Modelagem e implementação de uma planta didática de manufatura robótica inspirada em planejamento automático

• Autor(a) principal: Alves, Weslley da Silva
• Data de Publicação: 2023
• Tipo de documento: Dissertação
• Idioma: por
• Título da fonte: Repositório Institucional da UFG
• Texto Completo: http://repositorio.bc.ufg.br/tede/handle/tede/13084
• topic: Automação; Manufatura; Robótica; Planejamento automático; Bancada didática; Automation; Manufacturing; Robotics; AI planning; Idactic testbench; ENGENHARIAS::ENGENHARIA MECANICA

Current manufacturing systems have been undergoing significant technological advancements, particularly in the field of production planning and automation. The Fourth Industrial Revolution, or Industry 4.0, has already begun to enable technological innovations across various domains, especially in the manufacturing and services industries. There has been a noticeable surge in research on artificial intelligence techniques involving manufacturers seeking efficiency and speed. To achieve 'intelligent' behavior, it is inevitable to implement techniques for automated problem-solving, enabling some decision-making by the equipment and devices themselves. Automated planning, also known as 'automated planning' or 'AI Planning' in English, defines a specific type of state transition problem in which the goal is to find an admissible sequence of actions to bring the system from a certain initial state to a desired final state. The use of automated planning applied to manufacturing processes is gaining prominence in the academic sphere due to the potential to expand the use of techniques in real-world applications in modern industry. This work aims to primarily analyze data from the integration of automated planning solutions into real systems and describe a practical example based on a didactic plant that simulates a production line in a factory composed of individual cells. For the project's implementation, a programmable logic controller (PLC) was used as a model of real systems used in industrial automation, and the assembly and description steps of each station are presented. The language used for modeling the planning domain was the 'Planning Domain Definition Language' (PDDL), through the online platform 'PDDL Editor,' which is part of a set of online tools for AI Planning called 'Planning.Domains.' The modeling was distributed across five stations to facilitate solving the proposed problem for each station, thus generating five solution plans, one for each station. The results achieved from the domain modeling method in manufacturing using an online automated planning tool included the generation of solution plans for the proposed scenarios and practical implementation on the didactic bench using the 'Sequential Function Chart' (SFC) programming language. The proposed approach was compared with the classical approach, which concentrated programming logic on the PLC and used the Ladder programming language, highlighting the potential of using automated planning for Industry 4.0-related topics.