Настройки

Укажите год
-

Небесная энциклопедия

Космические корабли и станции, автоматические КА и методы их проектирования, бортовые комплексы управления, системы и средства жизнеобеспечения, особенности технологии производства ракетно-космических систем

Подробнее
-

Мониторинг СМИ

Мониторинг СМИ и социальных сетей. Сканирование интернета, новостных сайтов, специализированных контентных площадок на базе мессенджеров. Гибкие настройки фильтров и первоначальных источников.

Подробнее

Форма поиска

Поддерживает ввод нескольких поисковых фраз (по одной на строку). При поиске обеспечивает поддержку морфологии русского и английского языка
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Ведите корректный номера.
Укажите год
Укажите год
Применить Всего найдено 3. Отображено 3.
23-06-2023 дата публикации

Rotating body target detection neural network model, training method and device

Номер: CN116310302A
Автор: MAO JIANLIN, HUO LIN, SAN HONGJUN, WANG SEN, ZHU YANG, LI RUIQI
Принадлежит:

The invention discloses a rotator target detection neural network model, a training method and a training device, and belongs to the field of artificial intelligence, computer vision and visual vibration displacement measurement. A target detection neural network model is divided into three modules, a lightweight module is used for extracting shallow features, a residual feature pyramid module is used for extracting deep features, and meanwhile, shallow information and depth information are subjected to semantic feature fusion; and the head module is used for finally determining and outputting target position information. On the basis that the model provided by the invention is applied to the monitoring stage of visual vibration measurement of the rotating body, the speed of monitoring the safety performance of the rotating body is effectively improved on the premise of ensuring the monitoring accuracy; the actual engineering application value of the method is proved by comparing vibration ...

Подробнее
Номер записи: 1
13-04-2021 дата публикации

Building waste residue dust-free collection equipment

Номер: CN212952277U
Автор: HUO LIN, HE KUN, LIU JINWEI, OTHER INVENTORS HAVE WAIVED THE RIGHT TO BE MENTIONED, 霍琳, 何坤, 刘金伟, 其他发明人请求不公开姓名
Принадлежит: DOU JINLIAN, 窦金莲

The utility model discloses building waste residue dust-free collecting equipment which comprises a waste residue recycling box, a dust collecting pipe for placing smoke dust for diffusion is assembled at the top end of the waste residue recycling box, a speed reducing pipe is assembled at the right end of the dust collecting pipe, and stirring pipes are evenly assembled on the lower surface of the speed reducing pipe. According to the dust-free building waste residue collecting equipment with the dust collecting pipe, the speed reducing pipe and the stirring pipe, when the dust-free building waste residue collecting equipment is used, building waste residues transported by a large vehicle are poured to the inner surface of the shell from the front end of the waste residue recycling box to be stored or processed, and in the pouring and processing process, the dust-free building waste residue collecting equipment is convenient to use. Large dust carried after airflow passes through the dust ...

Подробнее
Номер записи: 2
13-06-2023 дата публикации

Visual processing-based vibration image target detection method

Номер: CN116258927A
Автор: MAO JIANLIN, HUO LIN, WANG SEN, SAN HONGJUN
Принадлежит:

The invention discloses a vibration image target detection method based on visual processing. The method comprises the following steps: acquiring a vibration image data set; dividing the vibration image data set into a training data set and a verification data set according to the obtained vibration image data set; labeling the training data set and the verification data set to obtain a labeled training set and a labeled verification set; establishing a target detection network model according to a backbone module, a neck module, a multi-scale feature fusion module and a head module which are connected in sequence; calling an annotation training set to train the target detection network model, and obtaining candidate weights after training is finished; evaluating the performance of the candidate weight by using the label verification set to obtain an optimal weight; and detecting a to-be-detected vibration image according to the target detection network model loaded with the optimal weight ...

Подробнее
Номер записи: 3