How can I design a neural network to detect and classify faults in a system?

the faults that I will detect are from the electrical system whose data I will obtain from the simulation of an electrical line which are current and voltage

Answer 1

[David Willingham]

Before even attempting to design and then train a neural network model, I recommend starting with the data.

Does your simulation data capture the faults you want to detect?

Does it capture them multiple times?

Can features be added to the simulation data that makes detecting features easier? For example, do standard statistical measures such as moving averages, max peaks, range etc differ from normal sometime before a fault occurs?

[Image Analyst]

Hopefully since it's a simulation there will be some kind of parameter to specify how frequently faults are put into the signals.

[Luis Zambrano Macias]

I have 1500 values ​​of voltage and current of three-phase faults, single-phase ground faults, two-phase faults and two-phase ground faults, each of these faults were simulated at a certain distance from a reference point of the electrical system

Answer 2

[Image Analyst]

One additional thing to consider is that you have to have lots of training faults. Otherwise it won't find them. Let's say you have faults 0.1% of the time and you have a dataset that has 10 thousand samples but only 10 had faults. Well, when if you train with that dataset, and then try to use it, it might not find faults. I mean it could say everything is without fault and be 99.9% accurate just by saying all samples are perfect. So obviously you don't want it to miss valid faults so you have to have lots of them in the training set.

https://medium.com/@dmahidhara/dealing-with-rare-events-in-machine-learning-14c2c167e222

Also do you want it to just say the signal has a fault or has no faults? Or do you want it to find the location and duration of the fault?