Paolo Priore, David de la Fuente, Rau´l Pino and Javier Puente
Dispatching rules are usually applied dynamically to schedule jobs in flexible manufacturing systems. Despite their frequent use, one of the drawbacks that they display is that…
Abstract
Dispatching rules are usually applied dynamically to schedule jobs in flexible manufacturing systems. Despite their frequent use, one of the drawbacks that they display is that the state the manufacturing system is in dictates the level of performance of the rule. As no rule is better than all the other rules for all system states, it would be highly desirable to know which rule is the most appropriate for each given condition, and to this end this paper proposes a scheduling approach that employs inductive learning and backpropagation neural networks. Using these latter techniques, and by analysing the earlier performance of the system, “scheduling knowledge” is obtained whereby the right dispatching rule at each particular moment can be determined. A module that generates new control attributes is also designed in order to improve the “scheduling knowledge” that is obtained. Simulation results show that the proposed approach leads to significant performance improvements over existing dispatching rules.
Details
Keywords
Raúl Pino, Isabel Fernández, David de la Fuente, José Parreño and Paolo Priore
The purpose of this paper is to focus on a supply chain (SC) simulation of all its management processes by means of a multi‐agent system (MAS).
Abstract
Purpose
The purpose of this paper is to focus on a supply chain (SC) simulation of all its management processes by means of a multi‐agent system (MAS).
Design/methodology/approach
Nowadays, the company must develop its activity in an environment characterized by: globalization, hard competitiveness, the necessity of flexibility and of answering dynamically to a changing demand. Thus, a distributed, autonomous approach, strong enough to face changes is necessary, which is what MASs contribute to. An agent can represent each of the components that form the SC. Then the resulting agent system will own similar characteristics to the ones in the studied SC: autonomy, social abilities, reactivity, pro‐activity.
Findings
When analysing the demand for each SC member (from manufacturer to final consumer), one can observe that while consumer demand is a relatively stable feature, the upper link in the chain (the manufacturer), presents a very pronounced variability. This is known as the “bullwhip effect” or “forrester effect” and is mainly due to the fact that the SC members' strategies are not considered as a whole but as a sum of individual strategies. In the proposed system, each agent will be communicated with other “agents” who will be the only responsible for making forecasts based on information provided to it by all components of the chain. The ultimate goal is for each SC echelon to satisfy its own objectives, while at the same time meet the local and external constraints.
Research limitations/implications
In this work a standard SC is proposed (one manufacturer – one distributor – one wholesaler – one retailer) although it could easily be modified to incorporate a bigger number of members in each echelon within the SC.
Originality/value
The paper shows the benefits of using artificial intelligence in the SC management.
Details
Keywords
Javier Puente, Raúl Pino, Paolo Priore and David de la Fuente
This study describes an alternative way of applying failure mode and effects analysis (FMEA) to a wide variety of problems. It presents a methodology based on a decision system…
Abstract
This study describes an alternative way of applying failure mode and effects analysis (FMEA) to a wide variety of problems. It presents a methodology based on a decision system supported by qualitative rules which provides a ranking of the risks of potential causes of production system failures. By providing an illustrative example, it highlights the advantages of this flexible system over the traditional FMEA model. Finally, a fuzzy decision model is proposed, which improves the initial decision system by introducing the element of uncertainty.