Multi-models and dual-sampling periods quality prediction with time-dimensional K-means and state transition-LSTM network

Prediction of steelmaking process variables using K-medoids and a time-aware LSTM network

A new method is required to address the challenge of predicting process parameters in high-temperature, high-pressure industrial processes. This study proposes a multi-model Long Short-Term Memory (LSTM) network prediction algorithm with irregular time interval sequences to predict the silicon yield in converter steelmaking. The experimental results demonstrate that this algorithm performs better than comparable neural network models in classifying high-dimensional, redundant industrial production data with noise and outliers. The algorithm is evaluated using data from a steel plant. The proposed algorithm has lower errors for predicting the alloy yield than other neural network models. An average mean absolute error (MAE) of less than 0.01 confirms the algorithm's feasibility and practicality.

Intra-annual vegetation changes and spatial variation in China over the past two decades based on remote sensing and time-series clustering

Vegetation is an important link between land, atmosphere, and water, making its changes of great significance. However, existing research has predominantly focused on long-term vegetation changes, neglecting the intra-annual variations of vegetation. Hence, this study is based on the Enhanced Vegetation Index (EVI) data from 2000 to 2022, with a time step of 16 days, to analyze the intra-annual patterns of vegetation changes in China. The average intra-annual EVI values for each municipal-level administrative region were calculated, and the time-series k-means clustering algorithm was employed to divide these regions, exploring the spatial variations in China's intra-annual vegetation changes. Finally, the ridge regression and random forest methods were utilized to assess the drivers of intra-annual vegetation changes. The results showed that: (1) China's vegetation status exhibits a notable intra-annual variation pattern of "high in summer and low in winter," and the changes are more pronounced in the northern regions than in the southern regions; (2) the intra-annual vegetation changes exhibit remarkable regional disparities, and China can be optimally clustered into four distinct clusters, which align well with China's temperature and precipitation zones; and (3) the intra-annual vegetation changes demonstrate significant correlations with meteorological factors such as dew point temperature, precipitation, maximum temperature, and sea-level pressure. In conclusion, our study reveals the characteristics, spatial patterns and driving forces of intra-annual vegetation changes in China, which contribute to explaining ecosystem response mechanisms, providing valuable insights for ecological research and the formulation of ecological conservation and management strategies.

A New Regularized Spatiotemporal Attention-Based LSTM with Application to Nitrogen Oxides Emission Prediction

The data collected from complex process industries are usually time series with considerable nonlinearities and dynamics, as well as excessive redundancy. Moreover, there are temporal and spatial correlations between input variables and key performance variables. These characteristics bring great difficulties to data-driven modeling of the key performance variables. To overcome the problems, a new regularized spatiotemporal attention (STA)-based long short-term memory (LSTM) was developed. First, a standard LSTM network with an STA module was trained to capture the dynamic relationship between input and target variables. Second, the least absolute shrinkage and selection operator was introduced to optimize the STA module. Third, the hyperparameter representing the regularization strength of the algorithm was determined using a moving window cross-validation strategy. Finally, the proposed algorithm was compared to other state-of-the-art algorithms using artificial data, and then it was used to predict the nitrogen oxide emissions of a selective catalytic reduction denitration system. Simulation results showed that the proposed algorithm achieved more accurate predictions than the other algorithms. Furthermore, the statistics and analysis of the importance of the variables are consistent with known chemical-reaction mechanisms and observations of field experts. Thus, the proposed method can provide technical support for the predictive control and optimization of such systems.

Semi-supervised echo state network with temporal-spatial graph regularization for dynamic soft sensor modeling of industrial processes

Echo state network (ESN) has been successfully applied to industrial soft sensor field because of its strong nonlinear and dynamic modeling capability. Nevertheless, the traditional ESN is intrinsically a supervised learning technique, which only depends on labeled samples, but omits a large number of unlabeled samples. In order to eliminate this limitation, this work proposes a semi-supervised ESN method assisted by a temporal-spatial graph regularization (TSG-SSESN) for constructing soft sensor model with all the available samples. Firstly, the traditional supervised ESN is enhanced to construct the semi-supervised ESN (SSESN) model by integrating both unlabeled and labeled samples in the reservoir computing procedure. The SSESN computes the reservoir states under high sampling rate for better process dynamic information mining. Furthermore, the SSESN's output optimization objective is modified by applying the local adjacency graph of all training samples as a regularization term. Especially, in view of the dynamic data characteristic, a temporal-spatial graph is constructed by considering both the temporal relationship and the spatial distances. The applications to a debutanizer column process and a wastewater treatment plant demonstrate that the TSG-SSESN model can build much smoother model and has better generalization capability than the basic ESN models in terms of soft sensor prediction results.