Development of a Fatigue Estimation Model For Industrial Workers

• Ano de defesa: 2024
• Autor(a) principal: González, Sophia Otálora
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal do Espírito Santo; BR; Mestrado em Engenharia Elétrica; Centro Tecnológico; UFES; Programa de Pós-Graduação em Engenharia Elétrica
• Palavras-chave em Português: Fadiga muscular; eletromiografia; sensores inerciais; sensores de fibra óptica; aprendizado de máquina; subject.br-rjbn; Área(s) do conhecimento do documento (Tabela CNPq)
• Link de acesso: http://repositorio.ufes.br/handle/10/17395

Muscle fatigue (MF) reduces the ability to maintain maximal strength during voluntary contraction. During long working shifts, workers often experience muscle fatigue which in the long term can lead to the development of musculoskeletal disorders (MSD), which can significantly impact their ability to engage in repetitive tasks. MSDs represent a major health concern in physical labor, affecting individuals’ quality of life and the ability to perform daily activities and work-related tasks. Estimating and analyzing MF has broad applications in sports, medicine, and ergonomics. Specifically, in ergonomics, reducing local muscular workloads is essential for maintaining the health and productivity of workers. Manual lifting, a common practice in various work environments, can contribute to excessive MF, affecting occupational safety, well-being, and overall productivity. During fatigue, kinematic changes occur, altering muscle activity, joint kinematics, and postural control. Various techniques, both invasive and non-invasive, are used for estimating MF. Invasive methods, such as blood samples or muscle biopsies, provide post-activity information but lack real-time monitoring. Non-invasive methods, like surface electromyography (sEMG), and wearable devices, such as Inertial Measurement Units (IMUs) and Optical Fiber Sensors (OFS), offer alternative approaches to MF estimation. These wearable devices could be used for early detection and management of muscle fatigue, being able to monitor in real-time industrial tasks. Although EMG remains the gold standard for measuring muscle fatigue, its limitations, such as inaccurate readings in long-term work, motivate the use of alternative wearable devices. This master thesis proposes a computational model for estimating muscle fatigue using wearable and non-invasive devices like OFS and two IMUs (located at the wrist and neck) along the subjective Borg scale. EMG sensors are used to observe their importance in estimating muscle fatigue being used as a reference system and comparing performance in different sensor combinations. This sensor is located in the subject’s biceps brachii. Also, a validation of the OFS sensor before the tests is performed. This study involves 30 subjects performing a repetitive lifting activity until reaching muscle fatigue. Muscle activity, elbow angles, and angular and linear velocities are measured to extract multiple features. Some features included mean, standard deviation, RMS value, amplitude, frequency-related features, among others. Different machine learning algorithms obtain a model that estimates three fatigue states (low, moderate, and high) using 70% for training and 30% for testing. Results showed that between the machine learning classifiers, the Light Gradient Boosting Machine (LGBM) presented an accuracy of 96.2% in the classification task using all of the sensors with 33 features and 95.4% using only OFS and IMU sensors with 13 features. This demonstrates that elbow angles, wrist velocities, acceleration variations, and compensatory neck movements are essential for estimating muscle fatigue. In conclusion, the resulting model can be used to estimate fatigue during heavy lifting in work environments, having the potential to monitor and prevent muscle fatigue during long working shifts.