Collaborative supply chain planning using the artificial neural network approach

Abstract

The purpose of this paper is to show how the concepts of collaborative agents and artificial neural networks (ANNs) can work together to enable collaborative supply chain planning (SCP). An agent-based supply chain network is decomposed into multiple ANNs in a way that the actual customer requirements and the agents' goals and constraints are matched in different stages. An error-minimising algorithm which models the agents' collaboration mechanism is used to train three ANNs, namely the supply net, the production net and the delivery net, for pursuing complete order fulfilment across the supply chain. In the example problem, the collaborative SCP paradigm is applied to determine the supply plan of an alliance of small firms, which provides assemble-to-order goods with short delivery lead-time to a regional market. The calculation results showed that the ANN approach achieved complete order fulfilment and significantly increased the resource utilisation of all supply chain agents.

Applying process mining approach to support the verification of a multi-agent system

“…For instance, an artificial neural network approach had been used in an agent-based supply chain network to enable the planning tasks. The experimental results showed that the performance about order fulfillment and resource utilization had been improved significantly (Chiu 2004). Another approach had linked the intelligent agent with a CPFR process for trading partner negotiation.…”

Simulation Reduction Models Approach Using Neural Network

“…In addition, neural networks have proved there abilities to extract performing models from experimental data [26]. Also the use of neural networks appears recently as an interesting approach within the framework of the supply chain [2,21].…”

A neural network for the reduction of a product-driven system emulation model

“…In addition, neural networks have proved their abilities to extract models from experimental data (Thomas et al 1999). Therefore, the use of neural networks has emerged recently as an interesting approach within the framework of the supply chain (Shervais et al 2003, Chiu andLin 2004).…”