Condition monitoring in Industry 4.0 production systems - the idea of computational intelligence methods application

Żabiński, Tomasz; Mączka, Tomasz; Kluska, Jacek; Madera, Michał; Sęp, Jarosław

doi:10.1016/j.procir.2019.02.012

Cited by 32 publications

(14 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The perceptron, first introduced by Rosenblatt [46], is the fundamental unit of artificial neural networks, just as the neuron is the fundamental unit of our central nervous system. Hence, it conforms the basis of advanced ML methods that are used on several real-life applications on Industry 4.0, such as smart manufacturing [47], condition monitoring [48], material selection [49], building occupancy prediction [50], among others. In the basic applications of Machine Learning, the Simple Perceptron is used as a supervised binary classifier [51], and it has four parts:…”

Section: Simple Perceptronmentioning

confidence: 90%

Education 4.0: Teaching the Basics of KNN, LDA and Simple Perceptron Algorithms for Binary Classification Problems

et al. 2021

View full text Add to dashboard Cite

One of the main focuses of Education 4.0 is to provide students with knowledge on disruptive technologies, such as Machine Learning (ML), as well as the skills to implement this knowledge to solve real-life problems. Therefore, both students and professors require teaching and learning tools that facilitate the introduction to such topics. Consequently, this study looks forward to contributing to the development of those tools by introducing the basic theory behind three machine learning classifying algorithms: K-Nearest-Neighbor (KNN), Linear Discriminant Analysis (LDA), and Simple Perceptron; as well as discussing the diverse advantages and disadvantages of each method. Moreover, it is proposed to analyze how these methods work on different conditions through their implementation over a test bench. Thus, in addition to the description of each algorithm, we discuss their application to solving three different binary classification problems using three different datasets, as well as comparing their performances in these specific case studies. The findings of this study can be used by teachers to provide students the basic knowledge of KNN, LDA, and perceptron algorithms, and, at the same time, it can be used as a guide to learn how to apply them to solve real-life problems that are not limited to the presented datasets.

show abstract

Section: Simple Perceptronmentioning

confidence: 90%

Education 4.0: Teaching the Basics of KNN, LDA and Simple Perceptron Algorithms for Binary Classification Problems

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The analysis is based on dividing machine programs into operations and studying the resultant time series. In recent years, time series techniques have begun to be used in the context of machine tools [16,17].…”

Section: Methodsmentioning

confidence: 99%

Machine Tools Anomaly Detection Through Nearly Real-Time Data Analysis

Herranz

Antolínez

Escartin

et al. 2019

JMMP

View full text Add to dashboard Cite

This work presents a new methodology for machine tools anomaly detection via operational data processing. The previous methodology has been field tested on a milling-boring machine in a real production environment. This paper also describes the data acquisition process, as well as the technical architecture needed for data processing. Subsequently, a technique for operational machine data segmentation based on dynamic time warping and hierarchical clustering is introduced. The formerly mentioned data segmentation and analysis technique allows for machine tools anomaly detection thanks to comparison between near real-time machine operational information, coming from strategically positioned sensors and outcomes collected from previous production cycles. Anomaly detection techniques shown in this article could achieve significant production improvements: “zero-defect manufacturing”, boosting factory efficiency, production plans scrap minimization, improvement of product quality, and the enhancement of overall equipment productivity.

show abstract

“…When utilizing machines, there is and will be a need for condition monitoring and try to identify possible machine faults before they cause unbearable costs. As described in Zabinski et al (2019), condition monitoring systems mainly deals with, monitoring and feature extraction, real-time anomaly detection and fault diagnosis [23]. Expert systems and rule based reasoning mechanisms, neural networks and deep learning methods as well as intelligent agents can be extensively used for monitoring the machines and process for possible anomalies and faults.…”

Section: Quality Operations During Execution Of Manufacturing Processesmentioning

confidence: 99%

Introduction to Intelligent Quality Management

Öztemel¹

2021

Quality Control - Intelligent Manufacturing, Robust Design and Charts

View full text Add to dashboard Cite

Intelligent manufacturing is becoming more and more attractive for industrial societies especially after the introduction of industry 4.0 where most of industrial operations are to be carried by robots equipped with intelligent capabilities. This explicitly implies that the manufacturing systems will entirely be integrated and all manufacturing functions including quality control and management will have to be made as much intelligent as possible in operating with minimum human intervention. This Chapter will present a brief overview of some implications about intelligent quality systems. It intends to provide the readers of the book to understand how the concept of artificial intelligence is to be embedded into quality functions. It is known that the interoperability is the rapid transformation requirement of industry specific operations. This requires the integration of quality functions to other manufacturing functions for sharing the quality related knowledge with other manufacturing functions in order to sustain total intelligent collaboration. Achieving this, on the other hand, ensures the improvement of manufacturing processes for better performance in an integrated manner. Note that, although some general information about intelligent manufacturing systems are given, this chapter is particularly focused on discussing intelligent quality related issues.

show abstract

Condition monitoring in Industry 4.0 production systems - the idea of computational intelligence methods application

Cited by 32 publications

References 6 publications

Education 4.0: Teaching the Basics of KNN, LDA and Simple Perceptron Algorithms for Binary Classification Problems

Education 4.0: Teaching the Basics of KNN, LDA and Simple Perceptron Algorithms for Binary Classification Problems

Machine Tools Anomaly Detection Through Nearly Real-Time Data Analysis

Introduction to Intelligent Quality Management

Contact Info

Product

Resources

About