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 2. Отображено 2.
18-04-2023 дата публикации

Milling cutter wear monitoring method based on multi-parameter guide space attention mechanism

Номер: CN115971970A
Автор: ZHANG KAI, LAI XUWEI, ZHENG QING, DING GUOFU, LI ZHIXUAN, QIN GUOHAO, DING KUN, LIU YANTAO
Принадлежит:

The invention provides a milling cutter wear monitoring method based on a multi-parameter guide space attention mechanism, which comprises the following steps of: introducing multiple parameters such as milling cutter structure parameters, process parameters and monitoring signal sampling frequency into a deep learning model structure and a parameter design process, and establishing a relation between the multiple parameters and the deep learning model; the provided space attention module can achieve identification of cutting/non-cutting part signal segments in monitoring signals, self-adaptive enhancement or suppression is conducted on the cutting/non-cutting part signal segments, signal segments irrelevant to the cutter state in the signals are shielded, and the cutter abrasion state can be accurately monitored. A new thought is provided for a tool wear monitoring method based on deep learning, the relevance between the model and objects such as a tool and a process is enhanced, and the ...

Подробнее
Номер записи: 1
28-07-2023 дата публикации

Rotary machinery noise label fault diagnosis method based on adaptive symmetry loss

Номер: CN116502085A
Автор: ZHANG KAI, ZHENG QING, QIN GUOHAO, DING GUOFU, LAI XUWEI, LI ZHIXUAN
Принадлежит:

The invention provides a rotary machine noise label fault diagnosis method based on adaptive symmetry loss, and solves the problem that a rotary machine fault diagnosis model based on deep learning under a noise label is easy to be trained by a wrong label sample damage model, and the diagnosis precision is reduced. According to the method, branch convolution is carried out by using a wide convolution kernel, and extraction of vibration signal features by the network is enhanced while the network depth is reserved. And then dynamic weighting is combined with feature information of different scales, and fault features of the rotating machinery are fully and accurately extracted. And finally, performing variance evaluation on the network output features as weight parameters of the adaptive symmetric cross entropy loss function, and performing back propagation to update network parameters.

Подробнее
Номер записи: 2