Purpose: Accurate prediction of order demand across omni-channel supply chains improves the management's decision-making ability at strategic, tactical and operational levels. The paper aims to develop a predictive methodology for forecasting near-real-time e-commerce order arrivals in distribution centres, allowing third-party logistics service providers to manage the hour-to-hour fast-changing arrival rates of e-commerce orders better.Design/methodology/approach: The paper proposes a novel machine learning predictive methodology through the integration of the time series data characteristics into the development of an adaptive neuro-fuzzy inference system. A four-stage implementation framework is developed for enabling practitioners to apply the proposed model.Findings: A structured model evaluation framework is constructed for cross-validation of model performance. With the aid of an illustrative case study, forecasting evaluation reveals a high level of accuracy of the proposed machine learning approach in forecasting the arrivals of real e-commerce orders in three different retailers at three-hour intervals.Research limitations/implications: Results from the case study suggest that real-time prediction of individual retailer's e-order arrival is crucial in order to maximize the value of e-order arrival prediction for daily operational decision-making.Originality/value: Earlier researchers examined supply chain demand, forecasting problem in a broader scope, particularly in dealing with the bullwhip effect. Prediction of real-time, hourly based order arrivals has been lacking. The paper fills this research gap by presenting a novel data-driven predictive methodology.
21 June 2020 in International Journal of Computer Integrated Manufacturing
Air cargo loading in terminals demands precise planning to ensure efficient operations and minimise costs with limited time in the airport. Real-time visualisation and loading optimisation are becoming increasingly important due to dynamic loading considerations, including the segregation of dangerous goods and inherent lithium batteries, weight balancing, and oversize cargo handling. A closed-loop dynamic air cargo loading digital twin system, integrating a cargo load plan optimisation simulation, multi-dimensional immersive virtual reality system, Internet of Things, and real-time sensors, is proposed for connecting, monitoring and controlling the operations in physical operations and virtual space. A Cave Automatic Virtual Environment (CAVE)-based virtual reality system is used to visualise and experiment with loading procedures. The system uses a feedback loop during sensor data capture to facilitates the decision-making processes on the optimal cargo load plan. Scenarios are discussed demonstrating the impact of the digital twin system on the daily operations of an air cargo terminal, especially the allocation of dangerous goods and special cargo. Load planners can master complex air cargo load planning through the system with optimal solutions generated. The operations of cargo assembly and security screening with digital twins could be further developed for future development.
7 October 2016 in Journal of Intelligent Manufacturing
Smart manufacturing attempts to build a collaborative and integrated platform to enable flexibility in product design and manufacturing processes so as to better address customer needs. This makes a smooth information flow a prerequisite for smart manufacturing. However, firms usually struggle with a lack of consistency and coherence in communication and information exchange in design and manufacturing practices, a phenomenon called “semantic gap.” This article presents a multitask learning framework to close the semantic gap between customers and designers/engineers to facilitate efficient product codevelopment. We elicited domain knowledge from a product review text corpus and integrated the knowledge into a bidirectional long short-term memory-based multitask learning network. Transfer learning was then applied to adapt the network so it could bridge the semantic gap between customer needs and product specifications. Experiment results indicate that the proposed method unites customer needs and product specifications in smart manufacturing by effectively mapping across these domains.