Frequency response function based damage identification using principal component analysis and pattern recognition technique

2014 ◽  
Vol 66 ◽  
pp. 116-128 ◽  
Author(s):  
Rupika P. Bandara ◽  
Tommy H.T. Chan ◽  
David P. Thambiratnam
Keyword(s):  
Principal Component Analysis ◽  
Pattern Recognition ◽  
Frequency Response ◽  
Response Function ◽  
Frequency Response Function ◽  
Damage Identification ◽  
Principal Component ◽  
Component Analysis ◽  
Pattern Recognition Technique ◽  
Recognition Technique

scholarly journals A Novel Method for Fault Diagnosis of the Two-Input Two-Output Nonlinear Mass-Spring-Damper System Based on NOFRF and MBPCA

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Jialiang Zhang ◽  
Jie Wu ◽  
Xiaoqian Zhang
Keyword(s):  
Principal Component Analysis ◽  
Fault Diagnosis ◽  
Nonlinear System ◽  
Frequency Response ◽  
Response Function ◽  
Frequency Response Function ◽  
Principal Component ◽  
Component Analysis ◽  
Novel Method ◽  
Mass Spring

For fault diagnosis of the two-input two-output mass-spring-damper system, a novel method based on the nonlinear output frequency response function (NOFRF) and multiblock principal component analysis (MBPCA) is proposed. The NOFRF is the extension of the frequency response function of the linear system to the nonlinear system, which can reflect the inherent characteristics of the nonlinear system. Therefore, the NOFRF is used to obtain the original fault feature data. In order to reduce the amount of feature data, a multiblock principal component analysis method is used for fault feature extraction. The least squares support vector machine (LSSVM) is used to construct a multifault classifier. A simplified LSSVM model is adopted to improve the training speed, and the conjugate gradient algorithm is used to reduce the required storage of LSSVM training. A fault diagnosis simulation experiment of a two-input two-output mass-spring-damper system is carried out. The results show that the proposed method has good diagnosis performance, and the training speed of the simplified LSSVM model is significantly higher than the traditional LSSVM.

scholarly journals Uncertainties Consideration in Empirical Frequency Response Function Data for Damage Identification Based On Artificial Neural Network

2021 ◽  
Vol 13 (3) ◽  
Author(s):  
Khairul H. Padil ◽  
◽  
Norhisham Bakhary ◽  
Wan Nur Firdaus Wan Hassan ◽  
Nadirah Darus ◽  
...  
Keyword(s):  
Frequency Response ◽  
Response Function ◽  
Structural Damage ◽  
Frequency Response Function ◽  
Damage Identification ◽  
Principal Component ◽  
Steel Truss Bridge ◽  
Artificial Neural ◽  
Actual Damage ◽  
Truss Bridge

The modern application of frequency response function (FRF) with artificial neural networks (ANN) has become one of the leading methods in vibration-based damage detection approach. However, since full-size empirically obtained FRF data is used as ANN input, a broad composition ANN input layer series would occur. Consequently, principal component analysis (PCA) is adopted to compress the FRF data magnitude. Despite this, PCA alone is unable to select the important FRF data features effectively, due to the exceedingly FRF data size in addition with existing uncertainties. Therefore, this study proposed the merger of a non-probabilistic analysis and ANN approach with PCA by considering the uncertainties effect and the inefficiency of using empirical FRF data. The empirical FRF data is obtained from a steel truss bridge structure. The results show that the PoDE values above 95% are measured at the particular executed damage locations and the DMI values show the damage severity at the actual damage locations. Overall, the results show that the proposed method is capable in considering the uncertainties effect on the empirical FRF data for structural damage identification.

Stratophenetic tracing of phylogeny using SIMCA pattern recognition technique: a case study of the late Neogene planktic foraminiferaGloboconellaclade

Paleobiology ◽  
1994 ◽  
Vol 20 (1) ◽  
pp. 52-65 ◽  
Author(s):  
Kuo-Yen Wei
Keyword(s):  
Pattern Recognition ◽  
Morphological Variability ◽  
Principal Component ◽  
Pattern Recognition Technique ◽  
Evolutionary Patterns ◽  
Continuous Increase ◽  
Late Neogene ◽  
History Of ◽  
Classification Procedures ◽  
Recognition Technique

The Plio-Pleistocene planktic foraminiferal sequence of theGloborotalia(Globoconella)puncticulata-inflataclade in Deep Sea Drilling Project Site 588, dated at 4.36 Ma to 0.05 Ma, records the branching history of theG. inflatalineage from the ancestralG. puncticulatalineage. The gradational nature of the divergence and the enormous morphological variability inherent in theG. inflatalineage have elicited different views on taxonomy and phylogeny of this clade. A pattern recognition technique, soft independent modeling of class analog (SIMCA), was used as an objective quantitative stratophenetic methodology to reconstruct the phylogenetic history.Typical specimens of two species,G. puncticulataandG. inflata,were identified from a stratigraphic level dated at 2.76 Ma. Principal component models were built to characterize the morphometric patterns of the two morphotypes using SIMCA. TheGloboconellaspecimens of the next lower and higher adjacent stratigraphic levels were evaluated against the models and classified into one of the two morphotypes. The newly classified specimens were then used to build new models for further tracing of lineages in lower and upper sections, respectively. Progression of such training and classification procedures through stratigraphic intervals resulted in a reconstruction of the evolutionary patterns of the two lineages. Cladogenesis gave rise to the descendant lineage,G. inflata,at about 3.5 Ma. The two co-existing species,G. inflataandG. puncticulata,differ only in size and show similarity in most characters at the beginning of their divergence. Other characters began to diverge later, at various rates. The gradients between planktic and benthic foraminiferal δ18O values show a continuous increase during the late Pliocene. The succession fromG. puncticulatatoG. inflataduring the same time correlates with the progressively increased vertical stratification in temperature of surface waters.Globorotalia puncticulatabecame extinct at 2.35 Ma when the temperature gradient further increased, corresponding to the onset of extensive glaciation in the Northern Hemisphere.

Pattern Recognition on X-ray Fluorescence Records from Copenhagen Lake Sediments Using Principal Component Analysis

2014 ◽  
Vol 225 (12) ◽  
Author(s):  
Norman Schreiber ◽  
Emanuel Garcia ◽  
Aart Kroon ◽  
Peter C. Ilsøe ◽  
Kurt H. Kjær ◽  
...  
Keyword(s):  
Principal Component Analysis ◽  
Pattern Recognition ◽  
Lake Sediments ◽  
Principal Component ◽  
Component Analysis ◽  
X Ray
Sign in / Sign up

Export Citation Format

Share Document