Accelerating the detection of unfeasible hypothetical zeolites via symmetric local interatomic distance criteria

In silico prediction of potential synthetic targets is the prerequisite for function-led discovery of new zeolites. Millions of hypothetical zeolitic structures have been predicted via various computational methods, but most of them are experimentally inaccessible under conventional synthetic conditions.Screening out unfeasible structures is crucial for the selection of synthetic targets with desired functions.The local interatomic distance（LID） criteria are a set of structure rules strictly obeyed by all existing zeolite framework types. Using these criteria, many unfeasible hypothetical structures have been detected. However, to calculate their LIDs, all hypothetical structures need to be fully optimized without symmetry constraints. When evaluating a large number of hypothetical structures, such calculations may become too computationally expensive due to the forbiddingly high degree of freedom. Here, we propose calculating LIDs among structures optimized with symmetry constraints and using them as new structure evaluation criteria, i.e., the LIDsymcriteria, to screen out unfeasible hypothetical structures. We find that the LIDsymcriteria can detect unfeasible structures as many as the original non-symmetric LID criteria do, yet require at least one order of magnitude less computation at the initial geometry optimization stage.

An adaptive data-driven method for accurate prediction of remaining useful life of rolling bearings

A novel data-driven method based on Gaussian mixture model （GMM） and distance evaluation technique （DET） is proposed to predict the remaining useful life （RUL） of rolling bearings. The data sets are clustered by GMM to divide all data sets into several health states adaptively and reasonably. The number of clusters is determined by the minimum description length principle. Thus, either the health state of the data sets or the number of the states is obtained automatically. Meanwhile, the abnormal data sets can be recognized during the clustering process and removed from the training data sets. After obtaining the health states, appropriate features are selected by DET for increasing the classification and prediction accuracy. In the prediction process, each vibration signal is decomposed into several components by empirical mode decomposition. Some common statis- tical parameters of the components are calculated first and then the features are clustered using GMM to divide the data sets into several health states and remove the abnormal data sets. Thereafter, appropriate statistical parameters of the generated components are selected using DET. Finally, least squares support vector machine is utilized to predict the RUL of rolling bearings.Experimental results indicate that the proposed method reliably predicts the RUL of rolling bearings.