Thesis Defence: A Novel Data-driven Rolling Horizon Production Planning Approach for the Plastic Industry under the Uncertainty of Demand and Recycling Rate

Razieh Larizadeh, supervised by Dr. Babak Tosarkani, will defend their thesis titled “A Novel Data-driven Rolling Horizon Production Planning Approach for the Plastic Industry under the Uncertainty of Demand and Recycling Rate” in partial fulfillment of the requirements for the degree of Master of Applied Science in Mechanical Engineering.

An abstract for Razieh Larizadeh’s thesis is included below.

Defences are open to all members of the campus community as well as the general public. Please email babak.tosarkani@ubc.ca to receive the Zoom link for this defence.

---

ABSTRACT

Developing an efficient production plan requires considering sustainability practices and the dynamic nature of manufacturing environments. This helps minimize waste to align with sustainability goals, enhance operational efficiency for cost savings, and foster resilience to adapt to market dynamics, thereby ensuring viability. To achieve these goals in the plastic industry, exploring opportunities for recycling integration and adaptability to the uncertain nature of key parameters such as market demand and recycling rate is necessary. The reason stems from the fact that fluctuations in time-varying parameters can pose serious challenges to a predetermined static production plan and make it infeasible in the real world. Furthermore, adhering to sustainability practices is essential to mitigate the detrimental effect of plastic pollution on the ecosystem and to conserve valuable natural resources by decreasing the demand for virgin materials.

This thesis develops a novel Data-driven Rolling Horizon Planning (DRHP) approach for a sustainable and dynamic production plan in the plastic industry. In this regard, a dynamic Rolling Horizon (RH) planning framework is formulated as a multi-product, multi-period Mixed Integer Linear Programming (MILP) model. This model aims at minimizing total production costs while taking into account the system’s constraints and sustainability considerations. To deal with uncertainty, the RH-based MILP model is coupled with a Long Short-Term Memory (LSTM) model. The LSTM model leverages historical data of market demand and recycling rate to predict future trends in time-varying parameters and consequently improve the efficiency of the production plan.

The outperformance of the proposed DRHP approach is demonstrated through an extensive comparison with a robust static counterpart in terms of total production cost and sustainability measures. Results indicate significant reductions, up to 80%, in production costs using the proposed DRHP approach. Furthermore, the effect of various rolling durations is investigated regarding total production cost, backlog, late-order, and inventory level. Findings underscore the potential of utilizing the proposed DRHP approach to mitigate inventory- and late-order-related challenges.