SKOS Tool: A Tool for Creating Knowledge Graphs to Support Semantic Text Classification

Ameri, Farhad; Yoder, Reid; Zandbiglari, Kimia

doi:10.1007/978-3-030-57997-5_31

Cited by 6 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A reconfigurable assembly line DT model that uses ontology to describe the properties of the virtual layer's five dimensions, namely geometric, rule, behavior, physical, and capability, was proposed in Reference [52]. Many organizations, however, do not have ontologies, as most ontology development approaches proposed in the literature have had very limited acceptability in industry [22,23]. We propose mining fault events and their effects directly from qualitative data sources, such as maintenance log data (or maintenance work order (MWO)), and corrective and preventive action (CAPA) report in this work.…”

Section: Digital Twinmentioning

confidence: 99%

“…Therefore, we first propose a method to develop a multistage manufacturing system DT model specifically for multiclass fault diagnostics. Given that an ontology is usually required to develop an effective DT model for fault diagnostics but many organizations do not currently have an ontology [22,23], our proposed method utilizes natural language processing (NLP) data-tagging technique to mine the fault cause-and-effect relationships directly from maintenance log data. Additionally, considering the challenge of developing high-fidelity simulation models that mimic the behavior of a machine with fine granularity, we utilized co-simulation of original equipment manufacturer (OEM) simulator and discrete-event simulation (DES) model to actualize a DT model.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Digital Twin for Training Bayesian Networks for Fault Diagnostics of Manufacturing Systems

Ademujimi

Prabhu

2022

Sensors

View full text Add to dashboard Cite

Smart manufacturing systems are being advocated to leverage technological advances that enable them to be more resilient to faults through rapid diagnosis for performance assurance. In this paper, we propose a co-simulation approach for engineering digital twins (DTs) that are used to train Bayesian Networks (BNs) for fault diagnostics at equipment and factory levels. Specifically, the co-simulation model is engineered by using cyber–physical system (CPS) consisting of networked sensors, high-fidelity simulation model of each equipment, and a detailed discrete-event simulation (DES) model of the factory. The proposed DT approach enables injection of faults in the virtual system, thereby alleviating the need for expensive factory-floor experimentation. It should be emphasized that this approach of injecting faults eliminates the need for obtaining balanced data that include faulty and normal factory operations. We propose a Structural Intervention Algorithm (SIA) in this paper to first detect all possible directed edges and then distinguish between a parent and an ancestor node of the BN. We engineered a DT research test-bed in our laboratory consisting of four industrial robots configured into an assembly cell where each robot has an industrial Internet-of-Things sensor that can monitor vibrations in two-axes. A detailed equipment-level simulator of these robots was integrated with a detailed DES model of the robotic assembly cell. The resulting DT was used to carry out interventions to learn a BN model structure for fault diagnostics. Laboratory experiments validated the efficacy of the proposed approach by accurately learning the BN structure, and in the experiments, the accuracy obtained by the proposed approach (measured using Structural Hamming Distance) was found to be significantly better than traditional methods. Furthermore, the BN structure learned was found to be robust to variations in parameters, such as mean time to failure (MTTF).

show abstract

Section: Digital Twinmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Digital Twin for Training Bayesian Networks for Fault Diagnostics of Manufacturing Systems

Ademujimi

Prabhu

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Only a few researchers have created BN from ontology in manufacturing domain. This is partly because creating an ontology itself is not an easy task and most approaches proposed in the literature have had limited practical success due to lack of scalability and interoperability, resulting in limited domain-wide acceptability [41,42].…”

Section: Background and Literature Reviewmentioning

confidence: 99%

Fusion-Learning of Bayesian Network Models for Fault Diagnostics

Ademujimi

Prabhu

2021

Sensors

View full text Add to dashboard Cite

Bayesian Network (BN) models are being successfully applied to improve fault diagnosis, which in turn can improve equipment uptime and customer service. Most of these BN models are essentially trained using quantitative data obtained from sensors. However, sensors may not be able to cover all faults and therefore such BN models would be incomplete. Furthermore, many systems have maintenance logs that can serve as qualitative data, potentially containing historic causation information in unstructured natural language replete with technical terms. The motivation of this paper is to leverage all of the data available to improve BN learning. Specifically, we propose a method for fusion-learning of BNs: for quantitative data obtained from sensors, metrology data and qualitative data from maintenance logs, corrective and preventive action reports, and then follow by fusing these two BNs. Furthermore, we propose a human-in-the-loop approach for expert knowledge elicitation of the BN structure aided by logged natural language data instead of relying exclusively on their anecdotal memory. The resulting fused BN model can be expected to provide improved diagnostics as it has a wider fault coverage than the individual BNs. We demonstrate the efficacy of our proposed method using real world data from uninterruptible power supply (UPS) fault diagnostics.

show abstract

Application of neural network language models based on distributive semantics for ontological modeling of the domain

Shishaev

Dikovitsky

Pimeshkov

2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The article discusses the technology of automated formation of SKOS-ontologies for semantic modeling of the subject area, based on natural language texts analysis. The technology is based on neural network and distributive (vector) language models. A brief description of the content and formulation of the problem of extracting concepts and relations from natural language texts is given, the results of constructing a neural network classifier of SKOS relations using the Glove vector model, as well as an example of using the technology to construct a fragment of an applied SKOS ontology are given.

show abstract

SKOS Tool: A Tool for Creating Knowledge Graphs to Support Semantic Text Classification

Cited by 6 publications

References 7 publications

Digital Twin for Training Bayesian Networks for Fault Diagnostics of Manufacturing Systems

Digital Twin for Training Bayesian Networks for Fault Diagnostics of Manufacturing Systems

Fusion-Learning of Bayesian Network Models for Fault Diagnostics

Application of neural network language models based on distributive semantics for ontological modeling of the domain

Contact Info

Product

Resources

About