Banca de DEFESA: HANSER STEVEN JIMENEZ GONZALEZ

Uma banca de DEFESA de DOUTORADO foi cadastrada pelo programa.
STUDENT : HANSER STEVEN JIMENEZ GONZALEZ
DATE: 22/12/2021
TIME: 09:00
LOCAL: Online
TITLE:

A CONTRIBUTION TO MACHINE LEARNING APPLICATIONS IN LOGISTICS AND MAINTENANCE PROBLEMS

KEY WORDS:

Deep learning. Inventory rationing. Dropshipping. Reinforcement Learning. Multi- component systems. Imperfect maintenance.

PAGES: 93
BIG AREA: Engenharias
AREA: Engenharia de Produção
SUMMARY:

As the time goes by, organizations acknowledge more and more the role of business support functions for the achievement of competitiveness and a sustainable performance. Considering that, it is important to propose novel mathematical models that enable the improvement of these functions. These models are supposed to be aligned with the challenges that organizations face due to factors such as the rapid evolution of technology and the Internet. Particularly, models are supposed to cope with changes in consumption patterns, and with the complexity and the way industrial operations are carried out in light of the adoption of Industry 4.0. In the recent years, for example, machine learning-based models have gained popularity in areas such as robotics, natural language processing, including manufacturing, logistic and maintenance management. They have proven to be efficient in these domains in which the relation between some variables is sometimes unknown or in which the problem dimensionality and solution space are high. According to that, this dissertation proposes a series of machine learning based models in order to solve logistic and maintenance problems. The first proposed model is based upon Deep Learning and aims to classify e-commerce orders in dropshipping systems as soon as they are placed on the internet. The model allows improving inventory rationing, increasing profit opportunities for e-tailers, and advancing the decision on how to fulfill a shared demand. The second model is based upon Deep Reinforcement Learning and Goal Programming. The aim of the model is to define dynamic maintenance actions in multi-state multi-component systems taking into consideration imperfect maintenance and multiple objectives for assessing the maintenance performance. Results show that the proposed models enable the improvement of key indicator performances such as order fulfilment rate, total e-tailer’s profit, maintenance cost rate and average system’s reliability.

BANKING MEMBERS:
Externo à Instituição - PHUC DO
Externo à Instituição - PHILIP ANTHONY SCARF
Externo à Instituição - HAI CANH VU
Interna - 1385501 - ANA PAULA CABRAL SEIXAS COSTA
Presidente - 1549303 - CRISTIANO ALEXANDRE VIRGINIO CAVALCANTE
Interna - 1561347 - DANIELLE COSTA MORAIS