Our latest research work is now online, contributing to the research comunity and sharing knowledge is the key towards #sustainability. We support open access publications in order to be avaialbe to anyone, our research work can be downloaded from here:
The global transition from traditional manufacturing systems to #Industry4 compatible systems has already begun. Therefore, the #digitization of the manufacturing systems across the globe is increasing with exponential growth which implies a significant increase in the volume and variety of the generated data. #Industry4 technologies are mostly #data driven and therefore, manufacturers need to be equipped with the appropriate tools and skill sets to extract useful knowledge and insights from the plethora of data continually collected form shop floors. Lack of syntactic and semantic interoperability among heterogenous systems and organizations is a major barrier to efficient collaboration and information exchange. #Interoperability can be defined as the ability of two or more heterogeneous, yet relevant, systems to communicate, correctly interpret, and act on information meaningfully and accurately with minimal effort. Governments and industry often tackle the interoperability challenge through the vehicle of #standards. Unfortunately, the traditional standards-based approaches for achieving interoperability are expensive and slow . Additionally, standards are brittle since they are often developed based on singular viewpoints of the world, and therefore, they are valid only in specific domains and contexts.
#Ontologies provide an opportunity to resolve problems of both syntactic and #semantic #interoperability by providing a systematically curated body of #vocabulary and formal definition to support consistent exchange of data among humans and machines. Another advantage of ontologies is using logic-based models which make ontological entities unambiguous and readable both for humans and machines. In contrast to standards that follow a lengthy and often complex development and approval process, ontologies can be developed and tested in a more agile manner and can provide cross-domain viewpoints. Additionally, ontologies can be implemented incrementally to realize the benefits from enhanced interoperability even at very early stages of ontology development process . Common, consensus-based ontologies have proven themselves in various domains, including the domains of biomedical and biology and financial business applications, as effective solutions for achieving interoperability. In the industrial domain, in contrast, the use of ontologies has not lived up to initial expectations associated for example with ontoSTEP and similar initiatives from the early 2000 s
Furthermore, #quality #assurance is a key domain in manufacturing that uses almost all the industry 4.0 technologies and has great impact on the sustainability of a manufacturing systems. The latest approach to higher quality and manufacturing sustainability is named Zero Defect Manufacturing (#ZDM). #ZDM interest has spiked the last three years illustrating the need for an alternative quality assurance approach from the traditional such as Six Sigma and Lean manufacturing. ZDM is a critical approach that heavily is depending on data and collaboration of multiverse software applications which can significantly benefit from ontologies and data semantics. Currently, there is no ontology that covers the ZDM domain. Therefore, the goal and novelty of the research reported in this paper is to create a ZDM ontology that can semantically align multiple software systems that interact in a ZDM ecosystem. The development of the proposed ZDM ontology was performed using the principles introduced by Industrial Ontology Foundry (IOF) and with the use of Basic formal ontology (BFO) as an upper-level ontology. The developed ontology was validated based on a real industrial case.
Therefore, the goal of this paper is to create a #ZDM #ontology that can #semantically align multiple software systems that interact in a ZDM ecosystem. The development of the proposed ZDM ontology was performed using the principles introduced by Industrial Ontology Foundry (IOF) and with the use of Basic formal ontology (BFO) as an upper level ontology. The proposed ontology was utilized in the Prediction Optimization Designer tool developed, to assist developers to create new projects reusing existing resources, or to respond to a specific challenge. The use case validation results show that the combination of Natural Language Processing (NLP) using Sentence-BERT and ontology-based search methods rooted in the ZDM ontology is a promising strategy to implement effective search engines for applications in the ZDM domain.
Comments