Impact 2024: The Industrial Data and AI Conference for and by Users | Nominate Speakers Now for a Ch...
Hi @Stig Harald Gustavsen Data augmentation seems like an interesting approach, on the top of my head I can think of two approaches for doing this: The simpler one would be to edit the signals at some points to add values outside of the normal range, e.g. too high temperatures or changes in frequency depending on what kinds of algorithms are being tested. Ideally, this would allow training models to detect anomalies or failures, but hardly would be useful for predictive maintenance. The second one would be to simulate not only the anomalies themselves but how the system would start to degrade over time based on physical models, which would be valuable for predictive maintenance but also requires a deep understanding of the system that are been modeled, in which case ML knowledge would not be enough but subject matter expertise is required. Does that make sense to you?
Thanks @kelvin , One other question, I notice that in several cases the end time seems to be earlier than the start time, as in the bellow image: Which date is a good default option in such cases?
Great, thanks @kelvin I looked into the Events tab in fusion, does it makes sense to consider the work orders and worktask as "maintenance events"? I didn't see a specific label for "Maintenance "
Hi @kelvin I have not found an alarm that clearly indicates an incident. Regarding the maintenance events, how can I look for them? is it in the same alarm signals or is there another place?
Hi @kelvin , Thanks for the response.I also looked into the vibration signals (e.g. VAL_23_YT_96134_01:Z.X.Value) I downloaded the data at the highest frequency available, about 6 samples per minute, and tried to find anomalies using FFT, but did not find any pattern in the frequencies. I'm guessing it is because of one of the following reasons: * The analysis I made was incomplete/incorrect * There is no pattern in the vibration frequencies * The sampling rate is not high enough to correctly map the signal's frequency spectrum. Do you have any comments on that?
Great! Thanks Eniko
Awesome resource! I just took the course. One question, in the last videos it is mentioned that there was a shutdown in July hence the mileage of the valve is counted from that point, also it is suggested to do the same from other maintenance events to measure the mileage between events. Where can I see which were maintenance events? from the time series there are some signals that indicate if the compressor is working or not, but I have not seen one related with a maintenance procedure.
Hi Stig, thanks a lot for the answer. One more related question, for this tag VAL_23_ZT_92538:Z.X.Value that indicated the valve position. Which units can I assume? and also is this at the input of the compressor? I’m looking to map the data of this control valve And also the tag labeled in the image, which does not have units:
Hi Stig, thanks for the suggestion. I'll look into the SDK option to download it. Regarding the use case, it is because we want to make some tests using augmented reality, which required to have the CAD files
Already have an account? Login
Enter your E-mail address. We'll send you an e-mail with instructions to reset your password.
Sorry, we're still checking this file's contents to make sure it's safe to download. Please try again in a few minutes.
Sorry, our virus scanner detected that this file isn't safe to download.