Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.7
3.5
Journals
Processes
Special Issues
Application of Machine Learning and Predictive Analytics in Industrial Processes
share announcement

Application of Machine Learning and Predictive Analytics in Industrial Processes

A special issue of Processes (ISSN 2227-9717). This special issue belongs to the section "Process Control and Monitoring".

Deadline for manuscript submissions: closed (15 February 2021) | Viewed by 8816

Special Issue Editor

Dr. Seung-Jun Shin

E-Mail Website
Guest Editor
Division of Interdisciplinary Industrial Studies, Hanyang University, Seoul 04763, Korea
Interests: smart manufacturing; cyber-physical production systems; Big Data analytics in manufacturing; environmentally-conscious manufacturing; industrial digital threads

Special Issue Information

Dear Colleagues,

Smart manufacturing has been recognized as a leading-edge trend across industries to implement industrial intelligence for real-time understanding, reasoning, planning, and management of industrial processes with the pervasive use of sensor-based data analytics. Predictive analytics provides humans and systems with the capability of foresights by anticipating target values through learning and mining industrial data and allows for proactive planning, operation, and control, thereby contributing to increase flexibility, productivity, and sustainability in industrial systems. Predictive analytics largely relies on data-driven learning approaches such as machine learning, reinforcement learning, and transfer learning, and thus, predictive analytics and machine learning are an inseparable relation. The main advantage of predictive analytics is to produce more accurate and reliable prediction models specific for target machines, products, and applications than those of theoretical and simulated methodologies. We believe that industrial systems will further evolve toward industrial autonomy, which realizes autonomous and cooperative planning, operation, and control by machines with the collaboration of humans, through using and applying predictive analytics in real fields.

This Special Issue on “Application of Machine Learning and Predictive Analytics in Industrial Processes” aims to collect high-quality research studies addressing challenges on the broad area of predictive planning, operation, and control in standalone or platform-based industrial systems. Topics include but are not limited to the following:

  • Theory and application of machine learning approaches;
  • Theory and application of transfer learning approaches;
  • Theory and application of reinforcement learning approaches;
  • Predictive analytics and predictive modeling;
  • Supervised and unsupervised learning;
  • Predictive simulation methods;
  • Uncertainty quantification and prediction;
  • On-demand and proactive supply chain resilience;
  • Big data analytics systems;
  • Data and model interoperability;
  • Modeling languages for data analytics.

Dr. Seung-Jun Shin
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Processes is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Predictive analytics
  • Predictive modeling
  • Big data analytics
  • Predictive planning, operation and control
  • Cyberphysical production systems
  • Industrial intelligence
  • Machine learning
  • Transfer learning
  • Reinforcement learning

Published Papers (3 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

14 pages, 3184 KiB  
Article
Automatic Control System for Cane Honey Factories in Developing Country Conditions
by Víctor Cerda Mejía, Galo Cerda Mejía, Octavio Guijarro Rubio, Isnel Benítez Cortes, Estela Guardado Yordi, Bernabe Ortega Tenezaca, Juan Miño Valdés, Erenio González Suárez and Amaury Pérez Martínez
Processes 2022, 10(5), 915; https://0-doi-org.brum.beds.ac.uk/10.3390/pr10050915 - 06 May 2022
Cited by 1 | Viewed by 1933
Abstract
(1) Background: A proposal for the automatic control of sugar cane honey factories based on simulation with real data is presented. (2) Methods: The P&ID diagram of the artisanal process is designed, as well as the measurement and control systems of the different [...] Read more.
(1) Background: A proposal for the automatic control of sugar cane honey factories based on simulation with real data is presented. (2) Methods: The P&ID diagram of the artisanal process is designed, as well as the measurement and control systems of the different process variables. A data acquisition and monitoring system is proposed with all the required equipment. Using GNU Octave software, the process was simulated, where the transfer functions and parameters of the different stages were determined. The transient responses of these systems are determined before step-jump type disturbances, as well as that of the controllers. (3) Results: A correct adjustment of the controllers is obtained, indicating those that work in a stable way before disturbance variations in the real ranges of plant work. (4) Conclusions: Simulation of controllers before different forcing functions in the ranges of the operating parameters allowed for establishing dynamic responses of each one, demonstrating that they are capable of adjusting the value of the variable of interest or the control, and determining control of the main operating variables. Full article
(This article belongs to the Special Issue Application of Machine Learning and Predictive Analytics in Industrial Processes)
►▼ Show Figures

Figure 1

16 pages, 5205 KiB  
Article
Mapping Uncertainties of Soft-Sensors Based on Deep Feedforward Neural Networks through a Novel Monte Carlo Uncertainties Training Process
by Erbet A. Costa, Carine M. Rebello, Vinicius V. Santana, Alírio E. Rodrigues, Ana M. Ribeiro, Leizer Schnitman and Idelfonso B. R. Nogueira
Processes 2022, 10(2), 409; https://0-doi-org.brum.beds.ac.uk/10.3390/pr10020409 - 19 Feb 2022
Cited by 3 | Viewed by 1425
Abstract
Data-driven sensors are techniques capable of providing real-time information of unmeasured variables based on instrument measurements. They are valuable tools in several engineering fields, from car automation to chemical processes. However, they are subject to several sources of uncertainty, and in this way, [...] Read more.
Data-driven sensors are techniques capable of providing real-time information of unmeasured variables based on instrument measurements. They are valuable tools in several engineering fields, from car automation to chemical processes. However, they are subject to several sources of uncertainty, and in this way, they need to be able to deal with uncertainties. A way to deal with this problem is by using soft sensors and evaluating their uncertainties. On the other hand, the advent of deep learning (DL) has been providing a powerful tool for the field of data-driven modeling. The DL presents a potential to improve the soft sensor reliability. However, the uncertainty identification of the soft sensors model is a known issue in the literature. In this scenario, this work presents a strategy to identify the uncertainty of DL models prediction based on a novel Monte Carlo uncertainties training strategy. The proposed methodology is applied to identify a Soft Sensor to provide a real-time prediction of the productivity of a chemical process. The results demonstrate that the proposed methodology can yield a soft sensor based on DL that provides reliable predictions, with precision being proven by its corresponding coverage region. Full article
(This article belongs to the Special Issue Application of Machine Learning and Predictive Analytics in Industrial Processes)
►▼ Show Figures

Figure 1

18 pages, 7228 KiB  
Article
Machine Learning-Based Dynamic Modeling for Process Engineering Applications: A Guideline for Simulation and Prediction from Perceptron to Deep Learning
by Carine M. Rebello, Paulo H. Marrocos, Erbet A. Costa, Vinicius V. Santana, Alírio E. Rodrigues, Ana M. Ribeiro and Idelfonso B. R. Nogueira
Processes 2022, 10(2), 250; https://0-doi-org.brum.beds.ac.uk/10.3390/pr10020250 - 27 Jan 2022
Cited by 8 | Viewed by 4825
Abstract
A misusage of machine learning (ML) strategies is usually observed in the process systems engineering literature. This issue is even more evident when dynamic identification is performed. The root of this problem is the gradient explode and vanishing issue related to the recurrent [...] Read more.
A misusage of machine learning (ML) strategies is usually observed in the process systems engineering literature. This issue is even more evident when dynamic identification is performed. The root of this problem is the gradient explode and vanishing issue related to the recurrent neural networks training. However, after the advent of deep learning, these issues were mitigated. Furthermore, the problem of data structuration is often overlooked during the machine learning model identification in this field. In this scenario, this work proposes a guideline for identifying ML models for the different applications in process systems engineering, which are usually for simulation or prediction purposes. While using the proposed guideline, the work also identifies a virtual analyzer for a pressure swing adsorption unit. In these types of adsorption separations, it is usual that the measurement of the main properties is not done online. Therefore, the virtual analyzer is another contribution of this manuscript. The overall results demonstrate that even though the test provides good performance during the ML model identification, its quality might degenerate over the application domain if the model application is overlooked. Full article
(This article belongs to the Special Issue Application of Machine Learning and Predictive Analytics in Industrial Processes)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-3
Back to TopTop