Creating an Intelligent Rescheduling System with Stochastic Reverse Learning and Chaos Mapping in Real-Time Scenarios

The Flexible Job Shop Scheduling Problem (FJSP) is a complex NP-hard problem frequently encountered in manufacturing systems, requiring simultaneous decisions on machine assignments and operation sequences to optimize objectives such as the maximum completion time To address this challenge, this study proposes an Intelligent Rescheduling System with Stochastic Reverse Learning and Chaos Mapping integrated into the Random Opposition-based Learning Dung Beetle Optimization (ROL-DBO) algorithm, designed for real-time scenarios. The algorithm incorporates multiple innovative strategies to enhance the traditional Dung Beetle Optimization (DBO) framework. Logistic-Tent chaotic mapping is utilized for population initialization, ensuring a diverse and well-distributed search space.The proposed system is validated on benchmark datasets (Kacem and Brandimarte), demonstrating consistent achievement of optimal or near-optimal solutions. Its ability to adapt to dynamic changes and reschedule operations in real time highlights its potential as a powerful tool for intelligent scheduling in modern manufacturing systems and Industry 4.0 applications.