An online machine learning framework for early detection of product failures in an Industry 4.0 context

ABSTRACT

Current paradigms such as the Internet of Things (IoT) and cyber-physical systems are transforming production environments, where related processes are not only faster and with higher standards, but also more flexible and adaptable to changes in the environment. To address the ever-increasing flexibility requirements while keeping current production standards, a new set of technologies is needed. This paper presents an IoT machine learning and orchestration framework, applied to detection of failures of surface mount devices during production. The paper shows how to build a scalable and flexible system for real-time, online machine learning. Furthermore, the approach is evaluated by using a novel and realistic simulation of a production line for electronic devices as a case study. The system evaluation is done in a holistic manner by analyzing various aspects involving the software architecture, computational scalability, model accuracy, production performance, among others.

KEYWORDS:

• Manufacturing information systems
• automated inspection
• data mining
• information technology
• PCB assembly
• quality
• Industry 4.0
• product failure detection

Disclosure statement

No potential conflict of interest was reported by the authors.

Notes

1. SMT is a method for producing electronic circuits in which the components are mounted directly onto the surface of printed circuit boards.

2. Message Queuing Telemetry Transport is a standard (ISO/IEC PRF 20,922) publish-subscribe-based messaging protocol (Banks and Gupta 2014).

3. Object Linking and Embedding for Process Control.

4. REpresentational State Transfer (REST) or RESTful.

5. Complex-Event Machine Learning (see Soto et al. 2016a).

6. Application Programming Interface.

7. The metrics are the values of the calculation of the performance scores (e.g. Accuracy or RMSE (root-mean-square error)) for classification or regression problems, respectively.

8. Matthews correlation coefficient is a preferred evaluation metric for imbalanced datasets, because it takes into account the weight of all classes.

Additional information

Funding

Work for this paper was supported by the European Commission Horizon 2020 Framework Programme under grant No. 691829 (Ilie-Zudor 2016) and the COMPOSITION project No. 723145 (Jentsch 2016).