UMP models were abstracted in Brodsky et al (2017) by piecewise-linear functions whereas real-world process models, which are typically physics-based, require non-linear arithmetic.…”

“…However, Brodsky et al (2017) lacked a systematic design of a UMP repository and its architecture, and an ecosystem around it. Furthermore, the UMP models were abstracted in Brodsky et al (2017) by piecewise-linear functions whereas real-world process models, which are typically physics-based, require non-linear arithmetic.…”

“…To overcome this, in Brodsky et al (2017) the authors reported on extending the functionality developed in Brodsky et al (2016a) with a software framework that allows hierarchical composition of service networks based on a reusable model repository for (1) production services, such as manufacturing processes, assembly and inspection and (2) contract services, such as vending, manufacturing, packaging, repair and transportation. However, to compose such service networks and to perform analysis, Brodsky et al (2017) provided a low-level Integrated Development Environment (IDE) user-interface. Such an interface is not suitable for end users such as process engineers and operators, who do not have a software development background.…”