A deep learning approach for the solution of probability density evolution of stochastic systems. (November 2022)

• Record Type: Journal Article
• Authors: Pourtakdoust, Seid H.; Khodabakhsh, Amir H.
• Is Part Of: Structural safety. Volume 99(2022)
• Publication Date: 2022-11
• Subjects: Probability Density Evolution Method (PDEM) -- General Density Evolution Equation (GDEE) -- Physics Informed Neural Network (PINN) -- Deep Neural Network (DNN) -- Probability evolution -- Stochastic systems; Structural stability -- Periodicals; Safety factor in engineering -- Periodicals; Reliability (Engineering) -- Periodicals; Constructions -- Stabilité -- Périodiques; Coefficient de sécurité en ingénierie -- Périodiques; Fiabilité -- Périodiques; 620.86
• DOI: 10.1016/j.strusafe.2022.102256
• Languages: English
• ISSNs: 0167-4730

Abstract

Highlights: Proposed a Physics-Informed DNN surrogate model for the density evolution problem. Utilized a label-free scheme to train the network. Investigated the effects of the hyper-parameters on the accuracy of the surrogate. Abstract: Derivation of the probability density evolution provides invaluable insight into the behavior of many stochastic systems and their performance. However, for most real-time applications, numerical determination of the probability density evolution is a formidable task. The latter is due to the required temporal and spatial discretization schemes that render most computational solutions prohibitive and impractical. In this respect, the development of an efficient computational surrogate model is of paramount importance. Recent studies on the physics-constrained networks show that a suitable surrogate can be achieved by encoding the physical insight into a deep neural network. To this aim, the present work introduces DeepPDEM which utilizes the concept of physics-informed networks to solve the evolution of the probability density via proposing a deep learning method. DeepPDEM learns the General Density Evolution Equation (GDEE) of stochastic structures. This approach paves the way for a mesh-free learning method that can solve the density evolution problem without prior simulation data. Moreover, it can also serve as an efficient surrogate for the solution at any other spatiotemporal points within optimization schemes or real-time applications. To demonstrate the potential applicability of the proposed framework, two network architectures with different activation functions as well as two optimizers are investigated. Numerical implementation on three different problems verifies the accuracy and efficacy of the proposed method.