Many real-world big data applications in domains like finance, telecommunication and manufacturing rely on the detection of exceedingly rare patterns in large time series data sets. In principle, machine learning models can be trained to detect and classify such patterns. However, these models often lack the necessary robustness for practical applications and do not generalize well in production. Additionally, their intransparent decision-making hampers systematic debugging and improvement. Time series shapelets are a popular data mining primitive that can be used to extract a shape-based feature representation from the data. However, existing algorithms do not adequately consider the robustness and redundancy of these features. While these drawbacks can be compensated if sufficient labeled data is available, this is not possible for highly imbalanced data. We propose alterations to the current state-of-the-art shapelet algorithm that consider the margin of separation and the multivariate dependencies between the extracted features. This results in more robust and diverse features, which in turn translates to higher classification accuracy. We compare our algorithm to the current state-of-the-art using a public benchmark data set. Additionally, we showcase its applicability to highly imbalanced data using a suitable data set from the manufacturing domain.

The increasing global competition demands continuous optimization of products and processes from companies in the process industry. Where conventional methods of Lean Management and Six Sigma reach their limits, new opportunities and challenges arise through increasing connectivity in the Industrial Internet of Things and machine learning. The majority of industrial projects do not reach the deployment or are isolated solutions, as the structures for data integration, training, deployment and maintenance of models are not established. This paper presents the conception of a reference architecture for machine learning in the process industry to support companies in implementing their own specific structures. The focus is on the development process and an exemplary implementation in the brewing industry.

The supply of defect-free, high-quality products is an important success factor for the long-term competitiveness of manufacturing companies. Despite the increasing challenges of rising product variety and complexity and the necessity of economic manufacturing, a comprehensive and reliable quality inspection is often indispensable. In consequence, high inspection volumes turn inspection processes into manufacturing bottlenecks. In this contribution, we investigate a new integrated solution of predictive model-based quality inspection in industrial manufacturing by utilizing Machine Learning techniques and Edge Cloud Computing technology. In contrast to state-of-the-art contributions, we propose a holistic approach comprising the target-oriented data acquisition and processing, modelling and model deployment as well as the technological implementation in the existing IT plant infrastructure. A real industrial use case in SMT manufacturing is presented to underline the procedure and benefits of the proposed method. The results show that by employing the proposed method, inspection volumes can be reduced significantly and thus economic advantages can be generated.

Predictive maintenance is one of the major drivers of Industry 4.0 as it can significantly reduce costs by improving overall equipment effectiveness and extending the remaining useful life of production machines. Most of the potential lies in the brownfield with old equipment where no sensors or connectivity are available. This paper shows how these production machines can be enabled for predictive maintenance by retrofitting with low-cost sensors, an Industrial-Internet-of-Things-architecture and machine learning. An industrial implementation on a heavy lift Electric Monorail System at the BMW Group will be shown.