3 / 2024-03-07 20:09:13

Empirical evaluation of deep autoencoders for anomaly detection in electricity consumption of rotor spinning system

anomaly detection; deep autoencoders; electricity consumption; rotor spinning system

The anormaly detection of electricity quantity in rotor spinning system plays an important role in realizing energy saving in yarn production. The characteristics of varied working condition and special process of the rotor spinning system, make previous data-driven methods hard to deal with, since the time series data of electricity consumption depends on many factors whose dynamics are often intertwined in many modalities. Motivated by the deep autoencoders that can be adapted to work with a wide variety of input modalities, this paper constructs four types of autoencoder-based models for detecting anomalies in electricity consumption of rotor spinning system, which are composed of convolutional, recurrent, and attention layers. The autoencoder-based model with best performance is selected and compared with the state-of-art methods in experiments. Experimental results on real data sets show that the proposed LSTM VAE method has more advantages than several existing mainstream methods, and provides a new idea for the model selection of energy consumption anomaly detection of rotor rotation system.