A Deep Learning Approach for the solution of Probability Density Evolution of Stochastic Systems

TL;DR

This paper introduces DeepPDEM, a deep learning framework that uses physics-informed neural networks to efficiently solve the probability density evolution in stochastic systems without prior simulation data, enabling real-time applications.

Contribution

It presents a novel mesh-free deep learning method, DeepPDEM, that encodes physical laws to solve the General Density Evolution Equation for stochastic systems.

Findings

Accurately predicts probability density evolution in multiple stochastic problems.

Demonstrates efficiency and accuracy over traditional numerical methods.

Applicable for real-time stochastic system analysis and optimization.

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 applica-tions, 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 with-out prior simulation data. Moreover, it can also serve as an efficient surrogate for the solu-tion at any other spatiotemporal points within optimization schemes or real-time applica-tions. 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.