A step forward on intelligent factories: A Smart Sensor-oriented approach

Gonçalves, Gil; Reis, Joao; Pinto, Rui; Alves, Marco; Correia, J.

doi:10.1109/etfa.2014.7005227

Cited by 21 publications

(7 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Adding (or removing) an MLA would increase (or decrease) the number of combinations to be evaluated. The Six Sigma approach or reaching of the maximum possible level in an organization is a business strategy, which summarized includes financial benefits, increased productivity, and a better customer satisfaction [59].…”

Section: Limitations Recommendations and Managerial Insightsmentioning

confidence: 99%

Process monitoring for quality — A multiple classifier system for highly unbalanced data

Escobar

Macias

2021

Heliyon

View full text Add to dashboard Cite

In big data-based analyses, because of hyper-dimensional feature spaces, there has been no previous distinction between machine learning algorithms (MLAs). Therefore, multiple diverse algorithms should be included in the analysis to develop an adequate model for detecting/recognizing patterns exhibited by classes. If multiple classifiers are developed, the next natural step is to determine whether the prediction benchmark set by the top performer can be improved by combining them. In this context, multiple classifier systems (MCSs) are powerful solutions for difficult pattern recognition problems because they usually outperform the best individual classifier, and their diversity tends to improve resilience and robustness to high-dimensional and noisy data. To design an MCS, an appropriate fusion method is required to optimally combine the individual classifiers and determine the final decision. Process monitoring for quality is a Quality 4.0 initiative aimed at defect detection via binary classification. Because most mature organizations have merged traditional quality philosophies, their processes generate only a few defects per million of opportunities. Therefore, manufacturing data sets for binary classification of quality tends to be highly/ ultra-unbalanced. Detecting these rare quality events is one of the most relevant intellectual challenges posed to the fourth industrial revolution, Industry 4.0 (I 4.0). A new MCS aimed at analyzing these data structures is presented. It is based on eight well-known MLAs, an ad hoc fitness function, and a novel meta-learning algorithm. For predicting the final quality class, this algorithm considers the prediction from a set of classifiers as input and determines which classifiers are reliable and which are not. Finally, to demonstrate the superiority of the MLAs over extensively used fusion rules, multiple publicly available data sets are analyzed.

show abstract

Section: Limitations Recommendations and Managerial Insightsmentioning

confidence: 99%

Process monitoring for quality — A multiple classifier system for highly unbalanced data

Escobar

Macias

2021

Heliyon

View full text Add to dashboard Cite

show abstract

“…The smart sensor enables compatible operation within different data networks supported through communication interface between sensing unit and processors, multi-compatibility with different sensor and actuator bus standards as well as interconnection of analogue transducers with digital networks (Gonçalves, Reis, Pinto, Alves, & Correia, 2014) Distributed control (network) Control network: means of logically intersecting nodes, using low-level and high-level concepts (for example network management and addressing). (Valente, Mazzolini, & Carpanzano, 2015) Self-monitoring devices/ machines Equipped with main processing unit incorporating computer and interrupt processing unit regularly interrupting program operation by the main processing unit.…”

Section: Smart Sensorsmentioning

confidence: 99%

Innovation landscape and challenges of smart technologies and systems – a European perspective

Micheler

Goh

Lohse

2019

Production & Manufacturing Research

View full text Add to dashboard Cite

Smart technologies with higher degrees of autonomy will be essential to achieve the next breakthrough in both agility and productivity in future manufacturing systems, often referred to as Industry 4.0. However, the technologies will also bring substantial design and integration challenges and novelty risks to manufacturing businesses. The aim of this paper is to analyse the current landscape and to identify the challenges for introducing smart technologies into manufacturing systems in Europe. Expert knowledge from both industrial and academic practitioners in the field was extracted using an online survey. A workshop was used to triangulate and extend the survey results. The findings indicate three main challenges for the ubiquitous implementation of smart technologies in manufacturing are: i) the perceived risk of novel technologies, ii) the complexity of integration, and iii) the consideration of human factors. Recommendations are made based on these findings to transform the landscape for smart manufacturing. ARTICLE HISTORY

show abstract

“…The I-RAMP 3 -Intelligent reconfigurable machines for smart plug-and-produce production-project (Goncalves et al, 2014) focused on the transformation of conventional production equipment into network-enabled devices (NETDEVs). The NETDEV interface enables the integration of plug-and-produce devices and sensors and actuators at MES level for work flow optimization and production data assessment, using standardized communication and collaboration mechanisms.…”

Section: Emerging Automation System Architecturesmentioning

confidence: 99%

Engineering of Next Generation Cyber-Physical Automation System Architectures

Foehr

Vollmar

Calà

et al. 2017

Multi-Disciplinary Engineering for Cyber-Physical Production Systems

View full text Add to dashboard Cite

Cyber-Physical-Systems (CPS) enable flexible and reconfigurable realization of automation system architectures, utilizing distributed control architectures with non-hierarchical modules linked together through different communication systems. Several control system architectures have been developed and validated in the past years by research groups. However, there is still a lack of implementation in industry. The intention of this work is to provide a summary of current alternative control system architectures that could be applied in industrial automation domain as well as a review of their commonalities. The aim is to point out the differences between the traditional centralized and hierarchical architectures to discussed ones, which rely on decentralized decision-making and control. Challenges and impacts that industries and engineers face in the process of adopting decentralized control architectures are discussed, analysing the obstacles for industrial acceptance and the new necessary interdisciplinary engineering skills. Finally, an outlook of possible mitigation and migration actions required to implement the decentralized control architectures is addressed.

show abstract

A step forward on intelligent factories: A Smart Sensor-oriented approach

Cited by 21 publications

References 9 publications

Process monitoring for quality — A multiple classifier system for highly unbalanced data

Process monitoring for quality — A multiple classifier system for highly unbalanced data

Innovation landscape and challenges of smart technologies and systems – a European perspective

Engineering of Next Generation Cyber-Physical Automation System Architectures

Contact Info

Product

Resources

About