An Adaptive Quantum Neural Network Steam Turbine Fault Trend Prediction Method

Abstract

The invention discloses a method for predicting fault trends of steam turbines by the aid of adaptive quantum neural networks. The method has the advantages that the traditional three-layer BP (back propagation) neural network models are improved, the quantum neural networks are introduced into the traditional three-layer BP neural network models, trend contribution force of different historical data is analyzed in input layers, influence of the latest data on the trends can be improved, direct connection weights from the input layers to output layers can be increased, excitation functions can be adaptively adjusted by the output layers according to signal characteristics, accordingly, the convergence speeds can be increased, and the prediction precision can be improved; the convergence speeds can be increased by the aid of the method for introducing the adaptive learning efficiency; the method is excellent in reliability and robustness, is key technical research on prediction of the fault trends of the steam turbines and can be widely applied to predicting the fault trends of the steam turbines.

Description

technical field [0001] The invention relates to an adaptive quantum neural network prediction method based on multi-factor input in steam turbine failure trend prediction. Background technique [0002] Turbine faults can affect production in the slightest, and cause system paralysis or even catastrophic accidents in severe cases, resulting in major economic losses. Steam turbine faults have attracted great attention. Generally, large steam turbine generator sets are equipped with TSI (steam turbine on-line vibration monitoring and protection system) and TDM (steam turbine real-time data fault diagnosis system). Fault prediction can reveal the development and changes of faults, and take effective preventive measures before accidents to prevent faults from occurring, so fault prediction is more important than maintenance after faults occur. [0003] The faults of steam turbines generally do not occur instantaneously, and most of them have a certain time delay, that is, it is ...

AI Technical Summary

Problems solved by technology

[0005] 1. The learning efficiency is fixed, and it is easy to fall into the flat area at the bottom of the error surface;

[0006] 2. If a single state variable is modeled, it cannot reflect the influence of other types of state variables on the results and reduce the prediction accuracy;

[0007] 3. According to the fault development mechanism, the trend should be more relevant to the latest data, while the traditional BP network, the input data is equally input to the network, and cannot highlight the influence of the latest data on the result prediction

[0008] 4. The traditional Sigmoid is used as the excitation function of the output layer, and the sensitivity of the model to symptom data with increasing or decreasing trends is insufficient;

[0009] 5. The training speed is slow, there is a risk of catastrophic amnesia during the training process, and the model accuracy is not high

Images