A novel framework to link Prognostics and Health Management and Product–Service Systems using online simulation

An Integrative Framework for Online Prognostic and Health Management Using Internet of Things and Convolutional Neural Network

With the development of the internet of things (IoTs), big data, smart sensing technology, and cloud technology, the industry has entered a new stage of revolution. Traditional manufacturing enterprises are transforming into service-oriented manufacturing based on prognostic and health management (PHM). However, there is a lack of a systematic and comprehensive framework of PHM to create more added value. In this paper, the authors proposed an integrative framework to systematically solve the problem from three levels: Strategic level of PHM to create added value, tactical level of PHM to make the implementation route, and operational level of PHM in a detailed application. At the strategic level, the authors provided the innovative business model to create added value through the big data. Moreover, to monitor the equipment status, the health index (HI) based on a condition-based maintenance (CBM) method was proposed. At the tactical level, the authors provided the implementation route in application integration, analysis service, and visual management to satisfy the different stakeholders' functional requirements through a convolutional neural network (CNN). At the operational level, the authors constructed a self-sensing network based on anti-inference and self-organizing Zigbee to capture the real-time data from the equipment group. Finally, the authors verified the feasibility of the framework in a real case from China.

An integrated shipment planning and storage capacity decision under uncertainty

Purpose

– In transportation and distribution systems, the shipment decisions, fleet capacity, and storage capacity are interrelated in a complex way, especially when the authors take into account uncertainty of the demand rate and shipment lead time. While shipment planning is tactical or operational in nature, increasing storage capacity often requires top management’s authority. The purpose of this paper is to present a new method to integrate both operational and strategic decision parameters, namely shipment planning and storage capacity decision under uncertainty. The ultimate goal is to provide a near optimal solution that leads to a striking balance between the total logistics costs and product availability, critical in maritime logistics of bulk shipment of commodity items.

Design/methodology/approach

– The authors use simulation as research method. The authors develop a simulation model to investigate the effects of various factors on costs and service levels of a distribution system. The model mimics the transportation and distribution problems of bulk cement in a major cement company in Indonesia consisting of a silo at the port of origin, two silos at two ports of destination, and a number of ships that transport the bulk cement. The authors develop a number of “what-if” scenarios by varying the storage capacity at the port of origin as well as at the ports of destinations, number of ships operated, operating hours of ports, and dispatching rules for the ships. Each scenario is evaluated in terms of costs and service level. A full factorial experiment has been conducted and analysis of variance has been used to analyze the results.

Findings

– The results suggest that the number of ships deployed, silo capacity, working hours of ports, and the dispatching rules of ships significantly affect both total costs and service level. Interestingly, operating fewer ships enables the company to achieve almost the same service level and gaining substantial cost savings if constraints in other part of the system are alleviated, i.e., storage capacities and working hours of ports are extended.

Practical implications

– Cost is a competitive factor for bulk items like cement, and thus the proposed scenarios could be implemented by the company to substantially reduce the transportation and distribution costs. Alleviating storage capacity constraint is obviously an idea that needs to be considered when optimizing shipment planning alone could not give significant improvements.

Originality/value

– Existing research has so far focussed on the optimization of shipment planning/scheduling, and considers shipment planning/scheduling as the objective function while treating the storage capacity as constraints. The simulation model enables “what-if” analyses to be performed and has overcome the difficulties and impracticalities of analytical methods especially when the system incorporates stochastic variables exhibited in the case example. The use of efficient frontier analysis for analyzing the simulation results is a novel idea which has been proven to be effective in screening non-dominated solutions. This has provided the authors with near optimal solutions to trade-off logistics costs and service levels (availability), with minimal experimentation times.