An Artificial Intelligence-based system for modernizing and optimizing production scheduling with a focus on Industry 4.0 and ESG

• Grant number: 24/04494-2
• Support Opportunities: Research Grants - Innovative Research in Small Business - PIPE
• Start date: November 01, 2024
• End date: October 31, 2025
• Field of knowledge: Engineering - Production Engineering - Operational Research
• Principal Investigator: Monique Simplicio Viana
• Grantee: Monique Simplicio Viana
• Company: 56.069.279 MONIQUE SIMPLICIO VIANA
• CNAE: Desenvolvimento e licenciamento de programas de computador customizáveis
• City: Guapiaçu
• Associated researchers: Orides Morandin Júnior
• Associated scholarship(s): 24/19318-5 - An artificial intelligence-based system for modernizing and optimizing production scheduling with a focus on industry 4.0 and ESG, BP.PIPE

Abstract

For the stage of the PIPE Start program, the project aims to develop a pre-operational prototype of a system based on Artificial Intelligence (AI) for the modernization and optimization of industrial production scheduling, with emphasis on Industry 4.0 and considering the principles of Environmental, Social, and Governance (ESG). The system aims to innovate the industry by strategically combining cutting-edge technologies and key sustainability considerations. Through the convergence of AI with ESG principles, the project proposes to create a new and highly efficient paradigm to improve the production scheduling process while considering environmental and social responsibility. Industry 4.0 represents a new era of industrial production, in which digitization, automation, and process interconnectivity are widely used to increase efficiency and competitiveness. In this context, production scheduling is a fundamental step, which seeks to organize and coordinate the workflow to maximize productivity and minimize costs. The system will use the most current and efficient advanced AI techniques, such as optimization algorithms, to determine accurate decisions. AI will process large volumes of data to analyze production performance and identify patterns, bottlenecks, and opportunities for improvement, identifying complex behaviors and enabling agile decisions. This will result in concise manufacturing operations, reduced costs, and greater adaptability to market fluctuations. In addition, the project will have a special focus on issues related to sustainability and social responsibility, incorporating ESG principles into the system. This means that, in addition to seeking productive efficiency, the system will also consider environmental, social, and corporate governance aspects to make more conscious and sustainable decisions. For example, the solution could optimize resource allocation to reduce energy consumption, minimize raw material waste and ensure safe and fair working conditions for employees. Transparency and accountability will also be improved, as AI will enable more detailed traceability and effective audits. By considering sustainability from the beginning of the production process, companies can meet the expectations of investors, regulators, and consumers who value responsible business practices. The benefits of the project are not just restricted to the scope of the companies' internal operations. Optimizing production scheduling can result in shorter lead times, high-quality products, and competitive prices. This will strengthen the position of companies in the global market. In addition, ESG practices can improve corporate reputation, attracting investors and partners aligned with sustainable values. Therefore, for this phase of the PIPE Start program, it is proposed that advances be made to fill three main gaps in the subject: the modeling of AIs that represent the state-of-the-art in acting on production scheduling problems for real industrial problems; the making of a computational prototype to present solutions optimized by AI, considering Makespan as a performance measure, which consists of the total production time of a set of products; the incorporation of ESG concepts in the modeling of the proposal, indicating how optimized scenarios are contributing to the reduction of environmental impacts. As expected results at the end of the first phase of the project, the technical feasibility of using AI must be demonstrated, already validated in academic benchmarks, on real industrial situations, thus proving the efficiency of the proposed project in meeting the identified gaps and, consequently, optimizing production scheduling considering ESG principles. (AU)