[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122191-en":3,"doc-seo-122191-105":30,"detail-sidebar-cat-0-en-105":90},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},122191,7971461740909,"Levi","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Trustworthy Machine Learning Operations for Predictive Maintenance Solutions","Industrial development and deployment increasingly rely on data-driven models such as predictive maintenance, yet improper training and ongoing maintenance can make predictions incorrect, unreliable, or difficult to interpret. Unlike conventional software, failures in such models often reduce productivity rather than producing traceable software errors. The work applies model performance evaluation measures from trustworthy AI operations (TrustAIOps) to trigger re-evaluation across the data pipeline and the deployed model under MLOps requirements, supporting robust operation amid Industry 4.0 changes.","Proceedings of the 8th European Conference of the Prognostics and Health Management Society 2024-ISBN – 978-1-936263-40-0  \nTrustworthy Machine Learning Operations for Predictive Maintenance Solutions  \nKiavash Fathi 1 , 2 , Tobias Kleinert2 , Hans Wernher van de Venn 1  \n1 Institute of Mechatronic Systems, Zurich University of Applied Sciences, 8400 Winterthur, Switzerland  \n[fath@zhaw.ch](fath@zhaw.ch), [vhns@zhaw.ch](vhns@zhaw.ch)  \n2 Chair of Information and Automation Systems for Process and Material Technology, RWTH Aachen University,  \n52064 Aachen, Germany  \n[kiavash.fathi@rwth-aachen.de](kiavash.fathi@rwth-aachen.de), [kleinert@plt.rwth-aachen.de](kleinert@plt.rwth-aachen.de)  \nABSTRACT  \nWith the ever-growing capabilities of data acquisition and computational units in industry, development, and deployment of data-driven models (e.g., predictive maintenance solutions) have become more abundant. However, if these models are not trained and maintained properly, they can be counterproductive as their predictions may be incorrect, unreliable, or difficult to interpret. In addition, unlike conventional software, the issues with such models often result in reduced productivity rather than traceable software errors. Therefore, we aim to use model performance evaluation measures introduced in trustworthy AI operations (TrustAIOps) to trigger re-evaluation of different parts of the data pipeline and the deployed data-driven model given machine learning operations (MLOps) requirements. We argue that by creating an ecosystem capable of monitoring different aspects of a datadriven solution by integrating and managing the implementation concepts in TrustAIOps and MLOps, it is possible to boost the performance of models given the constant changes induced by the specifications of Industry 4.0 .  \n1. INTRODUCTION  \nData acquisition and computational units improve daily which facilitate the development and deployment of data-driven approaches in Industry 4.0 settings. However, these data-driven models, when not trained and maintained properly, can be counterproductive as their predictions are not correct, reliable or interpretable. Unlike conventional software, the issues with model development manifest themselves in reduced productivity and not in other forms of traceable software error. Infact, when faced with during the run-time, they could be due to the errors from the data acquisition, data preprocessing,  \nKiavash Fathi et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.  \nmodel training or model deployment submodels (Ashmore, Calinescu, & Paterson, 2021) .  \nTo ensure the acceptable performance of data-driven solutions, numerous implementation concepts have been introduced from the machine leaning operations (MLOps) society, which cover different aspects of preparing and deploying a data-driven solution. The following are some the most important characteristics of the models developed given MLOps requirements (Huyen, 2022):  \n1. Reliability: Correctness despite adversity  \n2. Scalability: Possibility of growth in complexity  \n3. Adaptability: Can cope with different data distribution shifts and business requirements  \n4. Maintainability: Documented and open to different tools On the other hand, given the ever-growing application of machine learning solutions in different use cases, especially in safety-critical systems, performance criteria other than the accuracy have been promoted in research targeting trust worthy AI operations (TrustAIOps) which include but are not limited to (Li et al., 2023):  \n1. Robustness: Ability to deal with unseen data  \n2. Generalization: Distilling knowledge from limited training data for accurate predictions on unseen data  \n3. Explainability: Clarity on how a model makes decision  \n4. Trans","cbCaijC38UxYQZK6","https://ap.wps.com/l/cbCaijC38UxYQZK6","pdf",1108506,1,4,"English","en",105,"# Abstract\n# Introduction\n## Model performance and why issues matter\n## MLOps requirements for deployed models\n## TrustAIOps criteria beyond accuracy\n## Problem statement and study focus","[{\"question\":\"Why can predictive maintenance models become counterproductive in practice?\",\"answer\":\"If models are not properly trained and maintained, their predictions may be incorrect, unreliable, or hard to interpret, leading to reduced productivity rather than traceable software errors.\"},{\"question\":\"How do MLOps requirements define what matters for deployed models?\",\"answer\":\"The document highlights reliability, scalability, adaptability, and maintainability as core characteristics for preparing and deploying data-driven solutions under MLOps.\"},{\"question\":\"What is the role of TrustAIOps in this approach?\",\"answer\":\"TrustAIOps provides performance-related criteria such as robustness, generalization, explainability, and transparency, which the work uses to trigger re-evaluation of the data pipeline and deployed model.\"}]","Trustworthy Machine Learning Operations for Predictive Maintenance Solutions | PDF",1785809269,10,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":28},"trustworthy-machine-learning-operations-for-predictive-maintenance-solutions","",{"@graph":36,"@context":84},[37,53,67],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":21},"https://docshare.wps.com/document/trustworthy-machine-learning-operations-for-predictive-maintenance-solutions/122191/",{"url":52,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"Why can predictive maintenance models become counterproductive in practice?","Question",{"text":74,"@type":75},"If models are not properly trained and maintained, their predictions may be incorrect, unreliable, or hard to interpret, leading to reduced productivity rather than traceable software errors.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How do MLOps requirements define what matters for deployed models?",{"text":79,"@type":75},"The document highlights reliability, scalability, adaptability, and maintainability as core characteristics for preparing and deploying data-driven solutions under MLOps.",{"name":81,"@type":72,"acceptedAnswer":82},"What is the role of TrustAIOps in this approach?",{"text":83,"@type":75},"TrustAIOps provides performance-related criteria such as robustness, generalization, explainability, and transparency, which the work uses to trigger re-evaluation of the data pipeline and deployed model.","https://schema.org",{"og:url":52,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,133],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":29,"doc_module":4,"doc_module_name":46,"category_name":131,"show_sort_weight":29,"slug":132},"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":46,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]