- This topic has 2 replies, 2 voices, and was last updated 8 months, 3 weeks ago by
.
-
Posts
-
Although we do not have any obstacles in dealing with pdf or making json files, we want to ask a question.
Could you answer if it is not violation of competition?
The followings are my question.
1) You’ve mentioned ‘You will be given all of the measured data for four of the assets in the training dataset,’ in the ‘problem’ paragraph. Does it mean training set is a mixture of exactly four run-to-run or run-to-failure operation datasets corresponding to four assets?
IF the answer is yes, the training dataset is recorded from four run-to-run or run-to-failure operation dataset measured from each asset.
Else, the training set contains more than four operation dataset, such as two or more operations from each asset have been recorded.
2) At some point, engine health has been faulty. Then, can the engine restore to normal state? In other words, can the state of the engine be normal once the engine get faulty?
If you require more detailed about question, feel free to ask me.
These are all good questions. The data is recorded from actual helicopter use, as opposed to a lab setting where it’s run to failure. To the best of my knowledge, none of the engines were repaired over the duration of the data collection period(s). Having said that, a degrading engine may only be classified as faulty under some operational conditions. Does this answer your questions?
- You must be logged in to reply to this topic.