SENSORLESS DETECTION OF TOOL BREAKAGE IN MILLING

One of the most important research topics in the area of Intelligent Manufacture Systems (IMS) is the automatic detection of tool breakage, wear of chipping during the cutting process. Sensor-based techniques are available for cutting force measurements, but there are drawbacks in this approach in cost and idle times. This work proposes a sensorless monitoring system for tool monitoring in order to detect breakage and chipping by exploiting the wavelet transform and a neural network. Previous works have made use of these tools for monitoring several machining parameters, but we propose an integrated low-cost approach to detect quickly the changes in the tool integrity for monitoring. The system output produces an accurate detection of the tool integrity that enables the system to prevent damage due to tool breakage. This approach allows for an industrial solution to be developed.     

Chemical synthesis of tricaproin, trienantin and tricaprylin

In the present work, we optimised the glycerol + caproic acid/enantic acid/caprylic acid esterification conditions, using chemical routes, in order to get tricaproin, trienantin and tricaprylin in a medium solely composed of reagents. The option for cleaner conditions, without catalyst and solvent was preferred. The best conditions for tricaprylin and trienantin chemical synthesis were 6 h of contact, with a temperature around 160 ± 5 °C, followed by a 20 h of contact using higher temperatures (around 200 ± 5 °C). The volatility of caproic acid impeded the prolonged use of higher temperatures and this limited the yield of tricaproin that could be obtained. The synthesis of these triacylglycerols in the absence of both solvent and catalyst is of importance in consideration of the possible nutritional use of the products so formed.     

Cover Image

The cover image is based on the Review Review: materials and modelling for organic photovoltaic devices by Olivier Doat et al., https://doi.org/10.1002/pi.6280 .

     

The General Solution for Affine Control Systems on Lie Groups

The purpose of this paper is to present explicitly the solution curve for commutative affine control systems on Lie groups under the assumption that the automorphisms associated with the linear vector fields commutes. If we assume that the derivations associated with the linear vector fields of the system are inner, we obtain a simpler solution and we show some results of controllability. To finish, we work with conjugation by homomorphism of Lie groups between affine systems.

     

Feature definition and comprehensive analysis on the robust identification of intraretinal cystoid regions using optical coherence tomography images

Pattern Analysis and Applications - Currently, optical coherence tomography is one of the most used medical imaging modalities, offering cross-sectional representations of the studied tissues. This...     

Unsupervised Domain Adaptation via Principal Subspace Projection for Acoustic Scene Classification

Existing acoustic scene classification (ASC) systems often fail to generalize across different recording devices. In this work, we present an unsupervised domain adaptation method for ASC based on data standardization and feature projection. First, log-amplitude spectro-temporal features are standardized in a band-wise fashion over samples and time. Then, both source- and target-domain samples are projected onto the span of the principal eigenvectors of the covariance matrix of source-domain training data. The proposed method, being devised as a preprocessing procedure, is independent of the choice of the classification algorithm and can be readily applied to any ASC model at a minimal cost. Using the TUT Urban Acoustic Scenes 2018 Mobile Development dataset, we show that the proposed method can provide an absolute increment of over 10% compared to state-of-the-art unsupervised adaptation methods. Furthermore, the proposed method consistently outperforms a recent ASC model that ranked first in Task 1-A of the 2021 DCASE Challenge when evaluated on various unseen devices from the TAU Urban Acoustic Scenes 2020 Mobile Development dataset. In addition, our method appears robust even when provided with a small amount of target-domain data, proving effective using as few as 90 seconds of test audio recordings. Finally, we show that the proposed adaptation method can also be employed as a feature extraction stage for shallower neural networks, thus significantly reducing model complexity.

     

Defining amplifier’s gain to maximize the transmission rate in optical systems using evolutionary algorithms and swarm intelligence

Optical networks are currently the only technology capable of providing extremely high data transmission rates. Because of this, systems must be increasingly efficient and immune to failures. One way to improve network efficiency is to use dynamic approaches like Adaptive Control of Operating Point, which consists of autonomously choosing the best operating point for optical amplifiers on the link, thus providing the best configuration concerning Quality of transmission. Unlike the previous works that focused on optimizing Optical Signal-To-Noise Ratio, our proposal and analysis are focused on maximizing the transmission rate. In this paper, we compare the results obtained by five different and widely used evolutionary and swarm-based algorithms in the search for maximizing the transmission rate in optical links. We have observed that the differential evolution provided the best results in the analyzed scenarios.