http://popups.lib.uliege.be/1373-5411/index.php?id=1802 Publications of Auteurs Roberto Mosca fr 0 http://popups.lib.uliege.be/1373-5411/index.php?id=4733 The goal of this project is to create a real-time based virtual plant for an easier automated re-scheduling of production plan. Consider a real system plant (steelmaking plant for our case study), with complex logistic for machines placement: the system needs a production order list and the initial plant status, then an initial optimized production planning is generated to satisfy orders. During the production, accidents or other contingencies are possible and an immediate production planning re-scheduling is needed. Introducing a virtual plant all significant events that modify the planned production story introducing delays (i.e. increasing the lead time), we can see the plant status in real-time and for all stored possible events (particularly accidents) the system calculates and shows a new optimized re-scheduled production plan. At the same time the proposed system is able to provide a cost reduction over the energy purchase by interacting actively with the free market. Mon, 14 Oct 2024 16:59:36 +0200 Mon, 14 Oct 2024 16:59:45 +0200 http://popups.lib.uliege.be/1373-5411/index.php?id=4733 http://popups.lib.uliege.be/1373-5411/index.php?id=2465 The economic development of the emerging countries has been regarded in the recent time as a serious opportunity for cost reduction from western manufacturer, results obtained from this vision were the increase of the delocalization of the production process and the increase of the management complexity. In order to answer to the new market demand industry turn to software vendors looking for specific ERP systems(Davenport 1998) and starting specific projects for supporting Business Process Redesign (BPR). As seen in several industrial contexts few projects ended with success while the majority of them running very quickly out of budget and in serious delay. In this sector authors identified a lack of anticipatory models able to drive the ERP implementation process to the right and they propose in this paper a meta modeling approach able to bridge this gap. Proposed methodology integrates Data Analysis, Regression Meta-Modeling and Artificial Neural Networks processing in order to identiy hidden relationships among KPI and guide the BPR decision makers. The paper outline the proposed methodology as well as a practical application to a real life industrial case. Thu, 22 Aug 2024 14:26:42 +0200 Thu, 22 Aug 2024 14:26:49 +0200 http://popups.lib.uliege.be/1373-5411/index.php?id=2465 http://popups.lib.uliege.be/1373-5411/index.php?id=1798 The management of industrial systems involves decision making with respect to complex processes that are often stochastic in nature. Simulation is frequently the only effective mean to model the complexity of such industrial processes. Simulation enables detailed scenario testing and, thus, is well suited for "what if" analysis. However, industrial users often need to solve inverse problems, such as optimization or decision analysis, which cannot be handled by simulation alone. This paper proposes the integrated use of simulation and Artificial Intelligence techniques in hybrid system architectures for advanced industrial problem solving. Hybrid Decision Support Systems (DSSs), combine the complementary strengths of different techniques for integrated forecasting ,modeling, and optimization. Tue, 16 Jul 2024 15:51:31 +0200 Tue, 16 Jul 2024 15:51:42 +0200 http://popups.lib.uliege.be/1373-5411/index.php?id=1798