Incorporating Lasso Regression to Physics-Informed Neural Network for Inverse PDE Problem

Partial Differential Equation(PDE)is among the most fundamental tools employed to model dynamic systems.Existing PDE modeling methods are typically derived from established knowledge and known phenomena,which are time-consuming and labor-intensive.Recently,discovering governing PDEs from collected actual data via Physics Informed Neural Networks(PINNs)provides a more efficient way to analyze fresh dynamic systems and establish PEDmodels.This study proposes Sequentially Threshold Least Squares-Lasso(STLasso),a module constructed by incorporating Lasso regression into the Sequentially Threshold Least Squares(STLS)algorithm,which can complete sparse regression of PDE coefficients with the constraints of l0 norm.It further introduces PINN-STLasso,a physics informed neural network combined with Lasso sparse regression,able to find underlying PDEs from data with reduced data requirements and better interpretability.In addition,this research conducts experiments on canonical inverse PDE problems and compares the results to several recent methods.The results demonstrated that the proposed PINN-STLasso outperforms other methods,achieving lower error rates even with less data.

Micromechanical Analysis of Interfacial Debonding in Metal Matrix Composites Subjected to off-axis Loading

This study aims to investigate the effects of interfacial debonding and fiber volume fraction on the stressstrain behavior of the fiber reinforced metal matrix composites subjected to off-axis loading.The generalized method of cells(GMC)is used to analyze a representative element whose fiber shape is circular.The constant compliant interface model(CCI)is also adopted to study the response of composites with imperfect interfacial bonding.Results show that for the composites subjected to off-axis loading,the mechanical behaviors are affected appreciably by the interfacial debonding and the fiber volume fraction.

Physics-Informed Deep Neural Network for Bearing Prognosis with Multisensory Signals

Prognosis of bearing is critical to improve the safety,reliability,and availability of machinery systems,which provides the health condition assessment and determines how long the machine would work before failure occurs by predicting the remaining useful life(RUL).In order to overcome the drawback of pure data-driven methods and predict RUL accurately,a novel physics-informed deep neural network,named degradation consistency recurrent neural network,is proposed for RUL prediction by integrating the natural degradation knowledge of mechanical components.The degradation is monotonic over the whole life of bearings,which is characterized by temperature signals.To incorporate the knowledge of monotonic degradation,a positive increment recurrence relationship is introduced to keep the monotonicity.Thus,the proposed model is relatively well understood and capable to keep the learning process consistent with physical degradation.The effectiveness and merit of the RUL prediction using the proposed method are demonstrated through vibration signals collected from a set of run-to-failure tests.

Hybrid Intelligent Damage Identification of Composite Plate Based on Ensemble Empirical Mode Decomposition and Support Vector Machine

In this paper,a novel method based on strain distribution is presented to determine the presence of damage and its location in composite plate.By building a damage monitoring experimental platform with Fiber Bragg Gratings(FBGs)sensors,impact experiments are made respectively to gain the strain distribution both in heath and damage state.EEMD is used to process the data and IMFs energy feature is evaluated.Then,support vector machine is applied to identify the damage and the testing classification accuracy reaches 92.86%.Finally,by using the influence of the damage position and the propagation path on energy,the damage location is predicted.The experimental results indicate that the proposed method can accurately identify the presence and position of damage.The effectiveness and reliability of the proposed method is verified.