The rainflow counting method is a reasonable cyclecounting procedure for fatigue life calculation and simulation testing of structures.It defines cycles as closed stress /strain hysteresis loops.Application of the rai...The rainflow counting method is a reasonable cyclecounting procedure for fatigue life calculation and simulation testing of structures.It defines cycles as closed stress /strain hysteresis loops.Application of the rainflow counting method requires a data processing of the loading spectrum,which consists of the elimination of non-peak value data points,load time histories adjustment and loop extraction.In the data processing of the loading spectrum,if a stress point is neither the peak nor the valley,it will be identified and eliminated from the loading spectrum.Generally,the loading process is idealized as a single peak-valley straight line.But in actually,there are polylines or nearly straight lines between peaks and valleys which can't be ignored.Therefore,in the process of eliminating such data points,it will produce error in method itself.To reduce the error produced by the traditional method itself,a new method which can well simplify the polylines in data processing of loading spectrum is proposed in this paper.Comparing with the original approximation method,the proposed method has higher precision.展开更多
Remaining useful life(RUL)is a significant challenge in prognostics and health management.Existing methods suffer from a severe performance drop,as testing data from engine sensors exhibits high nonlinearity and compl...Remaining useful life(RUL)is a significant challenge in prognostics and health management.Existing methods suffer from a severe performance drop,as testing data from engine sensors exhibits high nonlinearity and complicated fault modes.In this paper,the authors introduce a reinforcement neural architecture search technique based on upper confidence bound(UCB)to optimize an efficient model.UCB explores the combinatorial parameter space of a multi-head convolutional layers concatenate with recurrent layers to search for a suitable architecture.To address the highly nonlinear dataset in complicated working conditions,rainflow counting algorithm is applied to extract features.Experiments are conducted on C-MAPSS dataset.Compared with state-of-the-art,the proposed approach yields better results in both RMSE and scoring function for all the sub-datasets.In multiple working conditions,the authors achieve lower RMSE with significant superiority.The experimental results confirm that the proposed method is an efficient approach for obtaining highly precise RUL predictions.展开更多
基金National Natural Science Foundation of China(No.11272082)
文摘The rainflow counting method is a reasonable cyclecounting procedure for fatigue life calculation and simulation testing of structures.It defines cycles as closed stress /strain hysteresis loops.Application of the rainflow counting method requires a data processing of the loading spectrum,which consists of the elimination of non-peak value data points,load time histories adjustment and loop extraction.In the data processing of the loading spectrum,if a stress point is neither the peak nor the valley,it will be identified and eliminated from the loading spectrum.Generally,the loading process is idealized as a single peak-valley straight line.But in actually,there are polylines or nearly straight lines between peaks and valleys which can't be ignored.Therefore,in the process of eliminating such data points,it will produce error in method itself.To reduce the error produced by the traditional method itself,a new method which can well simplify the polylines in data processing of loading spectrum is proposed in this paper.Comparing with the original approximation method,the proposed method has higher precision.
基金supported by the National Natural Science Foundation of China under Grant Nos.62073197and 61933006。
文摘Remaining useful life(RUL)is a significant challenge in prognostics and health management.Existing methods suffer from a severe performance drop,as testing data from engine sensors exhibits high nonlinearity and complicated fault modes.In this paper,the authors introduce a reinforcement neural architecture search technique based on upper confidence bound(UCB)to optimize an efficient model.UCB explores the combinatorial parameter space of a multi-head convolutional layers concatenate with recurrent layers to search for a suitable architecture.To address the highly nonlinear dataset in complicated working conditions,rainflow counting algorithm is applied to extract features.Experiments are conducted on C-MAPSS dataset.Compared with state-of-the-art,the proposed approach yields better results in both RMSE and scoring function for all the sub-datasets.In multiple working conditions,the authors achieve lower RMSE with significant superiority.The experimental results confirm that the proposed method is an efficient approach for obtaining highly precise RUL predictions.
