Time Series Forecasting of Motor Bearing Vibration Based on Informer

Abstract

Electric energy, as an economical and clean energy, plays a significant role in the development of science and technology and the economy. The motor is the core equipment of the power station; therefore, monitoring the motor vibration and predicting time series of the bearing vibration can effectively avoid hazards such as bearing heating and reduce energy consumption. Time series forecasting methods of motor bearing vibration based on sliding window forecasting, such as CNN, LSTM, etc., have the problem of error accumulation, and the longer the time-series forecasting, the larger the error. In order to solve the problem of error accumulation caused by the conventional methods of time series forecasting of motor bearing vibration, this paper innovatively introduces Informer into time series forecasting of motor bearing vibration. Based on Transformer, Informer introduces ProbSparse self-attention and self-attention distilling, and applies random search to optimize the model parameters to reduce the error accumulation in forecasting, achieve the optimization of time and space complexity and improve the model forecasting. Comparing the forecasting results of Informer and those of other forecasting models in three publicly available datasets, it is verified that Informer has excellent performance in time series forecasting of motor bearing vibration and the forecasting results reach 10−2∼10−6.

Optimized EWT-Seq2Seq-LSTM with Attention Mechanism to Insulators Fault Prediction

“…The encoding serves as the network’s memory by summarizing the pertinent information in the time series. Let us denote the input time series as , where T is the length of the time series [ 46 ]. The hidden state of the encoder LSTM at time step t is denoted as .…”

Smart Quantum Tunneling Composite Sensors to Monitor FKM and FFKM Seals

“…Such seals are generally formed of highly chemically-resistant elastomeric materials that are costly to purchase, so it is understandable that one may not want to replace a seal before replacement is indicated. At the same time, unplanned maintenance downtime due to equipment failure can be even more costly to a manufacturer than the replacement of the relatively inexpensive consumable [ 34 ]. Therefore, a point exists where optimum cost savings can be achieved by scheduling equipment maintenance at the ideal point.…”

“…Therefore, a point exists where optimum cost savings can be achieved by scheduling equipment maintenance at the ideal point. Broadly, predictive maintenance models have been developed in an attempt to find this point [ 34 , 35 , 36 ] with the ultimate goal of enhancing yield, reducing unplanned downtime, and general improvement of manufacturing efficiency.…”

“…One common approach to implementing predictive maintenance is to ‘sensorize’ equipment in an attempt to connect specific sensor output to critical performance metric information. For example, the use of vibration sensors to measure bearing performance inside a motor, where an optimal sensor location is found, and time-series vibration signals are analyzed to determine the point-of-failure of the bearings in industrial applications [ 34 , 36 ]. One other such example for maintenance of seals is a slit-valve door (BSV) seal described in a U.S. Patent [ 37 ], which is based on the use of sensors positioned on various locations of a slit valve door seal (Bonded Slit Valve, also known as BSV seal) that used external strain sensor data attached to the sealing product (along with other factors) to understand product lifetime, thus creating a seal lifetime monitoring system.…”

The Sunspot Number Forecasting Using a Hybridization Model of EMD, LSTM and Attention Mechanism

“…They used the 2010-2017 sunspot data as the training set to train the model and test its performance. The informer method [27], which is proposed by Haoyi Zhou, et al, can capture the long-range dependency coupling between the input and output data so that the method is more suitable for the time sequence of very long-time spans and have some applications in other fields [28][29][30]. The different neural network algorithms are mutually combined with each other to improve forecasting accuracy, such as CNN-LSTM [31], LSTM-GRU [32] and GRU-CNN [33].…”