Artificial intelligence is considered to be a significant technology for driving the future evolution of smart manufacturing environments. At the same time, automated guided vehicles (AGVs) play an essential role in manufacturing systems due to their potential to improve internal logistics by increasing production flexibility. Thereby, the productivity of the entire system relies on the quality of the schedule, which can achieve production cost savings by minimizing delays and the total makespan. However, traditional scheduling algorithms often have difficulties in adapting to changing environment conditions, and the performance of a selected algorithm depends on the individual scheduling problem. Therefore, this paper aimed to analyze the scheduling problem classes of AGVs by applying design science research to develop an algorithm selection approach. The designed artifact addressed a catalogue of characteristics that used several machine learning algorithms to find the optimal solution strategy for the intended scheduling problem. The contribution of this paper is the creation of an algorithm selection method that automatically selects a scheduling algorithm, depending on the problem class and the algorithm space. In this way, production efficiency can be increased by dynamically adapting the AGV schedules. A computational study with benchmark literature instances unveiled the successful implementation of constraint programming solvers for solving JSSP and FJSSP scheduling problems and machine learning algorithms for predicting the most promising solver. The performance of the solvers strongly depended on the given problem class and the problem instance. Consequently, the overall production performance increased by selecting the algorithms per instance. A field experiment in the learning factory at Reutlingen University enabled the validation of the approach within a running production scenario.
This paper proposes a novel framework – “Transparent Reasoning in Artificial intelligence Cause Explanation” (TRACE) – that combines root cause analysis, explainable artificial intelligence, and machine learning in an understandable way for the worker. The goal is to enhance transparency, interpretability, and explainability in AI-driven decision-making processes as well as to increase the acceptance of AI within an industrial manufacturing area. The paper outlines the need of such a framework, describes the design process, and shows a preliminary mockup, a possible underlying software architecture as well as an evaluation and integration plan in an industrial environment.
Autonomous Mobile Robots (AMRs) are increasingly important in Industry 4.0 intralogistics but creating path planning systems that adapt to dynamic and uncertain Flexible Manufacturing Systems (FMS), especially managing conflicts among multiple AMRs with a need for scalable decentralised solutions, remains a significant challenge. This research introduces a dynamic path planning system for AMRs designed for reactive adaptation to FMS disturbances and generalisation across factory layouts, incorporating support for multiple AMRs with integrated conflict avoidance. The system is built on a Multi-Agent Systems (MAS) architecture, where software AMR agents independently calculate their paths using a hybrid Genetic Algorithm (GA) that employs Cell-Based Decomposition (CBD) and optimises path length, smoothness, and overlap via a multi-objective fitness function. Multi-AMR conflict avoidance is implemented using the Iterative Exclusion Principle (IEP), which facilitates priority-based planning, knowledge sharing through Predictive Collision Avoidance (PCA), and iterative replanning among agents communicating via a blackboard agent. Verification demonstrated the system’s ability to successfully avoid deadlocks for up to nine AMRs and exhibit good scalability. Validation in a simulated FMS environment confirmed robust adaptation to various disturbances, including static and dynamic obstacles, while maintaining stable run times and consistent path quality. These results affirm the practical feasibility of this hybrid GA and MAS-based approach for dynamic AMR control in complex industrial settings.
Conventional production systems are evolving through cyber-physical systems and application-oriented approaches of AI, more and more into "smart" production systems, which are characterized among other things by a high level of communication and integration of the individual components. The exchange of information between the systems is usually only oriented towards the data content, where semantics is usually only implicitly considered. The adaptability required by external and internal influences requires the integration of new or the redesign of existing components. Through an open application-oriented ontology the information and communication exchange are extended by explicit semantic information. This enables a better integration of new and an easier reconfiguration of existing components. The developed ontology, the derived application and use of the semantic information will be evaluated by means of a practical use case.
The application of transfer learning to predict sales demand is an emerging topic that has been attracting more and more attention recently. However, the selection of data to be used for the learning process is not trivial. Data resources are usually scarce and often anonymized to a certain extent, so their usability for successful training is not guaranteed. One solution is to use already developed categorization schemes that group time series based on certain calculated parameters, but the derived categories do not necessarily capture the process of time series formation. This research addresses the question of whether categorization schemes are beneficial for transfer learning approaches by conducting an experiment in which Syntetos’, Boylan’s and Croston’s categorization scheme is used in combination with two deep learning architectures for the transfer learning process. The results show that similar patterns are indeed beneficial for prediction, but that models using all available data perform quite similarly.