Fabricio Alves de Almeida

The presence of oil slicks in the ocean presents significant environmental and regulatory challenges for offshore oil processing operations. During primary oil–water separation, produced water is discharged into the ocean, carrying residual oil, which is measured using the total oil and grease (TOG) method. The formation and spread of oil slicks are influenced by metoceanographic variables, including wind direction (WD), wind speed (WS), current direction (CD), current speed (CS), wind wave direction (WWD), and peak period (PP). In Brazil, regulatory limits impose sanctions on companies when oil slicks exceed 500 m in length, making accurate prediction of their occurrence and extent crucial for offshore operators. This study follows three main stages. First, the performance of five machine learning classification algorithms is evaluated, selecting the most efficient method based on performance metrics from a Brazilian company’s oil slick database. Second, the best-performing model is used to analyze the influence of metoceanographic variables and TOG levels on oil slick occurrence and detection probability. Finally, the third stage examines the extent of detected oil slicks to identify key contributing factors. The prediction results enhance decision-support frameworks, improving monitoring and mitigation strategies for offshore oil discharges.

The presence of oil films in the ocean poses a significant environmental challenge for companies engaged in primary oil processing on offshore platforms. During crude oil treatment, residual water containing oils and greases (TOG) is discharged back into the ocean, potentially leading to the formation of oil films. The interaction between TOG levels and meteoceanographic variables — including wind direction (WD), wind speed (WS), current direction (CD), current speed (CS), wind wave direction (WWD), and peak period (PP) — influences the formation and satellite detection of these films. This study investigates the impact of these factors on the occurrence, detection, and extent of oil films using various statistical classifiers. Key findings reveal that Random Forest outperformed other classifiers, achieving an area under the ROC curve of 0.93. The combined use of classifiers, multivariate techniques, desirability analysis, and Design of Experiments (DOE) proved highly effective. Higher values of WS, WD, and CS were associated with a lower likelihood of oil film occurrence and detection, whereas higher TOG, PP, WWD, and CD values increased this probability. CS and TOG positively contributed to the extent of oil films, while high WS values reduced it. These results provide a robust decision-support framework for monitoring and mitigating the environmental impacts of offshore oil processing operations.

In the light of Brazilian energy regulatory context, cluster strategies are required to classify groups of substations for voltage sag purposes. Tuning cluster algorithms is not a trivial task, due to the fact that these methods are sensitive to small errors. Therefore, this study proposes a new methodology based on principal components analysis (PCA), attribute agreement and analysis of covariance to verify the level of consistency and sensitivity of the linkage methods in the cluster formation for voltage sag studies. In order to prove this methodology, real data from power quality indices of distribution substations are used. Four distinct scenarios with disturbances are evaluated. PCA is applied for dimensionality reduction of the data. Then, grouping is performed for eight different linkage methods and agreement analysis is applied. Ward method was the only one that presented 100% consistency in all scenarios, considered as the most robust method whereas k-means showed consistency of 94.11%, with inversion of the clusters. However, when evaluating their groupings, it was found that k-means was unable to adequately separate the groups for this dataset. Finally, the proposed methodology is adequate for choose cluster methods for extensive data and it can be extended to applications in different areas.

A new approach to identify and diagnose the quality of extensive and multivariate data is presented, using the gage repeatability and reproducibility (GR&R) study through the weighting of rotated factor scores. The proposal uses axis rotation to improve the explanation and interpretations of latent information, providing a statistically appropriate alternative when dealing with two or more correlated data sets. To analyze data with a significant variance-covariance structure, factor analysis (FA) is applied for calculating the eigenvalues and extracting of the rotated scores. Once obtained, these scores are then weighted with their respective eigenvalue for each factor. This procedure results in a single response vector, which is capable of properly interpreting all of the quality responses analyzed. To illustrate an application of the method, a real data set from a resistance spot welding process is selected, and two different types of rotation are compared. The proposed method provided an output that contemplated all of the significant variability of the data in a unique and significant way. In addition, the method enabled a reduction in the data dimensionality, thus minimizing the time for analysis and computational effort.

One of the main goals in flux-cored arc welding processes is the optimization of bead geometry, in which multiple geometric characteristics of the welding bead are important; therefore, multi-objective optimization programming is often applied in this manufacturing process. However, several optimization problems that use stochastic programming do not consider the impact of the correlation between the output variables on their probabilistic constraints. In this context, this paper aims to present a multi-objective optimization method based on multivariate stochastic programming. To demonstrate the applicability of the proposal, we conducted a design of experiments to optimize a flux-cored arc welding process for stainless-steel claddings. The weighting-sums method was applied to formulate the multi-objective optimization problem. It was possible to formulate a multivariate probability distribution for the penetration and dilution. In addition, 20 Pareto-optimal solutions were obtained and a 95% probability to meet the predefined specification limits of the geometric characteristics was achieved for each solution.

As the lean product development (LPD) process is responsible for maximizing the value/waste relation by encouraging different types of innovation, it needs a clear understanding of end customer value. Moreover, lean systems engineering is related to the application of lean thinking (LT) in systems engineering to improve the delivery of value to all stakeholders of the system. Then, faced with this scenario, this research aims to propose a value‐adding conceptual model for incremental product innovations in LPD. A systematic review of the literature from the LT perspective was performed and the conceptions of value were identified and then analyzed and contrasted with the concepts and characteristics of the areas of product development, marketing, and consumer psychology, which made possible the proposition of a conceptual model. The results show that customer value is multidimensional, and it was possible to identify the importance and the need for prioritization of certain dimensions of value for specific markets and customers. The conceptual model named VA2I presented in this study is generic and can be adapted and applied in any type of organization.