Using Wearable Sensors to Evaluate Material Handling Operator’s Fatigue in Repetitive Activities: A Design of Experiments Approach
MetadataShow full metadata
Manual Material Handling is one the major causes which contributes to a large percentage of musculoskeletal disorders. In a manufacturing environment, associates lift loads repeatedly which leads to physical fatigue. Human fatigue not only leads to critical injuries, but also lowers productivity in a work environment which has an impact on the entire supply chain process. Hence, physical fatigue is a challenging safety issue in a manufacturing environment. In this research, a Lifting fundamental skill move mimicking a manufacturing environment is physically simulated with the use of Hexoskin sensors and a motion capture framework. The motion capture framework consists of multiple high version cameras, a workstation to perform the experiment, Hexoskin sensors, and a processor that collects a catalog of Bio-MoCap data on a time-series. The main goals of the study are to 1) determine the correlation of the physiological variables with the subjects RPE level of the Lifting skill move on the Borg’s scale, and 2) predict the level with respect to the task. In this study, we use statistical analysis and regression techniques to determine the relationship of the bio-factors with fatigue. A separate regression model is built to predict fatigue with respect to heart rate and time function. Results show the statistical significance of the bio-factors in the process of getting fatigued. A multiobjective optimization method is used for posture prediction and analysis with consideration of fatigue effect and its application case. This research has potential to contribute in the field of manual material handling and can help in efficiently planning workforce with the available resource.