PDF
Full
Outline
A method of real time warning for slow tires leakage based on machine learning was proposed to detect slow tire leakage in time. Firstly, data preprocessing such as abnormal data cleaning, sliding window mean filtering, isochromatic data interpolation and temperature compensation were carried out based on the original tire pressure data acquired real time. Secondly, the data segment of slow tires leakage was labeled by using the starting time when the absolute value of the tires pressure comparison difference of the self-owned tire for a vehicle was greater than a certain threshold value, and using the ending time at the moment before the first low pressure alarm, and select slow gas leakage data set and construct eigenvalue engineering. Then, data set division, model training, model evaluation and model parameter optimization were made. Finally, the slow leakage for tires predicted by the online model was selected for expert argumentation and user verification. The results show that the model accuracy rate is close to 98%, the average time of model warning is 106.3 h earlier than the low tire pressure alarm at vehicles, which verifies feasibility and reliability of the model algorithm.
PDF
180
79
| 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
