Friction stir processing is a novel material processing technique. In this study, neural network-based genetic optimization is applied to optimize the process performance in terms of post-friction stir processing mechanical properties of Al7075 alloy and the energy cost. At first, the experimental data regarding the properties (i.e. elongation, tensile strength and hardness) and the consumed electrical energy are obtained by conducting tests varying two process parameters, namely, feed rate and spindle speed. Then, a numerical model making use of empirical data and artificial neural networks is developed, and multiobjective multivariable genetic optimization is applied to find a trade-off among the performance measures of friction stir processing. For this purpose, the properties like elongation, tensile strength and hardness are maximized and the cost of consumed electrical energy is minimized. Finally, the optimization results are verified by conducting experiments. It is concluded that artificial neural network together with genetic algorithm can be successfully employed to optimize the performance of friction stir processing.

Decision-making under uncertainty implies dealing with information about different choices and their consequences that is partial for the decision-maker. In front of uncertainty, either the decision can be postponed, waiting for complementary information or the decision can be only made on the available information, despite possible consequences on the decision. We propose a model to identify and structure needed information. Human factors are taken into consideration in this structure. Then, to process the collected information, we propose a Fuzzy Decision Support System (FDSS) which deals with uncertain information. In this approach, a sequence of decisions leads to a final choice, taking progressively into account new information whose role is to refine available information. Human representation and reasoning mode are imitated, respectively by fuzzy sets and fuzzy inference rules. We apply the proposed FDSS to a case study held on a ski resort. The results with this approach prove effective compared to those a naive decisional approach.

Industrial projects are often difficult to accomplish, reaching all their goals on quality, time, cost, and respecting human well-being. Making decisions effectively and without delays would help achieve the goals and prevent waste of human and material resources. However, as recent literature shows very few organizations have undertaken systematic efforts to enhance decision-making processes. This paper investigates a methodology to identify and structure efficient practices that would improve collaborative decision-making in industrial projects. The proposed methodology uses CIMOSA cube as a reference architecture that provides multiple views to analyze the different aspects of decision-making process. A case study in drug development projects is presented to illustrate the interest of the proposed approach.