“…From table 3, NN-based PIML is widely used in PHM due to the advantages of NNs in processing time-series data. Among them, Ma et al [72] emphasized the importance of building degradation models based on physical knowledge and ML. Huang et al [62] extracted physical features from the output of the finite-element model (FEM) as inputs to the NN and designed physical loss functions to evaluate the discrepancy between the prediction of NN and FEM in figure 6.…”
Section: Applications Of Piml In Structural Integritymentioning
The development of machine learning (ML) provides a promising solution to guarantee the structural integrity of critical components during service period. However, considering the lack of respect for the underlying physical laws, the data hungry nature and poor extrapolation performance, the further application of pure data-driven methods in structural integrity is challenged. An emerging ML paradigm, physics-informed machine learning (PIML), attempts to overcome these limitations by embedding physical information into ML models. This paper discusses different ways of embedding physical information into ML and reviews the developments of PIML in structural integrity including failure mechanism modelling and prognostic and health management (PHM). The exploration of the application of PIML to structural integrity demonstrates the potential of PIML for improving consistency with prior knowledge, extrapolation performance, prediction accuracy, interpretability and computational efficiency and reducing dependence on training data. The analysis and findings of this work outline the limitations at this stage and provide some potential research direction of PIML to develop advanced PIML for ensuring structural integrity of engineering systems/facilities.
This article is part of the theme issue 'Physics-informed machine learning and its structural integrity applications (Part 1)'.
“…From table 3, NN-based PIML is widely used in PHM due to the advantages of NNs in processing time-series data. Among them, Ma et al [72] emphasized the importance of building degradation models based on physical knowledge and ML. Huang et al [62] extracted physical features from the output of the finite-element model (FEM) as inputs to the NN and designed physical loss functions to evaluate the discrepancy between the prediction of NN and FEM in figure 6.…”
Section: Applications Of Piml In Structural Integritymentioning
The development of machine learning (ML) provides a promising solution to guarantee the structural integrity of critical components during service period. However, considering the lack of respect for the underlying physical laws, the data hungry nature and poor extrapolation performance, the further application of pure data-driven methods in structural integrity is challenged. An emerging ML paradigm, physics-informed machine learning (PIML), attempts to overcome these limitations by embedding physical information into ML models. This paper discusses different ways of embedding physical information into ML and reviews the developments of PIML in structural integrity including failure mechanism modelling and prognostic and health management (PHM). The exploration of the application of PIML to structural integrity demonstrates the potential of PIML for improving consistency with prior knowledge, extrapolation performance, prediction accuracy, interpretability and computational efficiency and reducing dependence on training data. The analysis and findings of this work outline the limitations at this stage and provide some potential research direction of PIML to develop advanced PIML for ensuring structural integrity of engineering systems/facilities.
This article is part of the theme issue 'Physics-informed machine learning and its structural integrity applications (Part 1)'.
“…Under internal and external disturbances of the system, there are motor torque fluctuations, quantitative pump pressure pulsation, and system leakage. In addition, coupled with complex failure mechanisms and other unknown factors, the system is easy to appear degradation and failures [ 10 ]. In order to prevent serious consequences caused by the degradation or failure of the system's health status, operators must timely acquire the operating status of mechanical equipment.…”
“…Elevated temperatures affect the performance of the hydraulic oil, which results in a vicious cycle of increased overheating with a significant loss of viscosity, thinning of the hydraulic oil, increased flow loss, and increased wear on the structure. In addition, high temperatures accelerate the oxidation of the fluid and deterioration of seals, shortening the life of the oil, degrading the performance of the system, and potentially even seriously affecting the healthy operation of the EHA [10], [11].…”
Electro-hydrostatic actuators (EHAs) are widely used due to their high integration and high power-to-weight ratio. However, the elimination of a centralized oil source in EHAs limits the cooling capacity of the system. Excessively high temperatures can have a significant impact on the performance and lifespan of the EHA. In this paper, firstly, the power loss during energy transfer and heat dissipation characteristics of EHAs are carefully examined. To further study the heat behavior, a one-dimensional simulation model of the EHA thermal-hydraulic system is developed. By comparing the simulation results with experimental data obtained from an actual EHA system, the good agreement between the simulation and experimental results confirms that the developed model can accurately simulate the thermal behavior of EHAs.Based on the validated model, the cooling scheme of EHAs is further explored. The cooling mechanisms of air cooling and phase change heat dissipation are considered to optimize heat dissipation and manage the temperature rise within the EHA. This research provides insights and guidance for the thermal design of EHAs in the early stages to ensure system performance and extend its lifetime.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.