{"id":30845782,"url":"https://github.com/deng-cy/deep_learning_topology_opt","last_synced_at":"2025-09-07T00:03:44.717Z","repository":{"id":214549905,"uuid":"242273878","full_name":"deng-cy/deep_learning_topology_opt","owner":"deng-cy","description":"Code for paper \"Self-Directed Online Machine Learning for Topology Optimization\"","archived":false,"fork":false,"pushed_at":"2025-02-17T06:58:54.000Z","size":228,"stargazers_count":126,"open_issues_count":0,"forks_count":26,"subscribers_count":6,"default_branch":"master","last_synced_at":"2025-09-05T02:27:12.365Z","etag":null,"topics":["bat-algorithm","binary-bat-algorithm","comsol","deep-learning","matlab","optimization","python","pytorch","simmulated-annealing","topology-optimization"],"latest_commit_sha":null,"homepage":"","language":"MATLAB","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/deng-cy.png","metadata":{"files":{"readme":"readme.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2020-02-22T03:36:52.000Z","updated_at":"2025-08-24T07:20:07.000Z","dependencies_parsed_at":null,"dependency_job_id":"a0f0c2e5-9ca2-47e3-b073-9639eafda8f4","html_url":"https://github.com/deng-cy/deep_learning_topology_opt","commit_stats":null,"previous_names":["deng-cy/deep_learning_topology_opt"],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/deng-cy/deep_learning_topology_opt","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/deng-cy%2Fdeep_learning_topology_opt","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/deng-cy%2Fdeep_learning_topology_opt/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/deng-cy%2Fdeep_learning_topology_opt/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/deng-cy%2Fdeep_learning_topology_opt/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/deng-cy","download_url":"https://codeload.github.com/deng-cy/deep_learning_topology_opt/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/deng-cy%2Fdeep_learning_topology_opt/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273723780,"owners_count":25156408,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-09-05T02:00:09.113Z","response_time":402,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["bat-algorithm","binary-bat-algorithm","comsol","deep-learning","matlab","optimization","python","pytorch","simmulated-annealing","topology-optimization"],"created_at":"2025-09-07T00:02:01.114Z","updated_at":"2025-09-07T00:03:44.666Z","avatar_url":"https://github.com/deng-cy.png","language":"MATLAB","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Code for _Self-Directed Online Machine Learning for Topology Optimization_\n\n[This repository](https://github.com/deng-cy/deep_learning_topology_opt) contains code of the following paper:\n\nChangyu Deng, Yizhou Wang, Can Qin, Yun Fu, and Wei Lu. \"Self-Directed Online Machine Learning for Topology Optimization.\" Nature Communications\n13.1 (2022) [Website](https://www.nature.com/articles/s41467-021-27713-7) [Download](https://www.nature.com/articles/s41467-021-27713-7.pdf) [arXiv](https://arxiv.org/pdf/2002.01927.pdf)\n\n## Contact\n\nOpen an issue for this repository or send emails to dengcy@umich.edu. I will try to respond within a few hours. Pull requests are welcome.\n\n## Introduction\n\nThere are 8 examples of 4 types in the paper, two compliance minimization problems ([coarse mesh](./force_coarse)/[fine mesh](./force_coarse)), two\nfluid-structure optimization problems ([coarse mesh](./fluid_coarse)/[fine mesh](./fluid_fine)), a heat transfer enhancement problem ([heat](./heat))\nand three truss optimization problems ([truss](./truss)). Their code is in their individual folders; they do not share files. Please refer to\nthe `readme.md` file in their own folder for more specific info.\n\nIf you are not sure which example to start from, I recommend\n\n* [Fluid problem](./fluid_coarse), if you have a GPU. It needs Python, COMSOL and Matlab. It is simple to undertsand and computes fast when you have a\n  GPU.\n\n* [Compliance problem](./force_coarse), if you do not have a GPU. It needs Python, COMSOL and Matlab. It costs least computation but does not leverage\n  GPU, so it will be slower than fluid problems when you have a GPU.\n\n* [Truss problem](./truss), if you only have Python installed and do not want to install Matlab or COMSOL. It only uses Python, yet requires a GPU (\n  you can easily change the code to run on CPU, but you will wait for too long). Also, it is a little harder to understand than compliance problems\n  and fluid problems.\n\nI do NOT recommend starting from the [heat problem](./heat). It is not easy to understand and time-consuming to compute.\n\n## Software environment\n\nFollowing softwares are used by __most__ examples:\n\n* COMSOL Multiphysics 5.4\n* Matlab 2019b\n* Python 3.7\n  * PyTorch 1.2.0\n\nHigher versions should work fine. Lower versions may be compatible. Refer to the folders for more details. Some different packages may be needed.\n\n## Reproducibility\n\nPlease note that the reproducibility is not guranteed due to PyTorch platform (see\nits [documentation](https://pytorch.org/docs/stable/notes/randomness.html#reproducibility)), yet similar results are expected.\n\n## Alternative repositories\n\nThere are four repositories that store the code/data of this work.\n\nCode only:\n\n* [Github repository](https://github.com/deng-cy/deep_learning_topology_opt) (most recommended). It contains latest code and directions to latest\n  data.\n* [Zenodo repository](https://zenodo.org/record/5722376). It contains releases of code.\n\nCode and data (including generated .mph files and optimization results):\n\n* [Google drive](https://drive.google.com/drive/folders/1f6Xrd9e-RAUsh9vqIqUXbEw8F1_2Qg_5?usp=sharing).\n* [Zenodo database](https://doi.org/10.5281/zenodo.5725598).","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdeng-cy%2Fdeep_learning_topology_opt","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdeng-cy%2Fdeep_learning_topology_opt","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdeng-cy%2Fdeep_learning_topology_opt/lists"}