A fuzzy logic – based decision-making support system for risk assessment in hazardous manufacturing contexts

Estimating the level of risk that an operator might be exposed to is essential in industrial settings, especially in the age of Industry 4.0, where the availability of sensors and the Internet of Things is spreading. A real-time assessment of the risk is required to safeguard worker health and safety, prevent accidents, and reduce the likelihood of occupational diseases. This thesis centers on developing a decision-making support system that employs fuzzy logic to analyze a range of data gathered from diverse types of sensors - such as physiological, environmental, and manufacturing process data - to estimate and characterize potential risks to operators in hazardous manufacturing settings. The use of fuzzy logic enables the interpretation of sensor data, allowing data integration for risk assessment. The suggested framework provides a personalized methodology by identifying potential health risks that might be specific to particular operators and processes based on data acquired from a series of sensing units. A simulated case study is conducted including a range of scenarios in order to validate the proposed methodology. The outcomes show how effectively the fuzzy logic based system works in giving operators a real-time risk assessment, and how such technology has the capability to significantly improve safety in manufacturing environments.