Authors:
Mangolika Bhattacharya
;
Reenu Mohandas
;
Mihai Penica
;
Mark Southern
;
Karl Vancamp
and
Martin J. Hayes
Affiliation:
University of Limerick, Limerick, Ireland
Keyword(s):
Data Cleaning, Digital Manufacturing, Industry 4.0., Internet of Things (IoT), Message Queuing Telemetry Transport (MQTT) Protocol, Message-Oriented Middleware (MOM).
Abstract:
The recent paradigm shift in the industrial production systems, known as Industry 4.0, changes the work culture in terms of human machine interaction. Human labours are assisted by smart devices and machines as in human-machine cooperation and human-machine collaboration. For enhancing this process, data processing and analyses are needed. Therefore, data collection has become one of the most essential functions of large organizations. In this work, a data engineering experiment for a grinding process within a commercial orthotics manufacturing company is presented. The data collection and labelling is assessed for time stamp latency using the Message Queuing Telemetry Transport (MQTT) protocol. This step is necessary to determine if alarm prediction or ‘front running’ is feasible. The paper analyses the procured dataset and discusses its merits as an alarm predictor, using sparsity indicators and concludes that a new investment in sensor infrastructure is necessary. This work highli
ghts some of the limits of performance that exist for the use of MQTT with existing sensor infrastructure when retrofitting machine learning based alarm prediction in an industrial use case setting. A road-map for potential solution to this problem is provided which needs to be assessed by the company management before further progress can be made.
(More)