{"id":51726243,"url":"https://github.com/josepfontm/eovmitigation","last_synced_at":"2026-07-17T19:06:45.236Z","repository":{"id":175487658,"uuid":"619828307","full_name":"josepfontm/EOVmitigation","owner":"josepfontm","description":"Repository containing multiple EOV Mitigation Procedures for Structural Health Monitoring.","archived":false,"fork":false,"pushed_at":"2024-02-02T11:31:20.000Z","size":37468,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-09-05T01:28:01.500Z","etag":null,"topics":["damage-detection","environmental-and-operational-mitigation","operational-modal-analysis","structural-health-monitoring","vibration-analysis"],"latest_commit_sha":null,"homepage":"","language":"Python","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/josepfontm.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":"2023-03-27T14:01:53.000Z","updated_at":"2023-11-14T05:26:15.000Z","dependencies_parsed_at":null,"dependency_job_id":"bb114f67-7e39-46ea-802e-c49fa24d08be","html_url":"https://github.com/josepfontm/EOVmitigation","commit_stats":null,"previous_names":["josepfontm/eovmitigation"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/josepfontm/EOVmitigation","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/josepfontm%2FEOVmitigation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/josepfontm%2FEOVmitigation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/josepfontm%2FEOVmitigation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/josepfontm%2FEOVmitigation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/josepfontm","download_url":"https://codeload.github.com/josepfontm/EOVmitigation/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/josepfontm%2FEOVmitigation/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35592277,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-07-17T02:00:06.162Z","response_time":116,"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":["damage-detection","environmental-and-operational-mitigation","operational-modal-analysis","structural-health-monitoring","vibration-analysis"],"created_at":"2026-07-17T19:06:42.736Z","updated_at":"2026-07-17T19:06:45.226Z","avatar_url":"https://github.com/josepfontm.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# EOVmitigation\n\n## Interpreting Environmental Variability from Damage Sensitive Features\nResults presented in the [10th ECCOMAS Thematic Conference on Smart Structures and Materials (SMART 2023)](https://www.researchgate.net/publication/373757121_Interpreting_Environmental_Variability_from_Damage_Sensitive_Features). Additional information regarding the project can be found in this [presentation](https://www.researchgate.net/publication/372077222_Interpreting_environmental_variability_from_damage-sensitive_features).\nThe experimental data used in this work was extracted from the [Small-scale wind turbine blade](https://onlinelibrary.wiley.com/doi/epdf/10.1002/stc.2660/) provided by the [Chair of Structural Mechanics and Monitoring](https://chatzi.ibk.ethz.ch/) from ETH Zürich.\n\nThis work is part of an on-going collaboration between IQS School of Engineering, University of Southern Denmark and University of Edinburgh.\n\n### Abstract:\nMitigation of Environmental and Operational Variabilities (EOVs) remains one\nof the main challenges to adopt Structural Health Monitoring (SHM) technologies. Its implementation\nin wind turbines is one of the most challenging due to the adverse weather and\noperating conditions these structures have to face. This work proposes an EOV mitigation\nprocedure based on Principal Component Analysis (PCA), which uses EOV-Sensitive Principal\nComponents (PCs) as a surrogate of EOVs, which may be hard to measure or correctly\nquantify in real-life structures. EOV-Sensitive PCs are conventionally disregarded in an attempt\nto mitigate the effect of environmental variability. Instead, we postulate to use of these\nvariables as predictors in non-linear regression models, similar to how Environmental and Operational\nParameters (EOPs) are used in explicit EOV mitigation procedures. \n\nThe work results are validated under an experimental dataset of a small-scale wind turbine blade with various\ncracks artificially introduced. Temperature conditions are varied using a climate chamber. The\nproposed method outperforms the conventional-PCA-based approach, implying that directly disregarding\nSensitive-EOV PCs is detrimental in the decision-making within a SHM methodology.\nIn addition, the proposed method achieves similar results to an equivalent explicit procedure,\nsuggesting that EOV-Sensitive PCs can replace directly measured EOVs.\n\n### EOV Procedures:\nThe literature regarding EOV Mitigation is extensive. Nonetheless, some examples are presented here for clarity's sake.\nThe following [review](https://link.springer.com/chapter/10.1007/978-3-030-81716-9_15) serves as a good starting point to delve into the world of EOV Mitigation in Data-Driven SHM.\n\nSpecific works on the available approaches:\n- Implicit PCA: Conventionally, the first Principal Components (PCs) are disregarded to correct Damage Sensitive Features (DSFs). The rationale behind Implicit PCA is that PCs can be categorized between EOV-Sensitive, EOV-Insensitive and Noise, in this order [[1]](#1).\n\n- Explicit PCA Regression: A non-linear method is used to find the best fitting polynomial function for the data in the least squares sense. Temperature (or other EOVs) are used as independent variables (predictors), while Principal Components are used as dependent or explained variables. The following papers describes a similar method, but using natural frequencies as DSFs, instead of PCA results [[2]](#2).\n\nOur proposal:\n- PC-Informed Regression: In this publication, we proposed a method that uses the so-called EOV-Sensitive PCs as a surrogate of the Environmental and Operational variables driving the non-stationary behaviour in the DSFs. Hence, a regression model using EOV-Sensitive PCs as predictors and remaining PCs as explained variables. Previous works have explored the use of natural frequencies as surrogate variables for bridge damage detection [[3]](#3).\n\n### Pymodal:\nThe EOV Procedures that can be found in this repo have been added to the [Pymodal library](https://github.com/grcarmenaty/pymodal), an on-going project from the [Group of Applied Mechanics and Advanced Manufacturing (GAM)](https://techtransfer.iqs.edu/grupos/applied-mechanics-and-advanced-manufacturing) at IQS School of Engineering-URL.\n\n### References:\n\u003ca id=\"1\"\u003e[1]\u003c/a\u003e \nA.M. Yan, G. Kerschen, P. De Boe and J.C. Golinval (2005). \n[Structural damage diagnosis under varying environmental conditions - part i: A linear analysis](https://www.sciencedirect.com/science/article/abs/pii/S0888327004001785)\nMech. Syst. Signal Porcess.,vol. 19, no. 4,pp. 847-864\n\n\u003ca id=\"2\"\u003e[2]\u003c/a\u003e \nRoberts C, Cava DG, Avendaño-Valencia LD (2023)\n[Addressing practicalities in multivariate nonlinear regression for mitigating environmental and operational variations](https://journals.sagepub.com/doi/10.1177/14759217221091907)\nStruct. Health Monit.\n\n\u003ca id=\"3\"\u003e[3]\u003c/a\u003e \nWilliam Soo Lon Wah, Yung-Tsang Chen, John S Owen (2021)\n[A regression-based damage detection method for structures subjected to changing environmental and operational conditions](https://www.sciencedirect.com/science/article/pii/S0141029620340633),\nEng. Struct., Volume 228, 111462\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjosepfontm%2Feovmitigation","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjosepfontm%2Feovmitigation","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjosepfontm%2Feovmitigation/lists"}