Shop floor simulation optimization using machine learning to improve parallel metaheuristics

2020 ◽  
Vol 150 ◽  
pp. 113272 ◽  
Author(s):  
Wilson Trigueiro de Sousa Junior ◽  
José Arnaldo Barra Montevechi ◽  
Rafael de Carvalho Miranda ◽  
Mona Liza Moura de Oliveira ◽  
Afonso Teberga Campos
Keyword(s):  
Machine Learning ◽  
Simulation Optimization ◽  
Shop Floor ◽  
Parallel Metaheuristics

scholarly journals Efficient and Consumer-Centered Item Detection and Classification with a Multicamera Network at High Ranges

Sensors ◽  
2021 ◽  
Vol 21 (14) ◽  
pp. 4818
Author(s):  
Nils Mandischer ◽  
Tobias Huhn ◽  
Mathias Hüsing ◽  
Burkhard Corves
Keyword(s):  
Machine Learning ◽  
Shop Floor ◽  
Unsupervised Segmentation ◽  
User Friendliness ◽  
Industrial Environment ◽  
Machine Learning Methods ◽  
Eu Project ◽  
Detection And Localization ◽  
Industrial Context ◽  
The Eu

In the EU project SHAREWORK, methods are developed that allow humans and robots to collaborate in an industrial environment. One of the major contributions is a framework for task planning coupled with automated item detection and localization. In this work, we present the methods used for detecting and classifying items on the shop floor. Important in the context of SHAREWORK is the user-friendliness of the methodology. Thus, we renounce heavy-learning-based methods in favor of unsupervised segmentation coupled with lenient machine learning methods for classification. Our algorithm is a combination of established methods adjusted for fast and reliable item detection at high ranges of up to eight meters. In this work, we present the full pipeline from calibration, over segmentation to item classification in the industrial context. The pipeline is validated on a shop floor of 40 sqm and with up to nine different items and assemblies, reaching a mean accuracy of 84% at 0.85 Hz.

An Integrative Machine Learning Method to Improve Fault Detection and Productivity Performance in a Cyber-Physical System

2020 ◽  
Vol 20 (2) ◽  
Author(s):  
Ming-Chuan Chiu ◽  
Chien-De Tsai ◽  
Tung-Lung Li
Keyword(s):  
Machine Learning ◽  
Computational Complexity ◽  
Fault Detection ◽  
Real Time ◽  
Physical System ◽  
Shop Floor ◽  
Cyber Physical System ◽  
Machine Learning Method ◽  
Learning Method ◽  
The Impact

Abstract A cyber-physical system (CPS) is one of the key technologies of industry 4.0. It is an integrated system that merges computing, sensors, and actuators, controlled by computer-based algorithms that integrate people and cyberspace. However, CPS performance is limited by its computational complexity. Finding a way to implement CPS with reduced complexity while incorporating more efficient diagnostics, forecasting, and equipment health management in a real-time performance remains a challenge. Therefore, the study proposes an integrative machine-learning method to reduce the computational complexity and to improve the applicability as a virtual subsystem in the CPS environment. This study utilizes random forest (RF) and a time-series deep-learning model based on the long short-term memory (LSTM) networking to achieve real-time monitoring and to enable the faster corrective adjustment of machines. We propose a method in which a fault detection alarm is triggered well before a machine fails, enabling shop-floor engineers to adjust its parameters or perform maintenance to mitigate the impact of its shutdown. As demonstrated in two empirical studies, the proposed method outperforms other times-series techniques. Accuracy reaches 80% or higher 3 h prior to real-time shutdown in the first case, and a significant improvement in the life of the product (281%) during a particular process appears in the second case. The proposed method can be applied to other complex systems to boost the efficiency of machine utilization and productivity.

scholarly journals Challenges of Machine Learning Applied to Safety-Critical Cyber-Physical Systems

2020 ◽  
Vol 2 (4) ◽  
pp. 579-602
Author(s):  
Ana Pereira ◽  
Carsten Thomas
Keyword(s):  
Machine Learning ◽  
Autonomous Driving ◽  
Cyber Physical Systems ◽  
Shop Floor ◽  
Safety Engineering ◽  
Safety Hazards ◽  
Physical Systems ◽  
Safety Critical ◽  
Holistic Approaches ◽  
Transportation Vehicle

Machine Learning (ML) is increasingly applied for the control of safety-critical Cyber-Physical Systems (CPS) in application areas that cannot easily be mastered with traditional control approaches, such as autonomous driving. As a consequence, the safety of machine learning became a focus area for research in recent years. Despite very considerable advances in selected areas related to machine learning safety, shortcomings were identified on holistic approaches that take an end-to-end view on the risks associated to the engineering of ML-based control systems and their certification. Applying a classic technique of safety engineering, our paper provides a comprehensive and methodological analysis of the safety hazards that could be introduced along the ML lifecycle, and could compromise the safe operation of ML-based CPS. Identified hazards are illustrated and explained using a real-world application scenario—an autonomous shop-floor transportation vehicle. The comprehensive analysis presented in this paper is intended as a basis for future holistic approaches for safety engineering of ML-based CPS in safety-critical applications, and aims to support the focus on research onto safety hazards that are not yet adequately addressed.

Maschinelles Lernen zur Prognose von Auftragskennzahlen/Machine learning for the forecasting of key figures of customer orders

2021 ◽  
Vol 111 (03) ◽  
pp. 124-129
Author(s):  
Markus Böhm ◽  
Klaus Erlach ◽  
Thomas Bauernhansl
Keyword(s):  
Machine Learning ◽  
Complex Systems ◽  
Decision Trees ◽  
Real Time ◽  
Personal Experience ◽  
Shop Floor ◽  
Maschinelles Lernen ◽  
Classification Methods ◽  
Digital Models ◽  
High Expenditure

Prognosen bilden oft die Grundlage für Entscheidungen in der Produktion. Heute werden solche Voraussagen meist erfahrungs- oder modellbasiert getroffen. Bei komplexen Systemen stößt das an die Grenzen der Zuverlässigkeit oder ist mit hohem zeitlichen Aufwand verbunden. Klassierungsmethoden des Maschinellen Lernens versprechen dafür Lösungen. Automatisch erstellte Entscheidungsbäume können eine Möglichkeit sein, echtzeitnah Prognosen für Kennzahlen in der Produktion zu erstellen.   Forecasts often form the basis for decisions on the shop floor. Today, forecasts in production are mostly derived from personal experience or digital models. With complex systems, this approach reaches the limits of reliability or is associated with a high expenditure of time. Classification methods of machine learning promise solutions for this. Automatically generated decision trees can be a possibility to generate real-time forecasts for key figures in production.

scholarly journals Simulation, Optimization, and Machine Learning in Sustainable Transportation Systems: Models and Applications

2021 ◽  
Vol 13 (3) ◽  
pp. 1551
Author(s):  
Rocio de la Torre ◽  
Canan G. Corlu ◽  
Javier Faulin ◽  
Bhakti S. Onggo ◽  
Angel A. Juan
Keyword(s):  
Machine Learning ◽  
Social Impact ◽  
Simulation Optimization ◽  
Transportation Systems ◽  
Sustainable Transportation ◽  
Long Distance ◽  
Policy Makers ◽  
Systems Models

The need for effective freight and human transportation systems has consistently increased during the last decades, mainly due to factors such as globalization, e-commerce activities, and mobility requirements. Traditionally, transportation systems have been designed with the main goal of reducing their monetary cost while offering a specified quality of service. During the last decade, however, sustainability concepts are also being considered as a critical component of transportation systems, i.e., the environmental and social impact of transportation activities have to be taken into account when managers and policy makers design and operate modern transportation systems, whether these refer to long-distance carriers or to metropolitan areas. This paper reviews the existing work on different scientific methodologies that are being used to promote Sustainable Transportation Systems (STS), including simulation, optimization, machine learning, and fuzzy sets. This paper discusses how each of these methodologies have been employed to design and efficiently operate STS. In addition, the paper also provides a classification of common challenges, best practices, future trends, and open research lines that might be useful for both researchers and practitioners.

Sign in / Sign up

Export Citation Format

Share Document