Saber DARMOUL

Ecole Centrale Casablanca, Industrial Engineering, Faculty Member

King Saud University, Industrial Engineering, Faculty Member

Followers

Following

Co-authors

Public Views

Dr. Saber Darmoul is Assistant Professor of Industrial Engineering at Ecole Centrale Casablanca, Morocco. He has B.Sc. and M.Sc. degrees in Automation and Control Engineering with highest distinction from the National Institute of Applied Sciences and Technology (Institut National des Sciences Appliquées et de Technologie, INSAT), which is one of Tunisia’s renowned schools of Engineering. He has a Ph.D. degree in Computer Engineering from Université Blaise Pascal, Clermont-Ferrand, France. His teaching areas are related to Systems Engineering, with emphasis on system design, simulation, performance optimization, industrial information systems, and production planning, monitoring and control. His research interests focus on distributed control of manufacturing, service, and cyber-physical systems using artificial intelligence. Dr. Darmoul is exploring the use of distributed artificial intelligence (multi-agent, holonic and bionic/bio-inspired systems) to monitor and control disruptions and risks in manufacturing, service and cyber-physical systems. Applications include reconfigurable manufacturing systems, which are the next step in Flexible Manufacturing. These systems allow high agility and responsiveness to disturbances and risks, such as fluctuation of demand and production resource availability/reliability. Applications also include intelligent transportation systems (ITS), supply chains and project management. Dr. Darmoul is leading several funded research projects in transportation engineering, traffic engineering, human machine interaction and virtual reality.
Supervisors: Henri Pierreval and Sonia Hajri-Gabouj

less

Interests

Uploads

Papers by Saber DARMOUL

An analytic hierarchy process augmented with expert rules for product driven control in cyber-physical manufacturing systems

Computers in Industry

In Cyber-Physical Manufacturing Systems (CPMS), numerous distributed control architectures were s... more In Cyber-Physical Manufacturing Systems (CPMS), numerous distributed control architectures were suggested to make different production entities active with respect to decision-making and control processes, so that they can process information, interact, and make control decisions in an autonomous and adaptive way. Nevertheless, developing Product-Driven Control (PDC) mechanisms that enable Smart Products (SPs) to make control decisions to cope with disturbances is still a complex, open-ended, and challenging problem. This article suggests a PDC approach that enables SPs to learn how to make control decisions to react to disturbances and maintain continuity of operations. The control mechanism involves an Analytic Hierarchy Process (AHP) augmented with Expert rules to cope with the limitations of standard AHP in dealing with dynamic problems. The mechanism is applied to a dispatching problem in an industrial scale assembly process. A multi-agent discrete event simulation model is used to create a set of normal and disturbed production scenarios. SP agents use context indicators and performance assessment to activate Expert rules and update AHP preferences and scales before making dispatching control decisions to react to disturbances. Data analytics tools are developed to help manufacturing system Experts define and fine-tune rules, based on rule firing statistics and corresponding context indicators and performance assessment acquired from simulation. Experimentations and results show competitive performance and highlight interesting research directions.

Benchmarking Simulation Software Capabilities Against Distributed Control Requirements: FlexSim vs AnyLogic

Service Oriented, Holonic and Multi-Agent Manufacturing Systems for Industry of the Future, 2021

Industry 4.0 communication and data management technologies enable the development of distributed... more Industry 4.0 communication and data management technologies enable the development of distributed, product driven control architectures, where intelligent products can play active roles in manufacturing control processes. Although simulation is a widespread practice to test, evaluate, compare and validate different design alternatives, there is still a lack of papers that assess and discuss the capabilities of available simulation software to meet and implement the requirements of such distribution as a design alternative. This paper provides an analysis of distributed, product driven control requirements and benchmarks them against the capabilities of two commercially available simulation software, namely FlexSim and AnyLogic. A comparison of the strengths and weaknesses of each software is provided through a case study.

Parts

We have attached to the papier this archive file containing two folders: • A folder "VISSIM ... more We have attached to the papier this archive file containing two folders: • A folder "VISSIM model" containing the used simulation model (using VISSIM) including all used simulation parameters and the road network. • A folder " Data" including details of other data such as the initial immune memory and immune network Let us note that a "30-day PTV Visum free demo version" can be downloaded from this link: http://vision-traffic.ptvgroup.com/en-us/products/ptv-visum/trial-version/. This version includes all functions of VISSIM. Editors, reviewers and researchers can repeat the experiments that are performed in this work. We thank you very much in advance for the attention that you will give to this article. We hope that you will find it suitable for publication.

A Tutorial on Traffic Prediction and Control in Urban Areas Using SUMO and Artificial Neural Networks

Integration of Immune Features into a Belief-Desire-Intention Model for Multi-agent Control of Public Transportation Systems

Lecture Notes in Computer Science, 2017

There is a growing need to develop monitoring and control systems to maintain the performance and... more There is a growing need to develop monitoring and control systems to maintain the performance and the quality of service of Public Transportation Systems (PTS) at acceptable levels, especially in case of traffic disturbances, such as accidents or congestion. Despite the use of Multi-Agent Systems (MAS) to control PTS, many existing systems still rely on centralized control architectures, and do not offer generic agent behavior models. Many Belief-Desire-Intention (BDI) models were developed as generic agent decision-making processes, but existing developments still lack detailed descriptions of models instantiation and implementation. This article introduces a new framework for the implementation of the Belief-Desire-Intention (BDI) model for the development of an agent based decision support system for the control of public transportation systems. The suggested framework uses a set concepts and mechanisms inspired from biological immunity. Through a simulation case study, we have presented an example of implementation of the suggested BDI framework.

A Multi-Criteria Decision Framework Considering Different Levels of Decision-Maker Involvement to Reconfigure Manufacturing Systems

Machines, 2020

Reconfigurable Manufacturing Systems (RMSs) rely on a set of technologies to quickly adapt the ma... more Reconfigurable Manufacturing Systems (RMSs) rely on a set of technologies to quickly adapt the manufacturing system capacity and/or functionality to meet unexpected disturbances, such as fluctuation/uncertainty of demand and/or unavailability/unreliability of resources. At the operational stage, such disturbances raise new production requirements and risks, which call upon Decision-Makers (DMs) to analyze the opportunity to move from a running configuration to another more competitive one. Such a decision is generally based on an evaluation of a multitude of criteria, and several multi-criteria decision-making (MCDM) approaches have been suggested to help DMs with the reconfiguration process. Most existing MCDM approaches require some assignment of weights to the criteria, which is not a trivial task. Unfortunately, existing studies on MCDM for an RMS have not provided guidelines to weigh the evaluation criteria. This article fills in this gap by offering a framework to set up such ...

Saber DARMOUL

Uploads

Papers by Saber DARMOUL

Log In