Skip to main content

AI-powered framework to solve both forward and inverse problems in structural dynamics

Project description

AIStructDynSolve

Author:

AIStructDynSolve is an artificial intelligence (AI) powered framework designed to solve both forward and inverse problems in structural dynamics. It leverages advanced artificial intelligence methods - particularly physics-informed neural networks (PINNs), Physics-Informed Kolmogorov-Arnold Network(PIKANs) and their extensions - to model, predict, and analyze dynamic structural responses under various loading scenarios, such as seismic excitations.

The framework solves the following ODE of MDOF:

  • M*U_dotdot+C*U_dot+K*U=Pt

  • Initial Conditions: U(t=0)=InitialU U_dot(t=0)=InitialU_dot

The framework aims to:

  • Accurately simulate time-dependent structural behavior (forward problems).
  • Identify structural parameters or input forces from measured responses (inverse problems).
  • Incorporate domain knowledge and physical laws for improved generalization and interpretability.
  • Address challenges in multi-frequency, multi-scale dynamics, especially in earthquake engineering applications.

Date:

  • Initial: 2023/12/26
  • Latest: 2025/07/25

Update Log

  • Version 1.12 - Jul 25, 2025 Fixed minor bugs related to trainable_params handling for inverse problems involving "eq", "eqX", "eqY", or "eqZ".

  • Version 1.11 - Jul 23, 2025 Added support for trainable_params ("mass" or "stiffness" or "damping"or "pt" or "eq" or "eqX" or "eqY" or "eqZ") for inverse problems.

  • Version 1.10 - May 11, 2025 Improved accuracy and stability of PIKANs

  • Version 1.9 - Apr 30, 2025 Added support for EQ2D and EQ3D of structural dynamic simulations, enabling users to analyze 2D and 3D earthquake loading scenarios.

  • Version 1.8 - Apr 12, 2025 Improved accuracy of high-frequency response prediction

  • Version 1.7 - Apr 11, 2025 Minor bug fixes

  • Version 1.6 - Apr 7, 2025 Minor bug fixes

  • Version 1.5 - Jan 13, 2025 Minor bug fixes

  • Version 1.4 - Dec 31, 2024 Minor bug fixes

  • Version 1.3 - Dec 19, 2024 Minor bug fixes

  • Version 1.2 - Dec 18, 2024 Minor bug fixes

  • Version 1.1 - Dec 7, 2024 Minor bug fixes

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

aistructdynsolve-1.12.tar.gz (35.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

AIStructDynSolve-1.12-py3-none-any.whl (90.1 kB view details)

Uploaded Python 3

File details

Details for the file aistructdynsolve-1.12.tar.gz.

File metadata

  • Download URL: aistructdynsolve-1.12.tar.gz
  • Upload date:
  • Size: 35.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.0.1 CPython/3.12.7

File hashes

Hashes for aistructdynsolve-1.12.tar.gz
Algorithm Hash digest
SHA256 745e909e8e377cfc601c8d82fc957d99fb0a460e6caa220195845ede074e21e5
MD5 7436b56d76497820f6f3df6e91ebf114
BLAKE2b-256 fea8c0d9e3f41a932df02e18c0ce62d99a0bd91fbbb8cd0c5bf5cf79ba5a5425

See more details on using hashes here.

File details

Details for the file AIStructDynSolve-1.12-py3-none-any.whl.

File metadata

File hashes

Hashes for AIStructDynSolve-1.12-py3-none-any.whl
Algorithm Hash digest
SHA256 b0e6744ecd358ca39eeed7495386b613b9b7cec9c1f2a65b3b9ff911f7d4a5e6
MD5 6901b90bded60f4df6631d722140f4c4
BLAKE2b-256 513525bee506e75c5ea7036c3df94021deb5c056d2240b1a2d8cd1b9f952d54d

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page