Wind power forecasting – A data-driven method along with gated recurrent neural network

In the mechanical transmission system, the gear is one of the most widely used transmission components. The failure of the gear will cause serious accidents and huge economic loss. Therefore, the remaining life prediction of the gear is of great importance. In order to accurately predict the remaining life of the gear, a new type of long-short-term memory neural network with macroscopic–microscopic attention (MMA) is proposed in this article. First, some typical time-domain and frequency-domain characteristics of vibration signals are calculated, respectively, such as the maximum value, the absolute mean value, the standard deviation, the kurtosis, and so on. Then, the principal component of these characteristics is extracted by the isometric mapping method. The importance of fusional characteristic information is filtered via a proposed MMA mechanism so that the input weight of neural network data and recursive data can reach multilevel real-time amplification. With the new long short-term memory neural network, the health characteristics of gear vibration signals can be predicted based on the known fusion features. The experimental results show that this method can predict the remaining life of gears and bearings well, and it has higher prediction accuracy than the conventional prediction methods.

Macroscopic–Microscopic Attention in LSTM Networks Based on Fusion Features for Gear Remaining Life Prediction

Effects of lubrication on gear performance: A review

Long short-term memory neural network with weight amplification and its application into gear remaining useful life prediction

Wind power prediction based on high-frequency SCADA data along with isolation forest and deep learning neural networks

Starved lubrication of a spur gear pair

Investigation on the influence of work holding equipment errors on contact characteristics of face-hobbed hypoid gear

An elastohydrodynamic lubrication line contact-vibration model is proposed to study the stiffness and damping of the oil film existed in the EHL contact region. An initial mutual approach between interacting surfaces, which deviates from the steady-state balanced position, is assumed under the free contact-vibration to predict the response of the mutual approach. An inertia term, which represents the acceleration of the gap motion, is added to the classical force balance equation to form the equation of motion of the mutual approach. Response of the mutual approach is solved based upon the solving of the contact-dynamic model. The oil stiffness is calculated according to the natural frequency of the response under damped and non-damped conditions, the latter of which represents dry contact conditions. The oil film damping is calculated in terms of the principle of the energy conservation which utilizes the whole history of response compared with the log decrement method. Effect of the normal load, the rolling speed and the amplitude of the regular sinusoidal surface waviness on the oil film stiffness, the contact stiffness and the oil film damping are studied. The study provides an insight on the oil film dynamic characteristics of lubricated contact-vibration problems which appear in gears, bearings, etc. The results show that the oil film damping factor decreases with the increasing normal load as well as the increasing rolling speed. The oil film stiffness increases with the normal load and decreases with the rolling speed. Also, compared to the contact stiffness, the oil film stiffness makes less contribution to the total stiffness. The surface waviness amplitude has little effect on the oil film stiffness and the oil film damping.

Oil film stiffness and damping in an elastohydrodynamic lubrication line contact-vibration

Improvement of reliability and wind power generation based on wind turbine real-time condition assessment

Tribological evaluation of a coated spur gear pair

Chaosheng Song

Papers

Starved lubrication of a spur gear pair

Investigation on the influence of work holding equipment errors on contact characteristics of face-hobbed hypoid gear

Oil film stiffness and damping in an elastohydrodynamic lubrication line contact-vibration

Improvement of reliability and wind power generation based on wind turbine real-time condition assessment

Tribological evaluation of a coated spur gear pair