Construction Method of Prediction Model for Remaining Service Life of Wind Turbine Bearings

Abstract

The invention relates to a method for constructing a prediction model for the remaining service life of a wind turbine bearing, in particular to a method for constructing a prediction model for the remaining service life of a wind turbine bearing based on a long-short-term memory network. The purpose of the present invention is to use the long and short-term memory network in deep learning to provide a construction method for the prediction model of the remaining service life of the wind turbine bearing based on the long and short-term memory network, so as to realize the prediction of the remaining service life of the wind turbine bearing. The method proposed by the invention can greatly improve the accuracy of the remaining service life prediction, and is easy to realize the remaining service life prediction of the existing wind turbine bearings of various types. The method of the present invention is realized by the following steps: step 1, collecting bearing vibration data; step 2, data preprocessing; step 3, constructing a long and short-term memory network, configuring network parameters, and specifying training options; step 4, training the network; step 5 , Validation of prediction models.

Description

technical field [0001] The invention relates to a method for constructing a prediction model for the remaining service life of a wind turbine bearing, in particular to a method for constructing a prediction model for the remaining service life of a wind turbine bearing based on a long-short-term memory network. Background technique [0002] Wind energy is a kind of renewable energy with great potential, which has received extensive attention from countries all over the world. Wind power helps to solve the contradiction between economic and social development and environmental pollution, so it plays an important role in adjusting the energy structure. Wind power generation systems generally mainly include wind turbines, gearboxes, blades, power converters and other components, among which wind turbines are the core components of the wind power generation system, realizing the conversion of mechanical energy into electrical energy. Most of the wind turbines are installed in r...

AI Technical Summary

Problems solved by technology

[0008] Disadvantages of the existing technical solution 1: The remaining service life of the artificially stipulated bearing is generally different from the actual situation of the bearing, and the service life of the equipment cannot be maximized, resulting in a higher life cycle cost of the technical solution of the prior art 1

[0010] Disadvantages of the existing technical scheme 2: the extracted characteristic parameters do not necessarily have a strong correlation with the life of the bearing, and the generalization ability of the wind turbine at different speeds is poor; the life regression model is also relatively simple, and it is impossible to discover the bearing vibration. The implicit features in the data are also easily interfered by external noise signals, and there is a problem of large error between the fitted degradation curve and the actual degradation curve, which will eventually lead to low accuracy of the remaining service life prediction value

[0011] In addition, in order to improve the accuracy of remaining service life prediction, technology 2 requires multiple vibration signals as input, and it is often necessary to install vibration sensors at both the drive end and the non-drive end of the wind turbine, which indirectly increases the cost

Images