Data-driven Spare Parts Inventory Management

点击翻译按钮获取中文摘要

Spare parts are stock items used in maintenance activities required to keep equipment in operating condition. The spare parts inventory management system is critical because the cost of spare parts accounts for a significant share of the equipment's lifecycle cost. The long-term goal is to develop new mathematical models and solution methodologies for data-driven optimization approaches in inventory management. In the short term, the aim is to investigate data-driven optimization approaches for spare parts inventory management. In academia, this program will provide new data-driven models for spare parts inventory management, and develop solution methodologies for these models. In practice, the resulting methodologies will save costs related to Canada's spare parts inventory management across a broad range of industries, e.g., automobiles. Importantly, this program will emphasize supply chain sustainability and analytics for inventory management. Most of current literature focus on managing spare parts of capital goods. Unlike capital goods, consumer durable goods usually have a shorter lifecycle and a larger consumer base. The spare parts inventory of consumer durable goods is normally held by an Original Equipment Manufacturer (OEM) or third-party service provider to fulfill the warranty contracts while that of capital goods is held to support maintenance services regulated by service contracts. These differences indicate that the optimal inventory policies for spare parts of capital goods are unlikely to be optimal for those of consumer durable goods. As environmental concerns have been increasingly growing, the concept of supply chain sustainability is widely advocated. Reverse logistics (RL) is one of the popular topics in the literature on supply chain sustainability. The forward supply chain and the reverse supply chain constitute the closed-loop supply chain. In the existing literature, there is no study that investigates reducing the life cycle cost of spare parts in a closed-loop supply chain. Big data analytics (BDA) utilizes evidence-based data, statistical and operations analysis, predictive modeling, forecasting, and optimization techniques to evaluate operations and strategies to obtain insights in management. There is a clear gap in the literature indicating that BDA is rarely used in spare parts inventory management. Existing literature in spare parts inventory management mainly focus on managing at most hundreds of spare parts while it is common to see thousands of spare parts in practice. This program will address gaps in the literature while also ensuring impact within industry. Moreover, training of the next generation of scholars and supply chain executives is a key anticipated outcome; the HQP involved in this project will gain research skills and exposure challenges facing key stakeholders. This will ensure success in their future career choice and will assist in filling the skills and personnel gap.