# Predicting time-to-failure using multiple failure datasets and time-series sensors data

I have a dataset of a machine for the past year. The dataset consists of timestamps, various sensors readings, and machine failures. Different sensors have different data recording intervals (some recorded every 5 mins, some recorded every 30 mins), so the timestamps are different for each sensor (temperature, humidity, vibration, etc). A sample dataset (sensors with their respective timestamps) structure is as follows:

There are six failure events during one year time. Each failure event is provided with its timestamp. I want to train a machine learning model using these data and predict future failure occurrences in advance using the streaming data from sensors. My situation is very close to this and this questions. Which ML model will give me a good prediction result? How can I use the failure events as a target in my ML model?

• Question title could read "Which model is recommended for predictive maintenance?" Jun 30 '21 at 13:11

A purely machine-learning based approach may be less than optimal, if you have a very low number of failures or certain types of failures have not been observed, yet (or only very rarely). In that case human knowledge may have to play a major role in any solutions, although perhaps an anonmaly detection approach (e.g. predict with fbprophet and see whether sensor readings lie outside prediction intervals, or train a [e.g. denoising] autoencoder on certain time snippets from normal operation and see whether the hidden representation deviates a lot from the representations for normal) could be conceivable or could at least provide good features for simpler models for predicting upcoming failure times (but that might also flag if things look better than ever seen before...).