Neural Networks Based Diagnostics for Mistuned Bladed Disk

2000 ◽  
Author(s):  
Pei-Yuan Peng ◽  
M. T. Yang
Keyword(s):  
Complex System ◽  
Neural Networks ◽  
Finite Element ◽  
Vibration Frequency ◽  
Element Model ◽  
Disk System ◽  
Bladed Disk ◽  
The Neural Networks ◽  
Blade Frequency ◽  
Diagnostics System

Neural networks based diagnostics is studied in this paper for the fault/alert assessment of the mistuned bladed disk. By randomly varying the blades frequencies (± 2% of the nominal frequencies), we experimentally collected 1000 sets of data. Each set of data is composed of blade frequencies, maximal vibrating magnitude for each blade with the corresponding frequency. The goal is to investigate the mapping relationship from the blade property (blade frequency) to maximal vibrating displacement and the corresponding frequency. Assuming the system is forced by a traveling excitation, the vibration/frequency signature is derived. The challenging part stems from mistuned bladed disk system, where every blade performs differently for the same input excitement. The neural networks based diagnostics system demonstrate its capability to identify the mapping relation for this complex system. The simulation is based on a finite element model of bladed disk system and the results exhibit the effectiveness of the proposed algorithm.

scholarly journals Dynamic characteristics of mistuned bladed disk system under rub-impact force

2020 ◽  
Vol 12 (11) ◽  
pp. 168781402097306
Author(s):  
Hui Zhang ◽  
Tianyu Zhao ◽  
Hongyuan Zhang ◽  
Honggang Pan ◽  
Huiqun Yuan
Keyword(s):  
Finite Element ◽  
Variable Thickness ◽  
Impact Force ◽  
Element Model ◽  
Force Model ◽  
Disk System ◽  
Element Analysis ◽  
Bladed Disk ◽  
Blade Tip ◽  
The Impact

In order to study the rubbing of the mistuned bladed disk system with variable thickness blades, an elastically supported shaft-variable thickness blades coupled finite element model is established in this paper. A new rubbing force model is proposed considering the variable thickness section characteristics and rotation effect of the variable thickness blade. A method of mistuned parameter identification is introduced which consists of static frequency testing of blades, dichotomy, and finite element analysis. Based on the finite element method, the mistuned bladed disk system is made dynamic analysis in full rubbing by applying the judgment load method. The dynamic response of the mistuned bladed disk system is discussed under different conditions. The results show that increasing the amount of mistuning will increase the system vibration. At high speeds, the impact force will be partially offset by centrifugal force. And the rubbing gap affects the form of rubbing. With the gap decreases, the system will change from intermittent rubbing to continuous rubbing. In addition, when the system is rubbed, due to energy dissipation and blade damping, the stress is transferred from the blade tip to the blade root and attenuated. In general, rubbing is a random complex nonlinear vibration process.

scholarly journals An Implementation of Patient-Specific Biventricular Mechanics Simulations With a Deep Learning and Computational Pipeline

2021 ◽  
Vol 12 ◽  
Author(s):  
Renee Miller ◽  
Eric Kerfoot ◽  
Charlène Mauger ◽  
Tevfik F. Ismail ◽  
Alistair A. Young ◽  
...  
Keyword(s):  
Neural Networks ◽  
Finite Element ◽  
Element Model ◽  
Machine Learning Techniques ◽  
Patient Specific ◽  
Tissue Stiffness ◽  
Learning Techniques ◽  
Valve Motion ◽  
Multiple Neural Networks ◽  
The Neural Networks

Parameterised patient-specific models of the heart enable quantitative analysis of cardiac function as well as estimation of regional stress and intrinsic tissue stiffness. However, the development of personalised models and subsequent simulations have often required lengthy manual setup, from image labelling through to generating the finite element model and assigning boundary conditions. Recently, rapid patient-specific finite element modelling has been made possible through the use of machine learning techniques. In this paper, utilising multiple neural networks for image labelling and detection of valve landmarks, together with streamlined data integration, a pipeline for generating patient-specific biventricular models is applied to clinically-acquired data from a diverse cohort of individuals, including hypertrophic and dilated cardiomyopathy patients and healthy volunteers. Valve motion from tracked landmarks as well as cavity volumes measured from labelled images are used to drive realistic motion and estimate passive tissue stiffness values. The neural networks are shown to accurately label cardiac regions and features for these diverse morphologies. Furthermore, differences in global intrinsic parameters, such as tissue anisotropy and normalised active tension, between groups illustrate respective underlying changes in tissue composition and/or structure as a result of pathology. This study shows the successful application of a generic pipeline for biventricular modelling, incorporating artificial intelligence solutions, within a diverse cohort.

A Reduced Order Approach for the Vibration of Mistuned Bladed Disk Assemblies

1997 ◽  
Vol 119 (1) ◽  
pp. 161-167 ◽  
Author(s):  
M.-T. Yang ◽  
J. H. Griffin
Keyword(s):  
Finite Element ◽  
Finite Element Model ◽  
Degrees Of Freedom ◽  
Element Model ◽  
Reduced Order Model ◽  
Order Model ◽  
Disk System ◽  
Element Analysis ◽  
Reduced Order ◽  
Bladed Disk

A reduced order approach is introduced in this paper that can be used to predict the steady-state response of mistuned bladed disks. This approach takes results directly from a finite element analysis of a tuned system and, based on the assumption of rigid blade base motion, constructs a computationally efficient mistuned model with a reduced number of degrees of freedom. Based on a comparison of results predicted by different approaches, it is concluded that: The reduced order model displays structural fidelity comparable to that of a finite element model of the entire bladed disk system with significantly improved computational efficiency; and under certain circumstances both the finite element model and the reduced order model predict quite different response from simple spring-mass models.

scholarly journals A Reduced Order Approach for the Vibration of Mistuned Bladed Disk Assemblies

1995 ◽  
Author(s):  
M.-T. Yang ◽  
J. H. Griffin
Keyword(s):  
Finite Element ◽  
Finite Element Model ◽  
Degrees Of Freedom ◽  
Element Model ◽  
Reduced Order Model ◽  
Order Model ◽  
Disk System ◽  
Element Analysis ◽  
Reduced Order ◽  
Bladed Disk

A reduced order approach is introduced in this paper that can be used to predict the steady-state response of mistuned bladed disks. This approach takes results directly from a finite element analysis of a tuned system and, based on the assumption of rigid blade base motion, constructs a computationally efficient mistuned model with a reduced number of degrees of freedom. Based on a comparison of results predicted by different approaches it is concluded that: the reduced order model displays structural fidelity comparable to that of a finite element model of the entire bladed disk system with significantly improved computational efficiency; and under certain circumstances both the finite element model and the reduced order model predict quite different response from simple spring-mass models.

Design of Static Test Model for Three-Tower Cable-Stayed Self-Anchored Suspension Composed Bridge

2011 ◽  
Vol 243-249 ◽  
pp. 1528-1535
Author(s):  
Yu Zhao ◽  
Yong Jun Zhou ◽  
Jing Sun ◽  
Jin Tao Tang ◽  
Xu Li
Keyword(s):  
Complex System ◽  
Finite Element ◽  
Element Model ◽  
Test Model ◽  
Test Results ◽  
Static Test ◽  
Whole Process ◽  
Aesthetic Appearance ◽  
Load Carrying ◽  
Novel Structures

Cable-stayed self-anchored suspension composed bridges have novel structures and aesthetic appearance with complex system and difficulty for design and construction. In order to acquire a better knowledge of the load-carrying capability of this type of bridges, based on a real bridge and the theory of abnormal similarity, a full-bridge scaled down(1:20) test model was built to simulate the whole process of construction. The test results were preferably fit the theoretical calculation value. It can be seen that the design of the bridge was reasonable, and the accuracy of the calculation of finite element model was verified at the same time. The test and the related results can be used as the reference for the test and design of the similar bridges.

Finite Element Formulation and Vibration Frequency Analysis of a Fluid Filled Pipe

2005 ◽  
Author(s):  
Yi Jia ◽  
Reinaldo E. Madeira ◽  
Frederick Just-Agosto
Keyword(s):  
Finite Element ◽  
Coriolis Force ◽  
Frequency Analysis ◽  
Cross Sections ◽  
Vibration Frequency ◽  
Dynamic Performance ◽  
Element Model ◽  
Piping System ◽  
Element Formulation ◽  
Variable Cross

This paper presents the formulation of a finite element model and vibration frequency analysis of a fluid filled pipe having variable cross sections. The finite element method with consideration of Coriolis force developed in [1] was adopted for frequency analysis of a pipe in this study. The stiffness matrix, the c-matrix (Coriolis force) and mass (for dynamic analysis) matrix that contain all parameters of the fluids properties and flow conditions have been developed. The numerical model was employed to simulate the dynamic performance of the piping system with the specific configurations for an application. A critical relationship between the natural frequencies and pipe geometry has been established. The results of frequencies analysis of the piping system gave us an insight whether a resonance frequency might occur.

Damage quantification in foam core sandwich composites via finite element model updating and artificial neural networks

2020 ◽  
Vol 234 (21) ◽  
pp. 4288-4304
Author(s):  
Ali Mardanshahi ◽  
Masoud Mardanshahi ◽  
Ahmad Izadi
Keyword(s):  
Neural Networks ◽  
Finite Element ◽  
Artificial Neural Networks ◽  
Finite Element Model ◽  
Model Updating ◽  
Sandwich Structures ◽  
Element Model ◽  
Foam Core ◽  
Damage Quantification ◽  
Artificial Neural

The main idea of this paper is to propose a nondestructive evaluation (NDE) system for two types of damages, core cracking and skin/core debonding, in fiberglass/foam core sandwich structures based on the inverse eigensensitivity-based finite element model updating using the modal test results, and the artificial neural networks. First, the modal testing was conducted on the fabricated fiberglass/foam core sandwich specimens, in the intact and damaged states, and the natural frequencies were extracted. Finite element modeling and inverse eigensensitivity-based model updating of the intact and damaged sandwich structures were conducted and the parameters of the models were identified. Afterward, the updated finite element models were employed to generate a large dataset of the first five harmonic frequencies of the damaged sandwich structures with different damage sizes and locations. This dataset was adopted to train the machine learning models for detection, localization, and size estimation of the core cracking and skin/core debonding damages. A multilayer perceptron neural network classification model was used for detection of types of damages and also a multilayer perceptron neural network regression model was fitted to the dataset for automatically estimation of the locations and dimensions of damages. This intelligent system of damage quantification was also used to make predictions on real damaged specimens not seen by the system. The results indicated that the extracted natural frequencies from the accurate finite element model, in coordination with the experimental data, and using the artificial neural networks can provide an effective system for nondestructive evaluation of foam core sandwich structures.

Sign in / Sign up

Export Citation Format

Share Document