Towards an ontological infrastructure for chemical batch process management

Abstract

a b s t r a c t A crucial step for batch process improvement and optimization is to develop information structures that streamline data gathering and, above all, are capable of integrating transactional data into a system using the analytical tools that are developed. Current trends in electronics, computer science, artificial intelligence and control system technology are providing technical capability that greatly facilitates the development of multilevel decision-making support. In this paper, we present the batch process ontology (BaPrOn), wherein different concepts regarding batch processes are categorized and the relationships between them are examined and structured in accordance with ANSI/ISA-88 standards, which provide a solid and transparent framework for integrating batch-related information. This paper also focuses on systematic integration of different actors within the control process. The proposed approach bases the conceptualization through the ANSI/ISA-88 representation, providing the advantage of establishing a more general conceptualization of the batch process domain. The capabilities of the envisaged ontological framework were assessed in a test bed PROCEL pilot plant: scheduling-monitoring and control-rescheduling was closed, information quality was accessed by knowledge description, and an optimum decision-making task was performed. The ontological structure can be extended in the future to incorporate other hierarchical levels and their respective modeling knowledge.

The promise of artificial intelligence in chemical engineering: Is it here, finally?

“…Ontology is the most recent avatar in a long series of knowledge representation concepts, starting with predicate and propositional calculus in the 1940s, semantic networks in the 1960s, frames in the 1970s, and objects in the 1980s. While there has been some work recently on ontologies in process engineering, much more remains to be done, particularly for materials design. In this regard, the material science repository, Novel Materials Discovery Laboratory, and the use of text‐mining to discover interesting relationships among material science concepts are promising developments.…”

“…These include: graph‐theoretical models (as noted, used extensively to perform causal reasoning in the identification of abnormal events, diagnosis, and risk analysis rule‐based production system models (used in expert systems for automating higher‐order reasoning), semantic network models such as ontologies (used in materials discovery and design, domain‐specific compilers, and so forth), and object‐oriented models such as agent‐based models (used in simulating the behavior and decision‐making choices of independent, interacting, entities endowed with complex attributes and decision‐making powers). In addition, there are the data‐driven quantitative models such as pattern recognition‐based models (e.g., neural nets, fuzzy logic), stochastic models (e.g., genetic algorithm, simulated annealing), and so forth.…”

Modelling Decision Support Systems using Conceptual Constraints - Linking Process Systems Engineering and Decision Making Models

“…In the case of PSE, the extensive exploitation of general PSE ontologies to support the development and maintenance of models, as well as their integration and coordination with system/models from the related areas/domains is object of growing interest (Morbach et al, 2007, Muñoz et al, 2010,Roda and Musulin, 2014,Remolona et al, 2017. The research on these application has supported the management of the great amount of information related to the problem statement and the new exploitations has supported development and (re)used of conceptual models.…”

“…The interdisciplinary area of PSE and KE, different methodologies have been developed which centre on the creation of domain knowledge. The batch process ontology (BaPrOn) is built from the concepts of a batch control standard (ISA88) and used in order to monitor and control the scheduling in a pilot plant (Muñoz et al, 2010). The intention of not just communicating but also supporting the integration of different software tools and exploitation of plant database information are also considered (Muñoz et al, 2012).…”

“…The PSE community uses conceptualized modelling in order to support systematic problem solving. Recently, ontological modelling has been used to build semantic structures, while Knowledge Engineering (KE) foundations have been implemented as a new modelling paradigm with the purpose of supporting chemical process engineering (Morbach et al, 2007), managing chemical batch processes (Muñoz et al, 2010), data reconciliation (Roda and Musulin, 2014), pharmaceutical product engineering (Remolona et al, 2017), etc. In addition, there are other communities working on similar issues that PSE attempts to solve (e.g.…”