SUMMARY

Machine learning (ML) has been shown to be very powerful at learning representations from data. Increasingly machine learning is of interest in manufacturing. This is driven by the increase in data made available from Industry 4.0. Deploying an ML model in a new application requires overcoming several barriers associated with resource allocation, data acquisition, and access to ML expertise. To lower these barriers to entry , there has been significant work in the machine learning field, including scalable computing platforms, open-source deep-learning software frameworks, and publicly available fundamental models. While these advances can also be used by ML practitioners in industrial or manufacturing areas, this field has several unique challenges that have limited widespread adoption of ML. These challenges include feature selection from unique data sources, model selection within a new domain, and resource constrained model deployment. This research will advance the state-of-the-art of democratized machine learning in industrial applications through three studies. First, to make full use of the advances from image classification, this work will investigate how advances in convolution neural network architectures can be adapted for sensor data to estimate remaining useful life. Next, an architecture is proposed and tested to use anomaly detection as an input filter on edge devices and reduce the cost of deploying ML models. Finally, Bayesian optimization will be investigated to select the optimal time frequency representation of sensor data without previous domain knowledge . Together, this work will develop an understanding of how to integrate ML with industrial applications, and this knowledge can be leveraged by manufacturers of all sizes to improve manufacturing processes and produced goods.