ORCID
https://orcid.org/0000-0001-9266-1284
Abstract
In the context of Industry 4.0, predictive maintenance enhances operational efficiency by optimizing processes, minimizing downtime, and improving cost-effectiveness. However, implementing predictive maintenance requires a systematic approach due to its complexity. This study collected expert input from 15 food and beverage manufacturing industries located in Dar es Salaam, Tanzania, using a purposive sampling technique. Six representatives were selected from each industry, and their opinions were analyzed using MATLAB 7.6 through a fuzzy logic inference system. The analysis focused on key factors influencing Industry 4.0 technology adoption for predictive maintenance, including adoption intention (strategic decision, equipment data, perceived benefit) and perceived usefulness (organizational culture, risk perception, external pressure). The results indicate that when strategic decision-making (technical function) is at 20%, equipment data quality at 15%, and perceived benefit (flexibility) at 25%, the adoption intention of the technology drops to 10%. The fuzzy logic system used techniques such as fuzzification, inference, and aggregation to assess the feasibility of predictive maintenance adoption. The model was validated and refined to ensure accuracy and relevance, offering decision support for maintenance planning and resource allocation. This Fuzzy Logic-Based Decision Support System provides a structured approach to overcoming the complexities of adopting predictive maintenance in Industry 4.0, helping manufacturing industries improve their operational efficiency and competitiveness.
Recommended Citation
Peter, F. E. (2025). Fuzzy Logic-Based Decision Support System for Adoption of Industry 4.0 Predictive Maintenance by Manufacturing Industries. Tanzania Journal of Engineering and Technology, 44(2), 274-286. https://doi.org/https://doi.org/10.52339/tjet.v44i2.1305
Publisher Name
University of Dar es Salaam
Included in
Dynamic Systems Commons, Energy Systems Commons, Industrial Engineering Commons, Numerical Analysis and Computation Commons, Other Operations Research, Systems Engineering and Industrial Engineering Commons, Process Control and Systems Commons