Anomaly detection in Time Series Data - Help Required


#1

Dear Group Members,

Greetings for the day.

I am looking for algorithms on Anomaly detection in time series data. It is uni-variate analysis, considering single parameter (inlet pressure) of Air compressor sensor data. The objective is to detect if there is any significant deviation in parameter value in real time.
If any one has worked on similar projects, please share your thoughts.


#2

Hi @m_sunil104

Twitter did a nice bog and package for anomaly detection Twitter , the package is robust but as always with anomaly, you should be ready to spend time on how they do it, if you are working with relatively stable processes ( stationary at least for a certain period, or you do a pre transformation) the method is quite good. I sue something very similar for commodities consumption with good results.

Other point the code is on Github, so if you like to really go very deep !!! it is for you :slight_smile:

Hope this help.

Alain


#3

Thanks Alain for your suggestion…:slight_smile: