Showing papers in "IFAC-PapersOnLine in 2018"

TL;DR: It is shown, that literature concerning the highest development stage, the DT, is scarce, whilst there is more literature about DM and DS.

TL;DR: Wang et al. as discussed by the authors improved the You Only Look Once (YOLO) network and made it all convolutional, which consists of 27 convolution layers, providing an end-to-end solution for the surface defects detection of steel strip.

TL;DR: An explorative study to reflect on the role of digital twins to support decisionmaking in asset lifecycle management and of potentials for decision support offered by Digital Twin modeling.

TL;DR: The modified LSTM model proposed in this paper is much better than the other existing neural models and two non-linear system examples are used to compare the neural modeling with other well known methods.

TL;DR: In this paper, the authors conduct a qualitative literature review in order to investigate the current state of these innovative technologies and their practical application in industrial systems defining their core characteristics, and propose a framework for workforce training using augmented and virtual reality.

TL;DR: Deep neural networks are applied to the problem of fault detection and classification to illustrate their capability, and the results obtained are compared with other data-driven methods to illustrate the advantages of deep neural networks.

TL;DR: The present paper attempts to address issues by reviewing recent literature in the field and by providing relevant analysis and recommendations on the benefit of using FOPID controllers.

TL;DR: To develop a machine vision system for harvesting robot which can work all day, kiwifruit images were captured in an orchard at different timing, morning, afternoon, and night, with or without flash, and it suggested that the proposed method achieved higher detection average precision than ZFNet.

TL;DR: In this paper, a review of multi-agent collective behavior algorithms in the literature and classification of them according to their underlying mathematical structure is presented. And the authors highlight how versatile techniques such as artificial potential functions can be used for applications ranging from low-level position control to high-level coordination and task allocation, and discuss possible reasons for the slow adoption of complex distributed coordination algorithms.

TL;DR: In this paper, the authors conduct a scope literature review to investigate the role of maintenance for sustainable manufacturing, with particular focus on the 4th industrial revolution and the enabling technologies 40, with the aim of identifying future research directions in this field.

TL;DR: An illustration of a new digital maturity assessment approach - 360 Digital Maturity Assessment - which is based on the Problem Based Learning (PBL) model is provided.

TL;DR: In this article, the authors present acados, a new software package for model predictive control, which provides a collection of embedded optimization algorithms written in C, with a strong focus on computational efficiency.

TL;DR: The implications of optimally coordinating vehicles that are wirelessly connected to each other in roundabouts to achieve a smooth traffic flow are investigated and an optimization framework and an analytical solution that allows optimal coordination of vehicles for merging in such traffic scenario are applied.

TL;DR: Empirical evidence is presented which shows that the use of deep neural networks with many hidden layers as opposed to shallow networks with only one significantly improves the learning process of a robust NMPC control law.

TL;DR: By explicitly considering the state dependency of the uncertainty sets in the RMPC approach, it is shown how closed-loop performance can be improved over existing approaches that consider worst-case uncertainty.

TL;DR: In this article, the authors developed a picking robot that harvests strawberries on tabletop cultivation systems, which is a complete, fully autonomous system that detects the ripe fruits, picks them with no damage, and puts them in a punnet (box in which strawberries are put).

TL;DR: A recent deep-learning technique, variational autoencoders (VAEs), has been used for missing data imputation in image data, and was compared here to imputation by mean replacement and by principal component analysis (PCA) imputation.

TL;DR: The introduced FCSOR represents an extension on the Statistical Outliers Removal (SOR) method which is effective for both homogeneous and heterogeneous point clouds and is evaluated on real data obtained in outdoor environment.

TL;DR: The transfer function models for various configurations of power systems are developed and the PID tuning schemes are categorised into soft computing techniques, robust control schemes, fractional order based PID design and internal model control (IMC)based PID design approaches.

TL;DR: In this paper, the problem of transient stabilization of a power grid following a destabilizing disturbance is addressed, where a linear predictor, evolving on a higher dimensional (embedded) state-space, is built from observed data and subsequently used within a model predictive control (MPC) framework.

TL;DR: The proposed learning approach uses a receding horizon formulation that samples from the initial states and disturbances to enforce properties such as reachability, safety and stability and an over-approximate reachability analysis over the system, supported by range analysis for feedforward neural networks.

TL;DR: The basics of Time Sensitive Networks (TSN) are explained and compared with the features and possibilities of standard public networks (the Internet) in relation to the onset of the 4th industrial revolution as outlined in the article.

TL;DR: A tree-like structure of Key Performance Indicators (KPIs) is proposed to describe the Performance Measurement System (PMS) of a lean production system to give answers at strategic, tactical, and operational level.

TL;DR: Experimental results show that SAE-LSTM surpasses LSTM through reducing MSE respectively, proving that the hybrid model is more accurate.

TL;DR: The MPC (Model Predictive Control) approach is used in order to get a fuel consumption reduction when the traffic is congested due to the presence of a fixed bottleneck on the highway.

TL;DR: An intelligent fault diagnosis scheme based on long-short-term memory (LSTM) recurrent neural network (RNN) is proposed that can be utilized to detect the fault and classify the corresponding fault types in rotating machinery.

TL;DR: The utilization of edge computing in the IoT is described and its impact on energy consumption of IoT devices is analyzed and a possible implementation of the edge computing paradigm to positively influence the lifespan of constrained devices powered by batteries is presented.

TL;DR: A new modular corrective maintenance methodology, using the digital twin of an automation module, providing Fault ascription support for a human technician, performing corrective maintenance action of an automate module is provided by its digital twin and associated visual interface.

TL;DR: An application prototype based on a Digital Twin as Service Provider for a 4.0 knowledge fruition has been designed and developed to enable operators facing the highly dynamic factory floor and to have their ‘virtual eyes and hands’ on the physical system.

TL;DR: This paper proposes in this paper a defense strategy that prevents damages caused by cyber attacks in the sensor and/or actuator communication channels of supervisory control systems, without changing the behavior of the closed-loop system when it is not attacked.