Forum Replies Created
-
Posts
-
You will need to tested against our metrics. I.e. you should strive to hit those target values. The comment about monotonic transformation is what has been applied to data set as target vector. Your goal is to emulate it. The metric is grounded in the features derived from the degradation state as found on the images. It is not an equation/formula. The metric is intended to be a straight forward quantitative description of the degradation.
Q1. There is only one metric which quantifies the damage done. It only increases (damage isn’t be removed).
Q2. The scale is not a 0,1. It’s a metric that is consistent across all samples.
Q3. We forgot to link the sample submission to the web page. We’ll provide it in the download repository.
Sorry, this was language that carried over from last year.
If there is interest in holding a webinar to discuss the data, we can arrange that.
It could, but you still have to predict the next maintenance. I.e. what are the cycles to the next maintenance at the end of the window?
It could, but you still have to predict the next maintenance. I.e. what are the cycles to the next maintenance at the end of the window?
cycles_since_new are the number of cycles an engine goes through in it’s life (since new). Cycles in the test data set are obfuscated. The test windows are a random snapshot in an engine’s life and cycle starts at zero on that snapshop, but this is likely not the beginning of the engine’s life.
Hello,
You can add members after you’ve registered. No problem. I’ll check on a size limit, but I don’t think we’ve run into that scenario in the past.
Your final score will only be on validation_submission.jso
You don’t have to submit a submission.jso at all.
Note that the final “n” is dropped on the submission file.
The confidence is not related to the class. If you check the scoring function, you will see that you get no points if you set a confidence of zero.
Can you email [email protected]
I don’t think I understand your question. Can you reword it? Also I could jump on a teams meeting with you.
I’ve heard back.
outside air temperature = C
mean gas temperature = C
power available (this should be pressure altitude) = feet
indicated airspeed = knots
net power = percent
compressor speed = percent
measured torque = percentAlso a great question. I’ll have to check with the individual who gave us the dataset. I’ll let you know if/when I get an answer.
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?
