Tool wear monitoring is a critical issue in advanced manufacturing systems. In the search for sensing devices that can provide information about the grinding process, Acoustic Emission (AE) appears to be a promising technology. The present paper presents a novel deep learning-based proposal for grinding wheel wear status monitoring using an AE sensor. The most relevant finding is the possibility of efficient feature extraction form frequency plots using CNNs. Feature extraction from FFT plots requires sound domain-expert knowledge, and thus we present a new approach to automated feature extraction using a pre-trained CNN. Using the features extracted for different industrial grinding conditions, t-SNE and PCA clustering algorithms were tested for wheel wear state identification. Results are compared for different industrial grinding conditions. The initial state of the wheel, resulting from the dressing operation, is clearly identified for all the experiments carried out. This is a very important finding, since dressing strongly affects operation performance. When grinding parameters produce acute wear of the wheel, the algorithms show very good clustering performance using the features extracted by the CNN. Performance of both t-SNE and PCA was very much the same, thus confirming the excellent efficiency of the pre-trained CNN for automated feature extraction from FFT plots.

Recent advances in process modeling allow for more accurate prediction of complex phenomena. A combination of different modeling approaches makes it possible to develop new products to set up, control and optimize machining operations. In the near future, a continuous improvement strategy should be adopted, as improvements to advanced models open up new opportunities for industrial applications. In particular, the efforts made by different research groups on grinding have given rise to significant developments in this area, some of which have recently been made into applied software. As an example of the necessity for process modeling and the viability of industrialized tools based on it, this article presents the work carried out on the development of an assistant tool for the setting up and optimization of the centerless grinding process, focusing on avoiding the main limitations of this process and optimizing productivity.

Workpiece rejection originated by thermal damage is of great concern in high added-value industries, such as automotive or aerospace. Surface temperature control is vital to avoid this kind of damage. Difficulties in empirical measurement of surface temperatures in-process imply the measurement in points other than the ground surface. Indirect estimation of temperatures demands the use of thermal models. Among the numerous temperature measuring techniques, infra-red measurement devices excel for their speed and accurate measurements. With all of this in mind, the current work presents a novel temperature estimation system, capable of accurate measurements below the surface as well as correct interpretation and estimation of temperatures. The estimation system was validated by using a series of tests in different grinding conditions that confirm the hypotheses of the error made when measuring temperatures in the workpiece below the surface in grinding. This method provides a flexible and precise way of estimating surface temperatures in grinding processes and has shown to reduce measurement error by up to 60%.