15 research outputs found
Online Diagnosis based on Chronicle Recognition of a Coil Winding Machine
No full textThis paper falls under the problems of the diagnosis of Discrete Event System (DES) such as coil winding machine. Among the various techniques used for the on-line diagnosis, we are interested in the chronicle recognition and fault tree. The Chronicle can be defined as temporal patterns that represent system possible evolutions of an observed system. Starting from the model of the system to be diagnosed, the proposed method based on the P-time Petri net allows to generate the chronicles necessary to the diagnosis. Finally, to demonstrate the effectiveness and accuracy of the monitoring approach, an application to a coil winding unit is outlined
Human Machine Interface for monitoring a winding machine
No full textThe monitoring function that we are developing is part of an overall monitoring process. It aims, on the basis of the information available on its operating modes, to detect, locate and diagnose failures that may affect its performance and operational safety. The purpose of this paper is to carry out a method for monitoring an automated system based on a Human Machine Interface (HMI). The purpose of monitoring task is the detection and the rapid localization of faults in order to minimize the average system downtime. Finally, we illustrate the implementation of the proposed supervision approach on a winding machine in order to monitor the bobbins quality
Robust Control under Uncertainty for Seaport Handling Equipments
No full textAbstractUncertainty in transport includes mainly unavailability of transportation resource, durations of maintenance activities and the infrastructure constraints. The uncertainty influences the transportation resource availability, and consequently the planned transport schedule. Developments presented in this paper are devoted to the robustness control of transportation system. A robust control strategy towards uncertainty is presented. The presented control strategy tries to reduce unavailability of machines in transportation system and to minimize the total transfer time. To illustrate the effectiveness and accuracy of proposed robustness approach, an application to a seaport handling equipments is outlined
Corrigendum to “Modeling and Robustness Study of Railway Transport Networks Using P-Timed Petri Nets”
No full textModeling and Robustness Study of Railway Transport Networks Using P-Timed Petri Nets
No full textThe importance of public transport systems continues to grow. These systems must respond to an increasing demand for population mobility and traffic disturbances. Rail transport networks can be considered as Discrete Event Systems (DES) with time constraints. The time factor is a critical parameter, since it includes dates to be respected in order to avoid overlaps, delays, and collisions between trains. P-time Petri Nets have been recognized as powerful modeling and analysis tools for railway transport systems. Temporal disturbances in these systems include railway infrastructure, traffic management, and disturbances (weather, obstacles on the tracks, malice, social movement, etc.). The developments presented in this paper are devoted to the modeling and the study of the robustness of the railway transport systems in order to evaluate the stability and the efficiency of these networks. In this study two robust control strategies towards time disturbances are presented. The first one consists of compensating the disturbance as soon as it is observed in order to avoid constraints violation. The second one allows generating, by the control, a temporal lag identical to the disturbance in order to avoid the death of marks on the levels of synchronization transitions of the P-time Petri net model
A Monitoring-Maintenance Approach Based on Fuzzy Petri Nets in Manufacturing Systems with Time Constraints
No full textUnsupervised Learning and Digital Twin Applied to Predictive Maintenance for Industry 4.0
No full textThe diagnosis of anomalies in industrial equipment is a vital research area, as the product quality to be manufactured is inextricably linked to the machine’s efficiency. To date, conventional statistics on the industrial equipment fault prevention are weak. The major concept of the future Industrial 4.0 framework is the integration of artificial intelligence (AI) and the implementation of digital twin (DT), which could avoid serious economic losses caused by unexpected equipment failures and significantly improve system reliability. DT is an emerging technology in the context of digital transformation that enables the monitoring, diagnosis, energy efficiency, and optimization of different systems. Numerous initiatives have shown how AI can enhance the performance of DT for industrial applications. This paper proposes a methodology based on the integration of the autoencoder (AE) and the long short-term memory (LSTM) networks by using DT architecture for monitoring and predictive maintenance (PdM) in manufacturing. Our methodology was put into practice on a real-life industry example using data collection, analysis and deep learning approach. The aim of the proposal is to implement a deep learning hybrid model combining LSTM with AE to perform anomaly detection tasks on a monofilament winding machine. This approach enables better quality results and more efficient management of the weaver’s workshop. The effectiveness of the proposed approach in a monofilament winding machine is demonstrating by a high accuracy (98%) of the model
Computation of Passive Robustness Bound for Assembly/Disassembly Processes
No full textWorks presented in this paper deal with the robustness of manufacturing job-shops with time constraints. A computing algorithm of a lower bound of the maximal time disturbances allowed in a given point is provided. To demonstrate the effectiveness and accuracy of this algorithm, two industrial examples are depicted. The possession of this bound allows checking the death of marks without the generation of too many false alarms. From a practical point of view, the death of a mark corresponds to an incorrect treatment of a given product. In food or pharmaceutics industries, this scenario is not acceptable because it jeopardizes health of humans. When a disturbance is lower than the bound value, the production remains correct and no quality alarm is generated
