Quality control is a fundamental component of many manufacturing processes, especially those involving casting or welding. However, manual quality control procedures are often time-consuming and error-prone. In order to meet the growing demand for high-quality products, the use of intelligent visual inspection systems is becoming essential in production lines. Recently, Convolutional Neural Networks (CNNs) have shown outstanding performance in both image classification and localization tasks. In this article, a system is proposed for the identification of casting defects in X-ray images, based on the Mask Region-based CNN architecture. The proposed defect detection system simultaneously performs defect detection and segmentation on input images, making it suitable for a range of defect detection tasks. It is shown that training the network to simultaneously perform defect detection and defect instance segmentation, results in a higher defect detection accuracy than training on defect detection alone. Transfer learning is leveraged to reduce the training data demands and increase the prediction accuracy of the trained model. More specifically, the model is first trained with two large openly-available image datasets before finetuning on a relatively small metal casting X-ray dataset. The accuracy of the trained model exceeds state-of-the art performance on the GRIMA database of X-ray images (GDXray) Castings dataset and is fast enough to be used in a production setting. The system also performs well on the GDXray Welds dataset. A number of in-depth studies are conducted to explore how transfer learning, multi-task learning, and multi-class learning influence the performance of the trained system.

Machine learning (ML) (a subset of artificial intelligence that focuses on autonomous computer knowledge gain) is actively being used across many domains, such as entertainment, commerce, and increasingly in industrial settings. The wide applicability and low barriers for development of these algorithms are allowing for innovations, once thought unattainable, to be realized in an ever more digital world. As these innovations continue across industries, the manufacturing industry has also begun to gain benefits. With the current push for Smart Manufacturing and Industrie 4.0, ML for manufacturing is experiencing unprecedented levels of interest; but how much is industry actually using these highly-publicized techniques? This paper sorts through a decade of manufacturing publications to quantify the amount of effort being put towards advancing ML in manufacturing. This work identifies both prominent areas of ML use, and popular algorithms. This also allows us to highlight any gaps, or areas where ML could play a vital role. To maximize the search space utilization of this investigation, ML based Natural Language Processing (NLP) techniques were employed to rapidly sort through a vast corpus of engineering documents to identify key areas of research and application, as well as uncover documents most pertinent to this survey. The salient outcome of this research is the presentation of current focus areas and gaps in ML applications to the manufacturing industry, with particular emphasis on cross domain knowledge utilization. A full detailing of methods and findings is presented.

No abstract

The increasing liberalization of European electricity markets, the growing proportion of intermittent renewable energy being fed into the energy grids, and also new challenges in the patterns of energy consumption (such as electric mobility) require flexible and intelligent power grids capable of providing efficient, reliable, economical, and sustainable energy production and distribution. From the supplier side, particularly, the integration of renewable energy sources (e.g., wind and solar) into the grid imposes an engineering and economic challenge because of the limited ability to control and dispatch these energy sources due to their intermittent characteristics. Time-series prediction of wind speed for wind power production is a particularly important and challenging task, wherein prediction intervals (PIs) are preferable results of the prediction, rather than point estimates, because they provide information on the confidence in the prediction. In this paper, two different machine learning approaches to assess PIs of time-series predictions are considered and compared: 1) multilayer perceptron neural networks trained with a multiobjective genetic algorithm and 2) extreme learning machines combined with the nearest neighbors approach. The proposed approaches are applied for short-term wind speed prediction from a real data set of hourly wind speed measurements for the region of Regina in Saskatchewan, Canada. Both approaches demonstrate good prediction precision and provide complementary advantages with respect to different evaluation criteria.