Reliability evaluation for a complex waste to energy in industry 4.0 paradigm based on stochastic process

Waste-to-Energy (WtE) systems are vital for sustainable energy production but face significant challenges under the Industry 4.0 paradigm, including uncertainty in supply and demand. This study develops a reliability evaluation framework to address these challenges by integrating stochastic process modeling, Bayesian Belief Networks (BBN), and Q-learning. A simulated dataset of 5000 operational hours with 100 failures was analyzed to estimate system failure and repair rates. Results show that Industry 4.0 integration reduces the failure rate from 0.02 to 0.015 failures/hour, increases the repair rate from 0.4545 to 0.5 repairs/hour, and improves operational efficiency from 96 % to 97 %. Sensitivity analyses further demonstrate reduced downtime, improved system availability, and better cost–benefit performance when predictive maintenance and real-time monitoring are applied. These findings confirm the superiority of the proposed approach compared with traditional stochastic models, highlighting its potential for practical implementation in WtE reliability management. The study concludes with recommendations for engineers and policymakers to integrate Industry 4.0 technologies for more resilient and efficient waste-to-energy systems. • Efficiently process municipal solid waste to generate electricity and heat in the proposed waste to energy system. • Reduce the environmental footprint associated with waste disposal, including emissions and resource depletion. • Maximize the recovery of recyclable materials from waste streams using the proposed reliability evaluation method. • Utilize modern technologies to monitor system performance and ensure operational efficiency through industry 4.0 paradigm.