Digitalisation is argued to increase the efficiency of maintenance activities in a production system. One consequence of digitalisation is data deluge; this allows data analytics methods and technologies to be used. However, the actual data analytical methods and technologies used may differ, thus leading to many scientific papers on this topic. The purpose of our contribution is to find and cluster scientific papers regarding the implemented approaches relevant for use in production maintenance. Our research is based on a broad, systematic literature review consisting of a two-step search approach combined with additional filtering and classification. Based on the search results, we evaluate and visualise the potential impact of data analytics on the subject of maintenance. The results of this study broadly summarise the research activities in production maintenance, whilst indicating that the impact of data analytics will grow further. Specific methodological approaches are clearly favored.

Factories world-wide do not utilize their existing capacity to a satisfactory level. Several studies indicate an average Overall Equipment Efficiency (OEE) of around 55% in manufacturing industry. One major reason is machine downtime leading to substantial system losses culminating in production plans with unsatisfactory robustness. This paper discusses an approach to integrate maintenance strategies into a production planning approach using discrete event simulation. The aim is to investigate how and where in the planning process maintenance strategies can be integrated and how different maintenance strategies influence production performance and the overall robustness of production plans. The approach is exemplified in an automotive case study, integrating strategies for reactive maintenance in a simulation model to support decision making on how repair orders should be prioritized to increase production performance. The results show that introducing priority-based planning of maintenance activities has a potential to increase productivity by approximately 5%.

Machine failures are major causes of direct downtime as well as system losses (blocked and idle times) in production flows. A previous case study shows that prioritizing bottleneck machines over others has the potential to increase the throughput by about 5%. However, the bottleneck machine in a production system is not static throughout the process of production but shifts from time to time. The approach for this paper is to integrate dynamic maintenance strategies into scheduling of reactive maintenance using Discrete Event Simulation. The aim of the paper is to investigate how a shifting priority strategy could be integrated into the scheduling of reactive maintenance. The approach is applied to and evaluated in an automotive case-study, using simulation for decision support. This shows how to shift prioritization by tracking the momentary bottleneck of the system. The effect of shifting priorities for planning maintenance activities and its specific limitations is discussed.

The analysis of production systems using discrete, event-based simulation is wide spread and generally accepted as a decision support technology. It aims either at the comparison of competitive system designs or the identification of a “best possible” parameter configuration of a simulation model. Here, combinatorial techniques of simulation and optimization methods support the user in finding optimal solutions, but typically result in long computation times, which often prohibits a practical application in industry. This paper presents a fast converging procedure as a combination of heuristic approaches, namely Particle Swarm Optimization and Genetic Algorithm, within a material flow simulation to close this gap. Our integrated implementation allows automated, distributed simulation runs for practical, complex production systems. First results show the proof of concept with a reference model and demonstrate the benefits of combinatorial and parallel processing.

Journal of Simulation (JOS) publishes articles, technical notes, case studies and tutorials in the field of simulation, with a particular focus on the applications of simulation and modelling. Journal of Simulation is an official journal of the OR Society.

The requirements on production systems and their planning and control systems are constantly growing. Systems have to be flexible and provide viable solutions at the same time. Different planning and control approaches, such as optimization, simulation and combination of techniques etc., that attempt to solve the scheduling problems are available. Mathematical solutions which can be found in literature didn’t solve the real-world problems in an appropriate way. Current knowledge based solutions did not give any value about decision reliability as well as their decision attributes are not differentiate enough. We are developing a new rule based approach by using a combination of simulation and a knowledge generation within a dynamic production planning and -control for flow-shops. Ideas of how knowledge can be trained by simulation are presented. Furthermore which kind of rules and attributes can be used and how decisions about the rule selection can be made are shown.