Expert systen1s are receiving widespread interest in n1any fields. One critical application in the drilling industry that is ideally suited to use t.hif'l technology is aut01nated well control. In some drilling situations, particularly slim hole drilling, the reaction time between detection of a kick and the need to take corrective action rnay be only a fraction of a mittute. In this application, a significant amount of data n1ust. be continuously collected, processed: and analyzed in a short period of tiine. Expert systerns can automate these functions. This paper describes the de~ign, developrnent, and testing of an expert system . for well control (X WC) on a slim hole· drilling rig. The use of an expert system operating in real tin1e to perfor rn contplex analysis of the drilling data front rig sensors can significantly reduce false alarm rates as well as the probability of a small kick developing into an uncontrolled situation. The system is unique in several ways. First, it operates in real time. It sarnples flow in, flow out, and other pararneters, processes the data, and transfers the information to the expert system~ Second, the system can be classified as a true hybrid systern in that extensive algoritlunic calculations anclrnodels are incorporated where necessary. Finally, the entire system has been validated in a test well.

Currently, manufacturing industries are faced by ever-growing complexities. On the one hand, sustainability in economic and ecological domains should be considered in manufacturing. With respect to energy, many manufacturing companies still lack energy-efficient processes. On the other hand, Industry 4.0 provides large manufacturing datasets, which can potentially enhance energy efficiency. Here, traditional methods of data analytics reach their limits due to the increasing complexity, high dimensionality and variability in raw data of industrial processes. This paper outlines the potential of deep learning as an enabler for energy efficiency in manufacturing. We believe that enough consideration has not been given to make manufacturing efficient in terms of energy. In this paper, we present three manufacturing environments where available DL approaches are identified as opportunities for the realization of energy-efficient manufacturing.

Machine learning (ML) can be a valuable tool for discovering opportunities to save energy and resources in manufacturing systems. However, the hype around ML in the context of Industry 4.0 in the past few years has led to blind usage of the approach, occasionally resulting in usage when another analysis approach would be better suited. The research presented here uses a novel matrix approach to address this lack of differentiation of when to best use ML for improving energy and resource efficiency in manufacturing, by systematically identifying situations in which ML is well suited. Seventeen generic levers for improving manufacturing energy and resource efficiency are defined. Next, a generic list of six manufacturing data scenarios for when ML is a good method of choice for analysis is created. This results in a comprehensive matrix in which each lever is evaluated along each ML scenario and given a point, providing a quantitative ML suitability score for each lever. The evaluation is conducted by drawing on past studies demonstrating whether ML is appropriate. Specifically, operation parameter and input material optimization, as well as intelligent maintenance, are the levers that score the highest and are thus identified to be most suitable for machine learning. The majority of the remaining levers is deemed to have low suitability for machine learning. This simple yet informative matrix can be used as a guideline in data-driven manufacturing energy and resource efficiency projects to provide an appraisal on the applicability of ML as the initial analysis tool of choice.

No abstract