PDF
Full
Outline
In order to realize the safe monitoring of the operation status of hydroelectric units and solve the problem of automated watch keeping, based on speech recognition technology, the normal status model of measurement points based on the operation monitoring information of generating units was established to implement abnormality detection. Firstly, the experimental data of the bearings of Western Reserve University were used to verify the correctness of the selected modeling method of deep convolutional neural network (CNN) and Gaussian mixture model (GMM). Secondly, a total of forty-two measurement points were arranged for the turbine set, and ten sensitive measurement points were selected for position classification based on the rise rate of RMS before and after overspeed. Then some data were selected as training data to get CNN model and unit sound features. The GMM model was obtained by further training. Finally, the scoring results of the test data were used to determine the machine operation status, i.e., the degree of deviation from the normal status was determined to achieve abnormal status detection. The experimental scheme was confirmed by manual annotation, thus verifying the feasibility of the method, which realizes the design of sound-based abnormality detection algorithm for hydropower units.
PDF
87
23
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |
关闭全屏
No. 86 Xueyuan South Road, Haidian District, Beijing
010-62199257
qkjq@cast.org.cn
Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House
