Abstract
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.
Highlights
Nowadays, the decreasing sensor prices and the digital transformation are forcing the industry to adopt more flexible data-based solutions
To improve industry 4.0 reference architectures, such as the OpenFog Reference Architecture, we examine applications on intelligent sensors integrations towards real-time decision-making in cloud-fog-edge architectures
These are connected to the controlling PLC through an Extension Terminal (ET), providing real-time data over the samples and the analysts whenever they arrive at the working bench and start running tests
Summary
The decreasing sensor prices and the digital transformation are forcing the industry to adopt more flexible data-based solutions. We present applications and information architectures for integrating intelligent sensors towards real-time decision-making. The main research question of the work is on how to effectively integrate and acquire information from intelligent sensors towards assisting with cloud data-based decisionmaking in real-time. We use automatic identification sensors to trigger and improve the decision-making of the dynamic scheduling of tasks in analytical Quality Control (QC) laboratories. In addition to the main question, other research question arises, more specific to the use case, such as how to provide more precise task and subtask times, using automatic identification, under a mass customization environment to improve dynamic scheduling. An implementation to integrate business data with intelligent sensors for automatic identification, to estimate the duration of tasks and subtasks in real-time, supporting dynamic scheduling in personalized production environments.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
