A Hybrid Expert Decision Support System Based on Artificial Neural Networks in Process Control of Plaster Production – An Industry 4.0 Perspective

Abstract : Emerging technologies could affect future of factories and smartness is the main trend to receive that points. Quality was important and will be crucial in future but the question is how to build Smart Systems to guaranty quality in workshop level. This is an important challenge in Industry 4.0 paradigm. In this paper the main objective is to present practical solution under the light of Industry 4.0. The aim of this study is to presents propose a Hybrid Expert Decision Support System (EDSS) model, which integrates Neural Network (NN) and Expert System (ES) to detect unnatural CCPs and to estimate the corresponding parameters and starting point of the detected CCP. For this purpose, Learning Vector Quantization (LVQ) and Multi-Layer Perceptron (MLP) networks architecture have been designed to identify unnatural CCPs. Moreover, a rule based ES has been developed for diagnosing causes of process variations and subsequently recommending corrective action. The proposed model was successfully implemented in Construction Plaster producing company to demonstrate the capabilities and applicability of the model.
Document type :
Conference papers
Complete list of metadatas

Cited literature [27 references]  Display  Hide  Download

https://hal.inria.fr/hal-01629563
Contributor : Hal Ifip <>
Submitted on : Monday, November 6, 2017 - 3:28:40 PM
Last modification on : Thursday, October 10, 2019 - 2:50:08 PM

File

448071_1_En_5_Chapter.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Javaneh Ramezani, Javad Jassbi. A Hybrid Expert Decision Support System Based on Artificial Neural Networks in Process Control of Plaster Production – An Industry 4.0 Perspective. 8th Doctoral Conference on Computing, Electrical and Industrial Systems (DoCEIS), May 2017, Costa de Caparica, Portugal. pp.55-71, ⟨10.1007/978-3-319-56077-9_5⟩. ⟨hal-01629563⟩

Share

Metrics

Record views

78