Proactive Scheduling for Steelmaking-Continuous Casting Plant with Uncertain Machine Breakdown Using Distribution-Based Robustness and Decomposed Artificial Neural Network

An unpredictable breakdown often occurs and tends to complicate production scheduling in a steelmaking-continuous casting (SCC) plant. Because of particular characteristics and technology constraints of the SCC plant, traditional robust scheduling often provides an excessively conservative solution. This paper proposes an effective proactive scheduling that utilizes robustness adopting a distribution curve of a system performance created as a mix-integer model. The proposed robustness is designed to work effectively with the existing factory operation and is based on uncertainty assessment. In this paper, artificial neural network (ANN) is adopted with a challenge of designing an accurate model due to the model complexity from the discrete and nonlinear properties of the system performance. The ANN model is achieved by applying k-mean clustering, which decomposes machines to smaller groups having similar effect to the uncertainty. A case study based on data from a real SCC plant is conducted to demonstrate the methodology. The experimental result shows that the proposed methodology is successful in designing a robust schedule that provides a lower production cost under an acceptable breakdown probability while also consuming less computational time compared with the traditional approach.