Comparative Performance Analysis of Vibration Prediction Using RNN Techniques

Abstract

Drones are increasingly used in several industries, including rescue, firefighting, and agriculture. If the motor connected to a drone’s propeller is damaged, there is a risk of a drone crash. Therefore, to prevent such incidents, an accurate and quick prediction tool of the motor vibrations in drones is required. In this study, normal and abnormal vibration data were collected from the motor connected to the propeller of a drone. The period and amplitude of the vibrations are consistent in normal vibrations, whereas they are irregular in abnormal vibrations. The collected vibration data were used to train six recurrent neural network (RNN) techniques: long short-term memory (LSTM), attention-LSTM (Attn.-LSTM), bidirectional-LSTM (Bi-LSTM), gated recurrent unit (GRU), attention-GRU (Attn.-GRU), and bidirectional GRU (Bi-GRU). Then, the simulation runtime it took for each RNN technique to predict the vibrations and the accuracy of the predicted vibrations were analyzed to compare the performances of the RNN model. Based on the simulation results, the Attn.-LSTM and Attn.-GRU techniques, incorporating the attention mechanism, had the best efficiency compared to the conventional LSTM and GRU techniques, respectively. The attention mechanism calculates the similarity between the input value and the to-be-predicted value in advance and reflects the similarity in the prediction.

Risks of Drone Use in Light of Literature Studies

“…The aspects mentioned above have a significant impact on the operational safety of the drone. The increase in safety may also result from changes in the design [ 205 , 206 ], appropriate risk analysis tailored to the purpose of the drone [ 163 , 188 , 189 , 202 , 207 , 208 ], and the detection of unexpected behaviours and abnormal situations during the operation of the drone [ 209 , 210 , 211 , 212 , 213 ]. Just as important as the drone’s flight is its landing.…”

LSTM-Autoencoder for Vibration Anomaly Detection in Vertical Carousel Storage and Retrieval System (VCSRS)

“…The equation for the LSTM model can be defined using the mathematical expression below: where describes the input of the LSTM architecture cell, , , and represent the hidden states and cell states of the architecture which are documented in several related theories [ 54 , 55 , 56 , 57 ].…”

Extruder Machine Gear Fault Detection Using Autoencoder LSTM via Sensor Fusion Approach

“…i, f , O represents the input, forget, and output gates, x t describes the current input to the LSTM architectural structure, C t , c t−1 , h t , h t−1 represents the cell state, previous cell state, the hidden cell state, and the previous hidden cell state, respectively, and σ, W, b represents the sigmoid function, weight and bias of each gate [49][50][51][52].…”