A Novel Fault Diagnosis Approach for Chillers Based on 1-D Convolutional Neural Network and Gated Recurrent Unit

Abstract

The safety of an Internet Data Center (IDC) is directly determined by the reliability and stability of its chiller system. Thus, combined with deep learning technology, an innovative hybrid fault diagnosis approach (1D-CNN_GRU) based on the time-series sequences is proposed in this study for the chiller system using 1-Dimensional Convolutional Neural Network (1D-CNN) and Gated Recurrent Unit (GRU). Firstly, 1D-CNN is applied to automatically extract the local abstract features of the sensor sequence data. Secondly, GRU with long and short term memory characteristics is applied to capture the global features, as well as the dynamic information of the sequence. Moreover, batch normalization and dropout are introduced to accelerate network training and address the overfitting issue. The effectiveness and reliability of the proposed hybrid algorithm are assessed on the RP-1043 dataset; based on the experimental results, 1D-CNN_GRU displays the best performance compared with the other state-of-the-art algorithms. Further, the experimental results reveal that 1D-CNN_GRU has a superior identification rate for minor faults.

Gated Recurrent Unit Neural Networks for Automatic Modulation Classification With Resource-Constrained End-Devices

“…• Whereas the classification accuracy results are similar with GRU and LSTM cells, GRUs have fewer trainable parameters [43], so they require less memory, and they train and execute faster than LSTMs. • As the transceiver directly provides the I/Q samples of the received signal, the use of this format at the model input is more efficient than the use of amplitude and phase information, the calculation of which involves additional computational overhead for the device.…”

Remaining Useful Life Prediction Using Temporal Convolution with Attention

“…Other works on time series data sets makes use of different architectures of CNNs, RNNs and attention. Chiller fault data sets have shown that one dimensional temporal convolutions have achieved good results [31]. While using two layers, LSTMs have also outperformed other forms of RNNs in detecting faulty conditions in chillers as well.…”

Method for Fault Diagnosis of Temperature-Related MEMS Inertial Sensors by Combining Hilbert–Huang Transform and Deep Learning

“…In [ 35 ], a hierarchical CNN-based FD method was proposed by Guo et al for performing a mechanical FD task. In [ 36 ], Wang et al proposed a 1-D CNN (1D-CNN)-based Hiller system fault diagnosis method that combines 1D-CNN and a gated recurrent unit to perform the fault identification task. In [ 37 ], a random oversampling-based CNN FD method was presented by Chen et al to handle fault confusing problems and is applied in avionics FD.…”

“…Deep learning (DL) learns features from big data [ 32 , 33 ] and avoids the complex processes stemming from handcrafted features. CNN is a powerful DL model for handling two-dimensional (2-D) images and has been used in FD research, such as mechanical systems FD [ 34 , 35 ], circuit systems FD [ 36 ], and avionics FD [ 37 ]. In FD applications, because raw data is often sampled in one-dimensional (1-D) format, researchers have turned to feature extraction operations that construct 2-D features for addressing FD problems using CNNs, such as sliding window [ 38 , 39 ], short time Fourier transform (STFT) [ 40 ], discrete wavelet transform (DWT) [ 41 , 42 ], and Hilbert–Huang transform (HHT) [ 43 , 44 ].…”