Structural Health Monitoring using deep learning with optimal finite element model generated data

2020 ◽  
Vol 145 ◽  
pp. 106972 ◽  
Author(s):  
Panagiotis Seventekidis ◽  
Dimitrios Giagopoulos ◽  
Alexandros Arailopoulos ◽  
Olga Markogiannaki
Keyword(s):  
Finite Element ◽  
Deep Learning ◽  
Structural Health Monitoring ◽  
Finite Element Model ◽  
Health Monitoring ◽  
Element Model ◽  
Structural Health

An inverse elastic method of crack identification based on sparse strain sensing sheet

2020 ◽  
pp. 147592172093951 ◽  
Author(s):  
Zeyu Xiong ◽  
Branko Glisic
Keyword(s):  
Finite Element ◽  
Structural Health Monitoring ◽  
Finite Element Model ◽  
Health Monitoring ◽  
Phase Field ◽  
Direct Contact ◽  
Crack Detection ◽  
Element Model ◽  
Crack Identification ◽  
Structural Health

Reliable damage detection over large areas of structures can be achieved by spatially quasi-continuous structural health monitoring enabled by two-dimensional sensing sheets. They contain dense arrays of short-gauge sensors, which increases the probability to have sensors in direct contact with damage (e.g. crack opening) and thus identify (i.e. detect, localize, and quantify) it at an early stage. This approach in damage identification is called direct sensing. Although the sensing sheet is a reliable and low-cost technology, the overall structural health monitoring system that is using it might become complex due to large number of sensors. Hence, intentional reduction in number of sensors might be desirable. In addition, malfunction of sensors can occur in real-life settings, which results in unintentional reduction in the number of functioning sensors. In both cases, reduction in the number of (functioning) sensors may lead to lack of performance of sensing sheet. Therefore, it is important to explore the performance of sparse arrays of sensors, in the cases where sensors are not necessarily in direct contact with damage (indirect sensing). The aim of this research is to create a method for optimizing the design of arrays of sensors, that is, to find the smallest number of sensors while maintaining a satisfactory reliability of crack detection and accuracy of damage localization and quantification. To achieve that goal, we first built a phase field finite element model of cracked structure verified by the analytical model to determine the crack existence (detection), and then we used the algorithm of inverse elastostatic problem combined with phase field finite element model to determine the crack length (quantification) and location (localization) by minimizing the difference between the sensor measurements and the phase field finite element model results. In addition, we experimentally validated the method by means of a reduced-scale laboratory test and assessed the accuracy and reliability of indirect sensing.

Permanently installed corrosion monitoring using magnetic measurement of current deflection

2017 ◽  
Vol 17 (2) ◽  
pp. 227-239 ◽  
Author(s):  
Rollo Jarvis ◽  
Peter Cawley ◽  
Peter B Nagy
Keyword(s):  
Magnetic Field ◽  
Finite Element ◽  
Structural Health Monitoring ◽  
Finite Element Model ◽  
Health Monitoring ◽  
Element Model ◽  
Probability Of Detection ◽  
Structural Health ◽  
Defect Growth ◽  
The Magnetic Field

The detection of corrosion on insulated and/or coated pipes remains a challenge. A non-destructive evaluation method has been proposed where a low-frequency AC current is directly injected into the pipe at distant locations, and perturbations in the magnetic field induced by current deflection around defects are measured. Structural health monitoring is made possible by detecting changes in the magnetic field due to defect growth using a permanently installed array of sensitive and inexpensive magnetic sensors. The performance of current deflection structural health monitoring is evaluated using a flexible and efficient framework. Individual sensor performance was first predicted using receiver operating characteristics obtained by evaluating the stability of the magnetic field signal measured outside of a section of coated undamaged riser pipe in an environmental chamber over repeated temperature cycles. A finite element model was then used to predict the magnetic perturbation due to defect growth which allowed the potential array configurations for structural health monitoring to be explored. Results suggest that 90% probability of detection and 0.1% probability of false alarm for [Formula: see text] (wall thickness) diameter, 30% of T depth defects are possible outside of 25- to 50-mm-thick pipe coatings/insulation using 10–50 sensors per metre of pipe and 5–10 A of injected current. The structural health monitoring procedure was then demonstrated experimentally, an electrochemically grown defect being successfully monitored; this experiment also served to validate the three-dimensional finite element model. A very good agreement between the predicted and measured changes in the magnetic field due to the current deflection around the growing defect was obtained.

Continuing Structural Health Monitoring after Repair: Starting from Scratch?

2008 ◽  
Vol 56 ◽  
pp. 495-501
Author(s):  
Jyrki Kullaa
Keyword(s):  
Finite Element ◽  
Numerical Model ◽  
Structural Health Monitoring ◽  
Finite Element Model ◽  
Health Monitoring ◽  
Measurement Data ◽  
Element Model ◽  
Structural Condition ◽  
Structural Health ◽  
Before And After

Aging structures need repairing if their lifetime is to be extended. If the structure has been monitored before and after repair, the information from both configurations can be utilized. The data before repair include the environmental or operational influences, whereas the data after repair represent the current structural condition. Also, if damage is proportional to the worked modifications, its extent can be assessed solely from the measurement data; no finite element model is needed. The proposed method is verified with a numerical model of a vehicle crane.

Sign in / Sign up

Export Citation Format

Share Document