We present a prediction framework to estimate the remaining useful life (RUL) of equipment based on the generative adversarial imputation net (GAIN) and multiscale deep convolutional neural network and long short‐term memory (MSDCNN‐LSTM). The method we proposed addresses the problem of missing data caused by sensor failures in engineering applications. First, a binary matrix is used to adjust the proportion of “0” to simulate the number of missing data in the engineering environment. Then, the GAIN model is used to impute the missing data and approximate the true sample distribution. Finally, the MSDCNN‐LSTM model is used for RUL prediction. Experiments are carried out on the commercial modular aero‐propulsion system simulation (C‐MAPSS) dataset to validate the proposed method. The prediction results show that the proposed method outperforms other methods when packet loss occurs, showing significant improvements in the root mean square error (RMSE) and the score function value.
To improve the production efficiency and reduce the labor cost of seedling operations, cabbage was selected as the research subject, and a novel approach based on the attention mechanism combining the deep convolutional neural network (DCNN) and long short-term memory (LSTM) is proposed. First, the cabbage growth data and environmental monitoring data were normalized, and input samples were obtained by sliding the time window. Then, the DCNN and the LSTM were used to extract the spatial feature information and temporal correlation of the samples, respectively. At the same time, the attention mechanism was used to set the weight coefficients of different feature information and highlight the role of the main features of the sample in the model, thereby improving the prediction accuracy. By analyzing the experimental data collected by the Shandong Seedling Plant, the DCNN-LSTM method based on the proposed attention mechanism achieved good prediction results, providing experience for the engineering application of decision-making regarding seedling transplanting time. The experimental data showed that the mean absolute error, root-mean-square error, mean absolute percentage error, and symmetric mean absolute percentage error of the prediction results of this method were 0.356, 0.507, 0.157, and 0.082, respectively. Compared with the CNN, LSTM, LSTM-Attention and CNN-LSTM models, this model showed higher prediction accuracy.
Nitrogen nutrition index (NNI) can monitor winter wheat nitrogen status precisely. Current studies by remote sensing data are to construct the above-ground biomass (AGB) and plant nitrogen concentration (PNC) with spectral indices, respectively, and then substitute them into established NNI equation. This leads to an accumulation of unavoidable error. Therefore, the objective in the study was to construct a direct NNI equation with remote sensing data to reduce this error. Field measurements data including AGB, PNC and canopy hyperspectral at different winter wheat growth stages during 2012/2013, 2013/2014, 2014/2015, 2015/2016 growing seasons in Beijing, China were collected. This study was endeavored to establish a vegetation index critical N dilution curve (Nvic) with two different spectral indices, RTVI (Red edge Triangular Vegetation Index) and NDVI/PPR (the ratio of the normalized difference vegetation index to the plant pigment ratio), which are sensitive to AGB and PNC, respectively. The vegetation index NNI (NNIvi) was calculated from the ratio between the NDVI/PPR and Nvic. Results showed that (1) Nvic can be described by an equation, Nvic = 1106.4(VIRTVI)−1.512, where RTVI ranged from 2.39 to 22.14; the determination coefficient (R2) was 0.57; (2) The NNI based on the above Nvic dilution curve was in good accordance with the classical NNI, with the root mean square error (RMSE), normalized RMSE (nRMSE) and normalized average error (NAE) of 0.194, 22%, and 11%, respectively. The critical nitrogen dilution model constructed in this study was available for winter wheat nitrogen status monitoring. Thus, this study offers a new method which was suitable and convenient for estimating the NNI of the winter wheat and it can reduce quadric error for constructing NNI through indices directly instead of inversing AGB and PNC.
To guarantee the safe operation of machinery and reduce its maintenance costs, estimating its remaining useful life (RUL) is a crucial task. Hence, in this study, a multi-scale memory-enhanced prediction method is proposed to accurately describe the degradation trends of precision equipment. This method is based on a deep learning algorithm and is designed to estimate the RUL of aircraft engines. To handle the complex and multi-fault operating conditions with uncertain properties in RUL estimation, a hybrid model that combines a multi-scale deep convolutional neural network and long short-term memory is presented. Experimental verification was carried out with the Commercial Modular Aero-Propulsion System Simulation dataset from NASA. Compared with multi-scale deep convolutional and long short-term memory networks, the hybrid model performed more efficiently. Furthermore, compared with other state-of-the-art methods, the multi-scale memory-enhanced prediction method can achieve better prognostics, especially for equipment with multiple operating conditions and failure modes.