Intelligent Predictive Noise Cancellation System in Industrial Environments Based on AI Model

• Grant number: 25/12233-7
• Support Opportunities: Scholarships in Brazil - Doctorate
• Start date: August 01, 2025
• End date: July 31, 2029
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Hernane Borges de Barros Pereira
• Grantee: Raí Faustino Miranda Santos
• Host Institution: Faculdade de Tecnologia. Centro Universitário SENAI CIMATEC. Salvador , SP, Brazil
• Company: Centro Universitário SENAI CIMATEC. Faculdade de Tecnologia
• Associated research grant: 20/09770-7 - Center of Excellence in Applied Research in Artificial Intelligence for Industry, AP.PCPE

Abstract

This project proposes the development of an intelligent system for selective noise cancellation in industrial environments, implemented as firmware embedded in equipment or as attachable modules. The main objective is to create a practical solution for the factory floor that can identify and cancel, in real time, only unwanted machine noise, while preserving human voices. This is achieved by combining artificial intelligence for analysis and classification of sound signals and wave inversion techniques generated by transducers, which emit the inverse wave of the captured noise, thus eliminating it without impairing communication.The motivation comes from real industry demands, where excessive noise affects safety, productivity, and occupational health. Data from NIOSH (1998) and OSHA (2021) highlight that noise levels above 85 dB(A) increase risks of hearing loss and accidents. The proposed solution aims to eliminate the need for protective hearing equipment, acting directly on noise sources. Moreover, the system enables monitoring of specific machine sounds, allowing for predictive maintenance strategies through acoustic fault detection.The methodology involves literature and patent reviews on ANC and AI, engineering of relevant acoustic features, creation of a dataset with industrial noise and speech for AI model training, and firmware implementation with testing in simulated and real industrial environments. The expected result is a robust, integrated system with direct impact on safety, comfort, and efficiency in industrial settings, opening opportunities for partnerships with equipment manufacturers and companies seeking innovation and compliance with occupational health standards.Keywords: Artificial Intelligence; Active Noise Cancellation; Industrial Firmware; Industrial Environments; Predictive Maintenance. (AU)