Use of neural networks in detection of structural damage

“…After a pattern recognition algorithm has been trained, it can then be tested (preferably with data not used to train the algorithm) with input data to determine how accurate the trained algorithm is at properly characterizing the healthy or damaged state of the system. Pattern recognition techniques have been used to detect damage on a wide variety of structures, including stiffened plates [128], buildings [129][130][131], cantilever beams [132], bridges [133], trusses [134][135][136], spring-mass systems [137,138].…”

Section: Pattern Recognitionmentioning

confidence: 99%

Design and Analysis of Advanced Materials in a Thermal/Acoustic Environment. Delivery Order 0007: Volume 1 - Structural Health Monitoring

Grandhi¹,

Tobe²

2010

View full text Add to dashboard Cite

The public reporting burden for this collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching existing data sources, gathering and maintaining the data needed, and completing and reviewing the collection of information. Send comments regarding this burden estimate or any other aspect of this collection of information, including suggestions for reducing this burden, to Department of Defense, Washington Headquarters Services, Directorate for Information , 1215 Jefferson Davis Highway, Suite 1204, Arlington, VA 22202-4302. Respondents should be aware that notwithstanding any other provision of law, no person shall be subject to any penalty for failing to comply with a collection of information if it does not display a currently valid OMB control number. PLEASE DO NOT RETURN YOUR FORM TO THE ABOVE ADDRESS. REPORT DATE (DD-MM-YY) REPORT TYPE 3. DATES COVERED (From -To)March 2010 0A PERFORMING ORGANIZATION NAME(S) AND ADDRESS(ES) 8. PERFORMING ORGANIZATION REPORT NUMBERWright State University Department of Mechanical and Materials Engineering Dayton, OH 45435 SPONSORING/MONITORING AGENCY NAME(S) AND ADDRESS(ES)Air Force Research Laboratory SPONSORING/MONITORING AGENCY ACRONYM(S)Air ABSTRACTAir vehicles flying at hypersonic speeds encounter extreme thermal, aerodynamic and acoustic loads, utilizing thermal protection systems to shield the main structure from these 1oads.One type of failure in a mechanically attached thermal protection system is fastener failure. Determining structural health monitoring on the fastener health of the thermal protection system is needed and can be completed by analyzing changes in the dynamic characteristics of the system due to fastener failure. The damage detection metrics include the existing modal parameters-modal assurance criterion (MAC), partial (PMAC), and coordinate (CMAC)-as well as two new modal parameters-normalized coordinate MAC and normalized coordinate MAC X summation were investigated. Two new modal parameters were formulated to identify mode shape changes in a structure due to global damage to the structure. Two damage states caused a minimal change to the low-frequency structural dynamics and could not be localized with any of the investigated damage metrics. After the finite element model is validated for the healthy state with free-free boundary conditions, the global boundary conditions and fastener failure damage states are implemented. This damage simulation allows a better understanding of how the damage states cause low-frequency dynamic changes without requiring a experimental data for each of the damage states of interest. SUBJECT TERMSThe damage detection metrics include the existing modal parameters-modal assurance criterion, partial modal assurance criterion, and coordinate modal assurance criterion-as well as two new modal parameters-normalized coordinate modal assurance criterion and normalized coordinate modal assurance criterion summation. The existing modal parameters provide data...

show abstract

“…And with the fast development of computation, more attention was paid in algorithm these years. Neural network was among the first to be adopted to identified damage [9,10], and therefore others heuristic algorithm such as genetic algorithm (GA) [11], particle swarm optimization (PSO) [12] and artificial bee colony (ABC) [13] are proved to the available in damage identification.…”

Section: Introductionmentioning

confidence: 99%

A two-step approach for damage detection in beam based on influence line and bird mating optimizer

Tan¹,

Lu²

2017

Vib. proced.

View full text Add to dashboard Cite

Abstract. This paper presents a two-step approach for structural damage identification in beam structure using the influence line and bird mating optimizer (BMO). Local damage is simulated as the reduction of the elemental Young's modulus and mass of beam element. The technique for damage localization based on influence line and its derivatives before and after damage for beam structure was outlined. An objective function comprised of dynamic acceleration is utilized for BMO algorithm. The dynamic response data under external force is calculated by Newmark integration method. Numerical examples of a simply supported beam was investigated. Effect of measurement noise is studied. Studies in the paper indicate that the proposed method is efficient and robust for identifying damages in beam structures.

show abstract

Use of neural networks in detection of structural damage

Cited by 460 publications

References 5 publications

Detection of Transverse Cracks in a Composite Beam Using Combined Features of Lamb Wave and Vibration Techniques in Ann Environment

Detection of Transverse Cracks in a Composite Beam Using Combined Features of Lamb Wave and Vibration Techniques in Ann Environment

Design and Analysis of Advanced Materials in a Thermal/Acoustic Environment. Delivery Order 0007: Volume 1 - Structural Health Monitoring

A two-step approach for damage detection in beam based on influence line and bird mating optimizer

Contact Info

Product

Resources

About