Implementation of a Sequence-to-Sequence Stacked Sparse Long Short-Term Memory Autoencoder for Anomaly Detection on Multivariate Timeseries Data of Industrial Blower Ball Bearing Units.

The advent of Industry 4.0 introduced new ways for businesses to evolve by implementing maintenance policies leading to advancements in terms of productivity, efficiency, and financial performance. In line with the growing emphasis on sustainability, industries implement predictive techniques based on Artificial Intelligence for the purpose of mitigating machine and equipment failures by predicting anomalies during their production process. In this work, a new dataset that was made publicly available, collected from an industrial blower, is presented, analyzed and modeled using a Sequence-to-Sequence Stacked Sparse Long Short-Term Memory Autoencoder. Specifically the right and left mounted ball bearing units were measured during several months of normal operational condition as well as during an encumbered operational state. An anomaly detection model was developed for the purpose of analyzing the operational behavior of the two bearing units. A stacked sparse Long Short-Term Memory Autoencoder was successfully trained on the data obtained from the left unit under normal operating conditions, learning the underlying patterns and statistical connections of the data. The model was evaluated by means of the Mean Squared Error using data from the unit's encumbered state, as well as using data collected from the right unit. The model performed satisfactorily throughout its evaluation on all collected datasets. Also, the model proved its capability for generalization along with adaptability on assessing the behavior of equipment similar to the one it was trained on.

Industrial Data Space Architecture Implementation Using FIWARE.

We are in front of a new digital revolution that will transform the way we understand and use services and infrastructures. One of the key factors of this revolution is related to the evolution of the Internet of Things (IoT). Connected sensors will be installed in cities and homes affecting the daily life of people and providing them new ways of performing their daily activities. However, this revolution will also affect business and industry bringing the IoT to the production processes in what is called Industry 4.0. Sensor-enabled manufacturing equipment will allow real time communication, smart diagnosis and autonomous decision making. In this scope, the Industrial Data Spaces (IDS) Association has created a Reference Architecture model that aims to provide a common frame for designing and deploying Industry IoT infrastructures. In this paper, we present an implementation of such Reference Architecture based on FIWARE open source software components (Generic Enablers). We validate the proposed architecture by deploying and testing it in a real industry use case that tries to improve the maintenance and operation of milling machines. We conclude that the FIWARE-based IDS implementation fits the requirements of the IDS Reference Architecture providing open source software suitable to any Industry 4.0 environment.

Industry 4.0: Machinery integration with supply chain and logistics in compliance with Italian regulations.

This paper shows a real overview of the interconnection and automated integration of 4.0 machinery within the supply chain or logistics of two companies in the southern Italian territory. The authors provide an exhaustive analysis of the Italian legislation and the strict requirements in order to assess which investments are part of Industry 4.0 with a focus on business risk. The work also shows the potential of a new framework developed that allows using OPC-UA and Modbus protocols to access the functional variables of the 4.0 machinery in a bidirectional way, directly from cloud applications. The proposed solutions help companies to develop more efficient production processes and to fulfil the requirements imposed by Italian regulations in order to benefit from Industry 4.0 financial aid.

Adaptive On-the-Fly Changes in Distributed Processing Pipelines.

Distributed data processing systems have become the standard means for big data analytics. These systems are based on processing pipelines where operations on data are performed in a chain of consecutive steps. Normally, the operations performed by these pipelines are set at design time, and any changes to their functionality require the applications to be restarted. This is not always acceptable, for example, when we cannot afford downtime or when a long-running calculation would lose significant progress. The introduction of variation points to distributed processing pipelines allows for on-the-fly updating of individual analysis steps. In this paper, we extend such basic variation point functionality to provide fully automated reconfiguration of the processing steps within a running pipeline through an automated planner. We have enabled pipeline modeling through constraints. Based on these constraints, we not only ensure that configurations are compatible with type but also verify that expected pipeline functionality is achieved. Furthermore, automating the reconfiguration process simplifies its use, in turn allowing users with less development experience to make changes. The system can automatically generate and validate pipeline configurations that achieve a specified goal, selecting from operation definitions available at planning time. It then automatically integrates these configurations into the running pipeline. We verify the system through the testing of a proof-of-concept implementation. The proof of concept also shows promising results when reconfiguration is performed frequently.

Including non-public data and studies in systematic reviews and systematic maps.

Systematic reviews and maps should be based on the best available evidence, and reviewers should make all reasonable efforts to source and include potentially relevant studies. However, reviewers may not be able to consider all existing evidence, since some data and studies may not be publicly available. Including non-public studies in reviews provides a valuable opportunity to increase systematic review/map comprehensiveness, potentially mitigating negative impacts of publication bias. Studies may be non-public for many reasons: some may still be in the process of being published (publication can take a long time); some may not be published due to author/publisher restrictions; publication bias may make it difficult to publish non-significant or negative results. Here, we consider what forms these non-public studies may take and the implications of including them in systematic reviews and maps. Reviewers should carefully consider the advantages and disadvantages of including non-public studies, weighing risks of bias against benefits of increased comprehensiveness. As with all systematic reviews and maps, reviewers must be transparent about methods used to obtain data and avoid risks of bias in their synthesis. We make tentative suggestions for reviewers in situations where non-public data may be present in an evidence base.