3 results
Filters
Settings
Now showing1 - 3 of 3
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Explainable Artificial Intelligence to Advance Structural Health MonitoringIn recent years, structural health monitoring (SHM) applications have significantly been enhanced, driven by advancements in artificial intelligence (AI) and machine learning (ML), a subcategory of AI. Although ML algorithms allow detecting patterns and features in sensor data that would otherwise remain undetected, the generally opaque inner processes and black-box character of ML algorithms are limiting the application of ML to SHM. Incomprehensible decision-making processes often result in doubts and mistrust in ML algorithms, expressed by engineers and stakeholders. In an attempt to increase trust in ML algorithms, explainable artificial intelligence (XAI) aims to provide explanations of decisions made by black-box ML algorithms. However, there is a lack of XAI approaches that meet all requirements of SHM applications. This chapter provides a review of ML and XAI approaches relevant to SHM and proposes a conceptual XAI framework pertinent to SHM applications. First, ML algorithms relevant to SHM are categorized. Next, XAI approaches, such as transparent models and model-specific explanations, are presented and categorized to identify XAI approaches appropriate for being implemented in SHM applications. Finally, based on the categorization of ML algorithms and the presentation of XAI approaches, the conceptual XAI framework is introduced. It is expected that the proposed conceptual XAI framework will provide a basis for improving ML acceptance and transparency and therefore increase trust in ML algorithms implemented in SHM applications.Publicationtype: Journal Article151 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Metaization concepts for monitoring-related information(2020-10); ; ; In recent years, structural health monitoring (SHM) has become a widely used state-of-the-art method for analyzing and assessing the condition of civil infrastructure. SHM systems are characterized by a plethora of heterogeneous system components. For optimizing, documenting, and change tracking of SHM systems, information about SHM systems needs to be formally described on a sound basis. However, with current methods, such as ontologies, description languages or metamodels, only a small subset of information inherent to SHM systems, such as information about sensors, can formally be described. This paper presents a conceptual approach towards identifying and specifying monitoring-related information. Based on a summary review of SHM modeling approaches, metaization concepts to overcome the current limitations are discussed and a robust formalism to describe SHM systems mathematically is proposed. The review methodology is based on a three-pillar concept. First, regulations, standards, and guidelines related to SHM and, second, the current research landscape is examined to identify information required for describing SHM systems, and hierarchies of terms are proposed to categorize the findings. Third, metamodel architectures, such as SHM-related ontologies, BIM-based metamodels and description languages, are reviewed with respect to formally describe SHM systems. Being part of the third pillar, mathematical metamodeling approaches based on category theory, set theory and type theory are presented, capable to describe SHM system as well as approaches suitable to couple metamodels. As an outcome of this study, besides a comprehensive review of the above directions, a strategy towards developing a metaization concept is proposed to provide a robust formalism for SHM system descriptions, aiming to advance optimization, documentation, and change tracking of SHM systems.Publicationtype: Journal Article55 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Abstract life-cycle modeling of cyber-physical systems in civil engineering(2020-02-09); ; ; With recent advancements in embedded sensing technologies for the Internet of Things, cyber-physical systems, instrumented with structural health monitoring and control applications, are increasingly implemented in civil engineering. Several approaches towards metamodeling cyber-physical systems in civil engineering have been proposed in recent years, based on unified modeling language (UML), category theory, and abstract algebra. However, life-cycle metamodeling of cyber-physical systems in civil engineering has not yet been addressed in its full generality. The evolution of a cyber-physical system (CPS) during its life cycle typically requires the evolution of the corresponding metamodel, because different components of a system may be added or removed. Therefore, life-cycle metamodeling approaches must provide possibilities to de-scribe temporal behavior of CPS components, which is not supported by current metamodeling approaches utilized in civil engineering practice. Thus, in this study, an abstract modeling concept for integrating tem-poral evolutions of cyber-physical systems in civil engineering into existing metamodeling approaches is pro-posed. The integration starts with a detailed description of a typical CPS life cycle in civil engineering, under-lying unique features for each life-cycle phase. The features characterizing phases of a CPS life cycle are abstracted and formalized by abstract algebraic constructions, supporting diagram-based modeling approach-es, such as UML. Finally, an illustrative example of abstract CPS life-cycle modeling for additive manufac-turing of concrete is presented.Publicationtype: Conference Paper65