Search

This paper considers a multi-period multi-product capacitated lot-sizing problem. It develops an integrated predictive maintenance and production planning framework using deep learning and mathematical programming. The objective is to minimise the sum of maintenance, setup, holding, backorder, and production costs, while satisfying the demand for all products over the horizon under consideration. Based on a rolling horizon approach, the model dynamically integrates data-driven predictive maintenance and production planning. The used maintenance policy includes replacements and minimal repairs that are considered as preventive and corrective maintenance, respectively. To select preventive maintenance actions, a long short-term memory model is employed to accurately predict the health condition of the machine. Each rolling horizon consists of ordinary and forecast stages, and by collecting new sensor data, the maintenance and production decisions are simultaneously updated. The resulting integrated framework is validated using a benchmarking data set. The results are compared for different approaches to highlight the advantages of the proposed framework. [ABSTRACT FROM AUTHOR]

Production planning in maintenance facilities that rely on the availability of certified operators is a challenging task. This is primarily attributed to the need for the integration of workforce training with the operations schedule, in addition to the uncertain repair time of some components. We confine our attention to the repair and overhaul of advanced technological devices that are composed of several components. In this context, this study proposes a novel approach to embedding uncertain repair times of faulty components and develops a multi-stage stochastic programming model for integrated production and workforce planning in such facilities under independent random repair time. Our numerical experiments conducted on a range of problem instances expose the significant value of incorporating repair time uncertainty in this problem. [ABSTRACT FROM AUTHOR]

Transforming Pulp and Paper (P&P) mills into Integrated Forest Biorefineries (IFBR) is a prominent solution to save Canadian P&P industry that has been facing decline of conventional paper demand. We propose a comprehensive decision model for the design of IFBR value chains by taking the uncertain demand of bioproducts into consideration. In particular, we propose a multi-stage stochastic programming model to obtain the optimal investment plan over a long-term planning horizon in the presence of various market trends. We also develop a Monte-Carlo simulation platform to validate the proposed model and to compare its performance with alternative decision models. The model is applied to a realistic case study inspired from P&P companies in Canada, where the value of incorporating the dynamic nature of uncertain demand has been estimated. Further, we elaborate on the value of considering flexibility in terms of adjusting the investment plan in response to changes in the demand. Our results indicate that the demand for bioproducts has a substantial impact on the profitability of the IFBR. We also demonstrated the significant value of explicitly incorporating the uncertainty in IFBR network design as well as adapting the investment plan to the changes in the demand. [ABSTRACT FROM AUTHOR]

Companies that provide repair & overhaul services to the users of complex technical systems are confronted with uncertain volume of demand when making tactical decisions such as workforce training and planning of repair operations over an annual planning horizon. Given the high importance of equipment availability (e.g. gas turbines) to the users (e.g, power plants), any delay in the delivery of repaired equipment caused by demand uncertainty would lead to significant penalties and loss of customer goodwill. In this paper, a two-stage stochastic programming model is proposed to obtain the optimal number of items to repair, spare part inventory, and the number of operators to train with the goal of minimising the total expected cost of maintenance operations and late delivery. Outsourcing and borrowing strategies are adopted as corrective measures to reduce the probability of late delivery in the emerge of demand uncertainty. Numerical findings illustrate the importance of integrating uncertainty into these operations planning decisions as well as the mitigation strategies in handling the cost of the system. [ABSTRACT FROM AUTHOR]