{"id":30848342,"url":"https://github.com/aun151214/predictive-maintenance-cmapss","last_synced_at":"2026-05-09T03:34:51.534Z","repository":{"id":312936873,"uuid":"1046482337","full_name":"aun151214/predictive-maintenance-cmapss","owner":"aun151214","description":"Predictive Maintenance on NASA C-MAPSS dataset using LSTM, GRU, and Transformer architectures.","archived":false,"fork":false,"pushed_at":"2025-09-02T22:04:50.000Z","size":12516,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-09-03T00:09:54.072Z","etag":null,"topics":["cmapss","deep-learning","gru","keras","lstm","machine-learning","predictive-maintenance","tensorflow","transformer","turbofan"],"latest_commit_sha":null,"homepage":"https://www.linkedin.com/in/aunali-industrial-ai/","language":"Jupyter Notebook","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/aun151214.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-08-28T18:50:10.000Z","updated_at":"2025-09-02T22:04:53.000Z","dependencies_parsed_at":"2025-09-03T00:22:15.445Z","dependency_job_id":null,"html_url":"https://github.com/aun151214/predictive-maintenance-cmapss","commit_stats":null,"previous_names":["aun151214/predictive-maintenance-cmapss"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/aun151214/predictive-maintenance-cmapss","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aun151214%2Fpredictive-maintenance-cmapss","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aun151214%2Fpredictive-maintenance-cmapss/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aun151214%2Fpredictive-maintenance-cmapss/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aun151214%2Fpredictive-maintenance-cmapss/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/aun151214","download_url":"https://codeload.github.com/aun151214/predictive-maintenance-cmapss/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aun151214%2Fpredictive-maintenance-cmapss/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273990241,"owners_count":25203303,"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":"2025-09-07T02:00:09.463Z","response_time":67,"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":["cmapss","deep-learning","gru","keras","lstm","machine-learning","predictive-maintenance","tensorflow","transformer","turbofan"],"created_at":"2025-09-07T03:08:46.735Z","updated_at":"2026-05-09T03:34:51.502Z","avatar_url":"https://github.com/aun151214.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"🔧 Predictive Maintenance with NASA C-MAPSS Dataset\n\n![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)\n![Python](https://img.shields.io/badge/python-3.11-blue.svg) ![TensorFlow](https://img.shields.io/badge/TensorFlow-2.x-orange.svg) ![scikit-learn](https://img.shields.io/badge/scikit--learn-1.3-green.svg) ![Status](https://img.shields.io/badge/Status-Completed-brightgreen.svg)  \n\n\nThis project implements predictive maintenance using the NASA C-MAPSS Turbofan Engine Degradation Datasets (FD001–FD004).\nThe goal is to predict the Remaining Useful Life (RUL) of engines before failure.\n\nWe benchmark multiple models, from classical ML to deep learning (LSTM, GRU, Transformer).\n\n📂 Project Structure\npredictive-maintenance-cmapss/\n│\n├── data/\n│   ├── raw/              # Original C-MAPSS dataset (train/test/RUL txt files)\n│   └── processed/        # Preprocessed pickles (.pkl) generated by preprocessing\n│\n├── models/               # Saved trained models (.keras)\n├── results/              # Model evaluation outputs (CSV, plots, reports)\n│   ├── final_report.pdf  # Auto-generated summary report\n│   └── final_report.md   # Markdown summary of results\n│\n├── notebooks/            # Jupyter notebooks for exploration\n│   ├── 01_exploration.ipynb\n│   ├── 02_preprocessing.ipynb\n│   ├── 03_baseline_models.ipynb\n│   ├── 04_deep_learning_models.ipynb\n│   ├── 05_other_dl_models.ipynb\n│   └── 07_transformer_fd001.ipynb\n│\n├── src/                  # Training, evaluation, preprocessing scripts\n│   ├── 02_preprocessing.py\n│   ├── train.py\n│   ├── evaluate.py\n│   ├── aggregate_results.py\n│   └── utils.py\n│\n├── run_all.bat           # Full automation: preprocess → train → evaluate → report\n├── requirements.txt\n├── .gitignore\n└── README.md\n\n\n📊 Results\n\nPerformance is reported across all four subsets (FD001–FD004):\n\n| Model       | Dataset | RMSE   | MAE   | R²     |\n| ----------- | ------- | ------ | ----- | ------ |\n| LSTM        | FD001   | 63.61  | 50.67 | -0.358 |\n| LSTM        | FD002   | 68.73  | 54.47 | -0.339 |\n| LSTM        | FD003   | 87.25  | 63.52 | -0.162 |\n| LSTM        | FD004   | 102.05 | 76.52 | -0.311 |\n| GRU         | FD001   | 63.62  | 50.67 | -0.358 |\n| GRU         | FD002   | 68.37  | 54.17 | -0.325 |\n| GRU         | FD003   | 87.21  | 63.49 | -0.161 |\n| GRU         | FD004   | 102.11 | 76.57 | -0.313 |\n| Transformer | FD001   | 47.59  | 36.94 | 0.240  |\n| Transformer | FD002   | 52.94  | 41.11 | 0.206  |\n| Transformer | FD003   | 69.67  | 53.07 | 0.259  |\n| Transformer | FD004   | 80.61  | 59.30 | 0.182  |\n\n\n📄 See the final_report.pdf for full details with tables \u0026 charts.\n\n📥 Dataset Setup\n\nThe dataset comes from NASA’s C-MAPSS Turbofan Engine Degradation Simulation.\n\n🔗 Download here: NASA Prognostics Data Repository\n\nAfter downloading:\n\nExtract files into data/raw/\n\ndata/raw/\n├── train_FD001.txt\n├── test_FD001.txt\n├── RUL_FD001.txt\n├── train_FD002.txt\n├── ...\n\n\nRun preprocessing:\n\npython src/02_preprocessing.py\n\n\nThis will generate .pkl files under data/processed/.\n\n⚙️ Installation\n# Clone repo\ngit clone https://github.com/aun151214/predictive-maintenance-cmapss.git\ncd predictive-maintenance-cmapss\n\n# Create environment\npython -m venv .venv\n.venv\\Scripts\\activate   # Windows\n# source .venv/bin/activate  # Linux/Mac\n\n# Install dependencies\npip install -r requirements.txt\n\n🚀 Usage\n🔹 Train a Model\npython src/train.py --model lstm --dataset FD001 --epochs 100 --batch_size 64\npython src/train.py --model gru --dataset FD002 --epochs 100\npython src/train.py --model transformer --dataset FD004 --epochs 100\n\n🔹 Evaluate a Model\npython src/evaluate.py --model lstm --dataset FD001\n\n🔹 Run Full Pipeline (all models, all datasets, auto-report)\n.\\run_all.bat\n\n\nThis will:\n\nPreprocess datasets\n\nTrain \u0026 evaluate all models on FD001–FD004\n\nSave trained models in models/\n\nSave results in results/\n\nAuto-generate final_report.pdf \u0026 final_report.md\n\n📈 Key Insights\n\nTransformer performed best overall on FD001–FD004 (positive R²).\n\nLSTM and GRU underperformed on FD002–FD004 in this run, suggesting tuning/data augmentation needed.\n\nPipeline is fully automated → reproducible for any new dataset.\n\n📜 License\n\nThis project is released under the MIT License.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faun151214%2Fpredictive-maintenance-cmapss","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faun151214%2Fpredictive-maintenance-cmapss","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faun151214%2Fpredictive-maintenance-cmapss/lists"}