In this work, we carried out training and recognition of the types of aberrations corresponding to single Zernike functions, based on the intensity pattern of the point spread function (PSF) using convolutional neural networks. PSF intensity patterns in the focal plane were modeled using a fast Fourier transform algorithm. When training a neural network, the learning coefficient and the number of epochs for a dataset of a given size were selected empirically. The average prediction errors of the neural network for each type of aberration were obtained for a set of 15 Zernike functions from a data set of 15 thousand PSF pictures. As a result of training, for most types of aberrations, averaged absolute errors were obtained in the range of 0.012 – 0.015. However, determining the aberration coefficient (magnitude) requires additional research and data, for example, calculating the PSF in the extrafocal plane.
Industrial processing such as crude oil refining, petrochemical production, power generation and other may involve the transport of hot and cold utilities (fluids or gases) through heat transfer equipment such as heat exchangers. Over time and under various conditions, this transport of such utilities may result in fouling and scale deposits forming within the preheat trains or heat exchangers. Fouling and scale deposits reduce the performance of the equipment, leading to heat energy losses which has a negative productivity impact as well as overall negative economic and environmental impact on the industrial process.
Due to the lack of existing technologies oil refineries clean their key heat transfer equipment during major overhauls or roughly once in 2-4 years. Between these stops heat exchangers work below 50% of their heat transfer efficiency.
Cognitive Cleaning systems and methods integrates chemical innovation, process innovation and business model innovation into a single solution aimed to maximize technical, economic and environmental performance of the industrial processes through reducing energy intensity of the processes via cleanliness of heat exchangers.
Cognitive Cleaning is applicable for wide range of equipment geometry: shell and tube, plate, spiral heat exchangers. According to laboratory tests and on-site implementation's it is safe for equipment and has no harmful residues after cleaning.
Cognitive Cleaning technology was successfully commercialized on operating bitumen units, CDU, VDU, acid alkylation unit; on spiral, plate, shell-and-tube heat exchangers of several refineries of Gazpromneft, LUKOIL, TANECO demonstrated boost in equipment efficiency. Companies were able to extract real value out of previously done investments into digital infrastructure.
Applied cognitive cleaning can keep cleanliness of equipment increasing heat transfer efficiency up to 70%-80%, reduce CO2 emission and return around $2.4B to oil refineries of GCC countries.
The article is dedicated to analysis of the emotional side of the student protest activities on May-June 1968 in France. Different types of the historical sources have been used for better reflection of the events. The comparative historical and psychological methods make possible paying attention to the circumstances of the emotions. The conclusion is made that collective emotional portrait of the French students gave them a civic consciousness experience and developped free discussions on the problems of the universities and society.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.