Search for: All records

The tools and techniques such as imaging and machine learning used in the measurement of many material and microstructural properties are rapidly evolving. In metals, the grain size is routinely measured to estimate the yield strength. This paper describes some of the algorithms used in processing the microstructures to conduct quantitative measurements. The image processing methods provide the possibility to go beyond calculating the ASTM grain size number and calculate the actual surface area of each grain, grain boundary length, and the shape of the grains. The image analysis methods can be very helpful in conducting detailed quantitative analysis with greater accuracy than many labour-intensive manual methods currently in use. The work describes the complexities in applying the imaging methods and approaches in the metallurgical and materials fields. Successful application of such methods can reduce the time and effort required to characterise microstructures and can provide more precise information. 

This study analyzes transcripts of conversations in which mathematics teachers and researchers debrief videotaped lessons by, in part, examining aggregated classroom data from the videotaped lesson. We conclude that aggregating data in debrief conversations can support teachers’ concept development when the aggregation a) demonstrates internal contrasts and b) is underscored by participants’ discursive moves. Consequently, we recommend that facilitators seeking to prompt teacher learning use lesson-level aggregations to identify and press on comparisons and distinctions in teaching practice. This study can inform research on teacher learning by unpacking how a common practice—aggregating data—contributes to teachers’ concept development and has implications both for practitioners and for the emerging field of classroom data visualization. 

The products manufactured by the additive manufacturing (AM) methods have unique signatures in their microstructures due to the layer by layer manufacturing. Machine learning of microstructures of the printed sample can help in interpreting these signatures and the patterns can be used for either determining the authenticity of the product or for reverse engineering. In this work, specimens of 3D printed glass fiber reinforced polymer (GFRP) composite materials are subjected to imaging and machine learning in order to rebuild the tool path information. Since composites require significant research and development effort, the possibility of rebuilding the tool path by ML methods presents a significant vulnerability for intellectual property. The ML methods require a large training dataset and can be efficient in processing tomography datasets. Two kinds of artificial neural networks with three different algorithms are introduced in this work and their results are compared. A 3D printed GFRP specimen is imaged using a micro CT-scan and the images are processed using binarized statistical image features method for compression without compromising the microstructural information. The ML models are trained on this dataset and the results indicate that the ML is able to identify the printing tool path with accuracy.