Add your Insight
30 November 2021
Collaborative production and maintenance in the environment of big data and industry 4.0
The area of production planning (also commonly referred to as lot sizing) has remained very active over the last five decades due to not only the immense potential savings it engenders but also the challenging nature of the problems faced and the lack of a proper understanding of the underlying difficulties. Primarily, given a set of demands/orders over a planning horizon, production planning aims to find the least costly plan, which consists of decisions such as when and how much to produce/stock products, under the natural limitations of a manufacturing system such as capacities. On the other hand, during the production process, machines naturally deteriorate due to aging and wearing, and may then fail. In order to reduce these uncertainties and minimize the disruption in the production system, researchers in the area of maintenance planning have developed various policies in recent decades.
With the advancements of smart sensors such as RFID technologies, it is now possible to collect, store, and process a huge amount of data, which would not have been imagined a few years ago. However, the questions remain if sufficient information can be extracted from such data. Data provides little useful information unless it is properly analyzed. Many emerging frameworks and concepts have stimulated tremendous attentions on big data, as well as associated technologies and business models. The advents in machine learning and artificial intelligence have significantly boosted the accuracy of data-driven descriptions and predictions. The efforts devoted to big data is envisioned to lead transformations in production and maintenance management.
Knowledge learnt from sensor data for maintenance scheduling has gained momentum in recent years. The learning on maintenance scheduling is conventionally performed by the machine suppliers while the learning on production processes is managed by the manufacturers. Nevertheless, in most cases, knowledge learnt from production processes contributes to the understanding of the machine deterioration mechanism, and the sensor measurements on machine status provide valuable information for the manufacturers in their process improvement and production planning. Data sharing between the two parties is envisioned to significantly improve the production and maintenance performance, and lead to a more informative decision-making process.
Deteriorated production lines may be detrimental to product quality, which in turn can be served as an indicator of machine degradation, contributing to the robustness of the production planning and re-planning process. Overall, collaborative learning of the sensor data and production information will lead to an improved production and maintenance strategy. This special issue therefore calls for studies on collaborative production and maintenance planning in the context of industry 4.0. Original research papers, review articles and case studies in the field are welcome. The topics of the special issue include but are not limited to:
- Production planning/lot sizing
- Machine learning in production and maintenance modeling
- Smart manufacturing and production
- Big data analytics in production and maintenance
- Production in industry 4.0
- Prognostic and health management for production systems
- Maintenance modeling and optimization
- Degradation modeling for production systems
- Life cycle management and service
- Scheduling and Discrete Optimization
- Optimization and Machine Learning in Manufacturing and Design
- Automated Systems, Simulation-based Optimization and Reliability Issues
Looking to Publish your Research?
We aim to make publishing with Taylor & Francis a rewarding experience for all our authors. Please visit our Author Services website for more information and guidance, and do contact us if there is anything we can help with!
View the latest tweets from tandfSTEM