Luciana Oshiro Yamada

Abstract
A significant challenge in asset management is the selection of investment projects for infrastructures, which often relies on subjective judgement and lacks structured decision support methods. This challenge is particularly complex in water systems due to the diverse and heterogeneous nature of the components requiring investment. While the infrastructure value index (IVI) is widely used to characterise assets and support investment decisions in the water sector, its application in optimisation models for generating efficient project portfolios remains unexplored. To address this research gap, this study introduces optimisation models for generating investment portfolio plans in water systems' asset management. The proposed approach includes two mixed-integer linear programming (MILP) models that determine optimal solutions and an evolutionary algorithm that offers sub-optimal alternative investment selection plans to provide decision-makers with additional choices for balancing optimal outcomes. The primary contribution of this research is the combined utilisation of MILP and evolutionary algorithms, integrating the IVI into the decision-making process. These tools provide decision-makers with structured methods for defining investment plans and minimising the subjective elements typically associated with such processes. To illustrate the effectiveness of the models, a case study is presented involving a pumping station of a Portuguese water company. The results demonstrate the practical application and benefits of the proposed approach in optimising investment decisions. This research contributes to advancing asset management practices by integrating quantitative optimisation techniques and leveraging the IVI, thereby enhancing the objectivity and efficiency of investment planning in water systems' asset management.

Abstract
Data clustering combined with multiobjective optimization has become attractive when the structure and the number of clusters in a dataset are unknown. Data clustering is the main task of exploratory data mining and a standard statistical data analysis technique used in many fields, including machine learning, pattern recognition, image analysis, information retrieval, and bioinformatics. This project analyzes data to extract possible failure patterns in Solar Photovoltaic (PV) Panels. When managing PV Panels, preventive maintenance procedures focus on identifying and monitoring potential equipment problems. Failure patterns such as soiling, shadowing, and equipment damage can disturb the PV system from operating efficiently. We propose a multiobjective evolutionary algorithm that uses different distance functions to explore the conflicts between different perspectives of the problem. By the end, we obtain a non-dominated set, where each solution carries out information about a possible clustering structure. After that, we pursue a-posteriori analysis to exploit the knowledge of non-dominated solutions and enhance the fault detection process of PV panels.