The simultaneous integration of information from sensors with business data and how to acquire valuable information can be challenging. This paper proposes the simultaneous integration of information from sensors and business data. The proposal is supported by an industrial implementation, which integrates intelligent sensors and real-time decision-making, using a combination of PLC and PC Platforms in a three-level architecture: cloud-fog-edge. Automatic identification intelligent sensors are used to improve the decision-making of a dynamic scheduling tool. The proposed platform is applied to an industrial use-case in analytical Quality Control (QC) laboratories. The regulatory complexity, the personalized production, and traceability requirements make QC laboratories an interesting use case. We use intelligent sensors for automatic identification to improve the decision-making of a dynamic scheduling tool. Results show how the integration of intelligent sensors can improve the online scheduling of tasks. Estimations from system processing times decreased by over 30%. The proposed solution can be extended to other applications such as predictive maintenance, chemical industry, and other industries where scheduling and rescheduling are critical factors for the production.

In the last few decades, there has been a growing necessity for systems that handle market changes and personalized customer needs with near mass production efficiency, defined as the new mass customization paradigm. The Industry 5.0 vision further enhances the human-centricity aspect, in the necessity for manufacturing systems to cooperate with workers, taking advantage of their problem-solving capabilities, creativity, and expertise of the manufacturing process. A solution is to develop a flexible manufacturing system capable of handling different customer requests and real-time decisions from operators. This paper tackles these aspects by proposing a digital twin of a robotic system for solution preparation capable of making real-time scheduling decisions and forecasts using a simulation model while allowing human interventions. A discrete event simulation model was used to forecast possible system improvements. The simulation handles real-time scheduling considering the possibility of adding identical parallel machines. Results show that processing multiple jobs simultaneously with more than one machine on critical processes, increasing the robot speed, and using heuristics that emphasize the shortest transportation time can reduce the overall completion time by 82%. The simulation model has an animated visualization window for a deeper understanding of the system.

This article presents a model for courier services designed to guide a fleet of vehicles over a dynamic set of requests. Motivation for this problem comes from a real-world scenario in an ever-changing environment, where the time to solve such optimization problem is constrained instead of endlessly searching for the optimal solution. First, a hybrid method combining Ant Colony Optimization with Local Search is proposed, which is used to solve a given static instance. Then, a framework to handle and adapt to dynamic changes over time is defined. A new method pairing nearest neighbourhood search with subtractive clustering is proposed to improve initial solutions and accelerate the convergence of the optimization algorithm. Overall, the proposed strategy presents good results for the dynamic environment and is suitable to be applied on real-world scenarios.