To improve state-of-health (SOH) estimation and remaining useful life (RUL) prediction, a prognostic framework shared by multiple batteries is proposed. A variant long-short-term memory (LSTM) neural ...network (NN), called AST-LSTM NN, is designed to guarantee the performance of proposed framework. Firstly, the input and forget gates are coupled by a fixed connection, which leads simultaneous determination of old information and new data. Secondly, the element-wise product of the new inputs and the historical cell states is conducted for screening out more beneficial information. Thirdly, a peephole connection from the “constant error carousel” (CEC) is added into the output gate to shield the unwanted error signals. AST-LSTM NNs, with mapping structures of many-to-one and one-to-one, are well-trained separately for the prediction of SOH and RUL. Compared with other data-driven methods, the experiments carried on NASA dataset demonstrate our method hits lower average root mean square, 0.0216, and conjunct error, 0.0831, for SOH and RUL, respectively.
Display omitted
•More generic framework applicable to multiple batteries.•Upgraded LSTM NN with tracking cell states actively.•Enhanced LSTM cell with novel structure.•Model with many-to-one structure for SOH estimation.•Accurate and robust multi-step RUL prediction.
The water environment plays an essential role in the mangrove wetland ecosystem. Predicting water quality will help us better protect water resources from pollution, allowing the mangrove ecosystem ...to perform its normal ecological role. New approaches to solve such nonlinear problems need further research since the complexity of water quality data and they are easily affected by the noise. In this paper, we propose a water quality prediction model named CNN-LSTM with Attention (CLA) to predict the water quality variables. We conduct a case study on the water quality dataset of Beilun Estuary to predict pH and NH
3
-N. Linear interpolation and wavelet techniques are used for missing data filling and data denoising, respectively. The hybrid model CNN-LSTM is highly capable of resolving nonlinear time series prediction problems, and the attention mechanism captures longer time dependence. The experimental results show that our model outperforms other ones, and can predict with different time lags in a stable manner.
Evaluating the importance of nodes for complex networks is of great significance to the research of survivability and robusticity of networks. This paper proposes an effective ranking method based on ...degree value and the importance of lines. It can well identify the importance of bridge nodes with lower computational complexity. Firstly, the properties of nodes that are connected to a line are used to compute the importance of the line. Then, the contribution of nodes to the importance of lines is calculated. Finally, degree of nodes and the contribution of nodes to the importance of lines are considered to rank the importance of nodes. Five real networks are used as test data. The experimental results show that our method can effectively evaluate the importance of nodes for complex networks.
•A Node Importance ranking method (DIL) is proposed based on local information.•The importance of line is considered to evaluate the importance of node.•DIL can well identify the importance of nodes especially the bridge nodes.•DIL can be used in large-scale networks with lower computational complexity.
As an important factor affecting the mangrove wetland ecosystem, water quality has become the focus of attention in recent years. Therefore, many studies have focused on the prediction of water ...quality to help establish a regulatory framework for the assessment and management of water pollution and ecosystem health. To make a more accurate and comprehensive forecast analysis of water quality, we propose a method for water quality prediction based on the multi-time scale bidirectional LSTM network. In the method, we improve data integrity and data volume through data preprocessing. And the network processes input data forward and backward and considers the dependencies at multiple time scales. Besides, we use the Box–Behnken experimental design method to adjust hyper-parameters in the process of modeling. In this study, we apply this method to the water quality prediction research of Beilun Estuary, and the performance of our proposed model is evaluated and compared with other models. The experiment results show that this model has better performance in water quality prediction than that of using LSTM or bidirectional LSTM alone.
Graphical Abstract
Schematic of research work
In this paper, we propose a novel hybrid algorithm to construct an improved recurrent neuron network (RNN) for modeling tunnel microwave thermal process. The new design involves a hierarchical ...learning process, in which the recurrent neurons of RNN are optimized by the cuckoo search (CS) algorithm, while effectiveness and efficiency of the model are guaranteed by using the orthogonal least squares (OLS) method, which is a fast approach for construction of neural networks in a stepwise forward procedure. The major contribution is to integrate seamlessly the OLS model selection and CS neuron optimization in an innovative way so that it can well track the underlying dynamic of this complicated thermal process with a very sparse model. By conducting a microwave rice drying experiment, a set of real-world datasets is used to drive the RNN model. Simulation results demonstrate the effectiveness of the proposed model compared with existing well-known approaches in terms of modeling accuracy and model compactness.
The thermal error of a machine tool is one of the main factors affecting the machining accuracy. By establishing the error model and compensating the error, the accuracy can be improved effectively. ...This paper presents a novel static thermal deformation modeling method based on a hybrid CNN-LSTM model with spatiotemporal correlation (ST-CLSTM). Firstly, by organizing the temperature data into a specific matrix, a sample set with spatiotemporal characteristics is constructed. Secondly, using convolutional neural network (CNN) to extract spatiotemporal features in the sample set, the problem of selecting temperature-sensitive points in thermal error modeling can be solved. Thirdly, the long short-term memory (LSTM) network is used to capture the characteristics of temperature change abstractly from the perspective of the time series of temperature data. Finally, the ST-CLSTM model is verified at different working conditions and compared with other traditional methods, such as the multiple linear regression (MLR) model, the back propagation neural network (BPNN) model, the CNN model, and the LSTM model. The experimental results show that the ST-CLSTM model obtains higher prediction accuracy in X, Y, and Z directions, which guarantees the stability of prediction performance. The proposed model possesses strong robustness and shows a preliminary industrial application prospect.
In the traditional microwave heating partial differential equation (PDE) model, one of the main characteristics is the infinite-dimensional nature, which does not allow to readily design and ...implement a controller. Motivated by this obstruction, this paper proposes a microwave heating finite-dimensional ordinary differential equation (ODE) model, which can not only describe the thermodynamics field with nonhomogeneous boundary conditions but also be coupled with the variation of electromagnetic field in temperature-dependent dielectric media. Initially, the equivalent PDE model with a homogeneous boundary condition is derived by constructing an auxiliary function in order to directly derive the eigenspectrum of the spatial differential operator. With the help of model-reduction techniques, the dominant dynamics of temperature distribution are subsequently captured with a reasonable Galerkin truncation. The simulation results on microwave heating a water prototype show that the temporal and the spatial evolution of the temperature profile can be described by solving the temperature-dependent electromagnetic field and the finite-dimensional ODE model. Moreover, the effectiveness of the model is verified by comparing with the numerical results from the traditional COMSOL model. A further development of this ODE model may provide a useful numerical tool for the design and synthesis of microwave heaters to avoid thermal runaway phenomena.
The bearing is one of the key components in modern industrial equipment. In the past few years, many studies have been carried out on bearing diagnosis through data-driven methods. However, there are ...two practical problems. First, under actual working conditions, the lack of fault samples is a major factor that hinders the application of these methods in industrial environments. Second, there is a lack of full utilization of a priori knowledge in the current stage of methods using relational networks for fault diagnosis. It is manifested by the incompleteness of the relational network structure. To address these problems, we present a new diagnosis method based on few-shot learning, which is suitable for the environment where the data is scarce. In this method, we train the model with the data generated by the artificial damaged bearings instead of the data from the real bearing. We experimentally validate the performance improvement of the complete relational network structure. It is able to perform the few-shot learning task better. In addition, we also reduce the global feature discrepancy by introducing an attention mechanism to improve the performance of the model. And the impact of the number of layers of the attention mechanism on the model is also discussed in detail. In this paper, our model performs better under the same experimental conditions compared with other transfer learning models.
Aspect-based sentiment analysis can predict the sentiment polarity of specific aspect terms in the text. Compared to general sentiment analysis, it extracts more useful information and analyzes the ...sentiment more accurately in the comment text. Many previous approaches use long short-term memory networks with attention mechanisms to directly learn aspect-specific representations and model comment text. However, these methods always ignore the importance of the aspect terms position and interactive information between the aspect terms and other words. To address these issues, we propose an improved model based on convolutional neural networks. First, a novel relative position encode layer can integrate the relative position information of specific aspect terms validly in a text. Second, by using the aspect attention mechanism, the semantic relationship between aspect terms and words in the text is fully considered. To verify the effectiveness of the proposed models, we conduct a large number of experiments and comparisons on seven public datasets. The experimental results show that this model outperforms to other state-of-the-art methods.
•A hybrid quantized Elman neural network with quantized training is proposed for STLF.•The GA algorithm is used to optimize the structures of the proposed neural model.•The comparisons for STLF are ...carried out among the ENN, MFNN and our neural models.
This paper investigates the short-term load forecasting (STLF) problem via a hybrid quantized Elman neural network (HQENN) with the least number of quantized inputs, hourly historical load, hourly predicted target temperature and time index. The purpose is to show the capabilities of HQENN to learn the complex dynamics of hourly power load time series and forecast the near future loads with high accuracies. The HQENN model is comprised of the qubit neurons and the classic neurons. The laws of quantum physics are employed to describe the interactions of the qubit neurons and the classic neurons. The extended quantum learning algorithm makes the context-layer weights being extended into the hidden-layer weights matrix such that they can be updated along with hidden-layer weights to extract more information about the load series. To improve the forecasting accuracy, the genetic algorithm (GA) is introduced to obtain the optimal or suboptimal structure of the HQENN model. The results indicate that the forecasting method based on HQENN has an acceptable high accuracy.