Supply chain dynamics and forecasting

Niu, Mu (2009) Supply chain dynamics and forecasting. Doctoral thesis, Northumbria University.

Preview

Text (Doctoral Thesis) niu.mu2_phd.pdf - Submitted Version Download (15MB) | Preview

Abstract

Nowadays, the global supply chain system needs to respond promptly to changes in customer demand and adapt quickly to advancements in technology. Supply chain management becomes an integral approach which links together producers, distributors and customers in collaborative management of the whole system. The variability in orders or inventories in supply chain systems is generally thought to be caused by exogenous random factors such as uncertainties in customer demand or lead time. Studies have shown, however, that orders or inventories may exhibit significant variability, even if customer demand and lead time are deterministic. Most researchers have concentrated on the effects of the ordering policy on supply chain behaviour, while not many have paid attention to the influences of applying different forecasting to supply chain planning. This thesis presents an analysis of the behaviour of a model of a centralised supply chain. The research was conducted within the manufacturing sector and involved the breathing equipment manufacturer Draeger Safety, UK. The modelling process was embedded in the organization and was focused on the client's needs. A simplified model of the Draeger Safety, UK centralised supply chain was developed and validated. The dynamics of the supply chain under the influence of various factors: demand pattern, ordering policy, demand-information sharing, and lead time were observed. Simulation and analysis were performed using system dynamics, non-linear dynamics and control theory. The findings suggest that destructive oscillations of inventory could be generated by internal decision making practices. To reduce the variation in the supply chain system, the adjustment parameters for both inventory and supply line discrepancies should be more comparable in magnitude. Counter- intuitively, in certain fields of decision, sharing demand information can do more harm than good. The linear forecasting ARMA (autoregression and moving average) model and the nonlinear forecasting model Wavelet Neural Network were applied as the supply chain forecasting methods. The performance was tested against supply chain costs. A management microworld was developed, allowing managers to experiment with different decision policies and learn how the supply chain performs.

Actions (login required)

View Item

Downloads