Distributed Piezotransducers for Damage Detection

2000 ◽  
Author(s):  
Grzegorz Kawiecki
Keyword(s):  
Neural Networks ◽  
Low Frequency ◽  
Structural Components ◽  
Reasonable Accuracy ◽  
Strain Fields ◽  
Damage Location ◽  
Related Information ◽  
New Type ◽  
Form Model ◽  
Complex Strain

Abstract The purpose of this paper is to show the feasibility of applying neural networks and arrays of piezotransducers for condition monitoring of basic structural components. It is shown that simple neural networks can be used to interpret damage-related anomalies in signals transferred between elements of a piezotransducer array. These relatively low frequency signals in the 0 Hz–1 kHz range carry enough information to determine damage location and size with a reasonable accuracy. The feasibility of a neural network-based expert system for signal processing is shown using a simple closed-form model of a thin, homogeneous vibrating plate. A new type of a rosette piezotransducer is presented. This type of a piezotransducer can generate and sense complex strain fields containing more damage-related information.

scholarly journals Generalization of Patterns by Identification with Polynomial Neural Network

2010 ◽  
Vol 61 (2) ◽  
pp. 120-124 ◽  
Author(s):  
Ladislav Zjavka
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Functional Dependence ◽  
Polynomial Neural Network ◽  
New Type ◽  
Input Variables ◽  
The Brain ◽  
Functional Output ◽  
Simplified Form

Generalization of Patterns by Identification with Polynomial Neural Network Artificial neural networks (ANN) in general classify patterns according to their relationship, they are responding to related patterns with a similar output. Polynomial neural networks (PNN) are capable of organizing themselves in response to some features (relations) of the data. Polynomial neural network for dependence of variables identification (D-PNN) describes a functional dependence of input variables (not entire patterns). It approximates a hyper-surface of this function with multi-parametric particular polynomials forming its functional output as a generalization of input patterns. This new type of neural network is based on GMDH polynomial neural network and was designed by author. D-PNN operates in a way closer to the brain learning as the ANN does. The ANN is in principle a simplified form of the PNN, where the combinations of input variables are missing.

A periodic seismic isolation foundation with an extremely broad low-frequency attenuation zone: Theoretical analysis and experimental verification

2021 ◽  
pp. 136943322110646
Author(s):  
Peng Zhou ◽  
Shui Wan ◽  
Xiao Wang ◽  
Yingbo Zhu ◽  
Muyun Huang
Keyword(s):  
Seismic Isolation ◽  
Seismic Waves ◽  
Periodic Structures ◽  
Finite Size ◽  
Low Frequency ◽  
Bridge Structure ◽  
Engineering Structures ◽  
P Waves ◽  
New Type ◽  
Dominant Frequencies

The attenuation zones (AZs) of periodic structures can be used for seismic isolation design. To cover the dominant frequencies of more seismic waves, this paper proposes a new type of periodic isolation foundation (PIF) with an extremely wide low-frequency AZ of 3.31 Hz–17.01 Hz composed of optimized unit A with a wide AZ and optimized unit B with a low-frequency AZ. The two kinds of optimized units are obtained by topology optimization on the smallest periodic unit with the coupled finite element-genetic algorithm (GA) methodology. The transmission spectra of shear waves and P-waves through the proposed PIF of finite size are calculated, and the results show that the AZ of the PIF is approximately the superposition of the AZs of the two kinds of optimized units. Additionally, shake tests on a scale PIF specimen are performed to verify the attenuation performance for elastic waves within the designed AZs. Furthermore, numerical simulations show that the acceleration responses of the bridge structure with the proposed PIF are attenuated significantly compared to those with a concrete foundation under the action of different seismic waves. Therefore, the newly proposed PIF is a promising option for the reduction of seismic effects in engineering structures.

Mechanisms and Mitigation of 3D Coupled Vibrations in Drilling with PDC Bits

2021 ◽  
Author(s):  
Shilin Chen ◽  
Chris Propes ◽  
Curtis Lanning ◽  
Brad Dunbar
Keyword(s):  
Torsional Oscillation ◽  
Excitation Frequency ◽  
Low Frequency ◽  
Coupled Vibration ◽  
Stick Slip ◽  
Rock Interaction ◽  
Bottom Hole ◽  
New Type ◽  
Design Characteristics ◽  
Axial Resonance

Abstract In this paper we present a new type of vibration related to PDC bits in drilling and its mitigation: a vibration coupled in axial, lateral and torsional directions at a high common frequency (3D coupled vibration). The coupled frequency is as high as 400Hz. 3D coupled vibration is a new dysfunction in drilling operation. This type of vibration occurred more often than stick-slip vibration. Evidences reveal that the coupled frequency is an excitation frequency coming from the bottom hole pattern formed in bit/rock interaction. This excitation frequency and its higher order harmonics may excite axial resonance and/or torsional resonance of a BHA. The nature of 3D coupled vibration is more harmful than low frequency stick-slip vibration and high frequency torsional oscillation (HFTO). The correlation between the occurrence of 3D coupled vibration and bit design characteristics is studied. Being different from prior publications, we found the excitation frequency is dependent on bit design and the occurrence of 3D coupled vibration is correlated with bit design characteristics. New design guidlines have been proposed to reduce or to mitigate 3D coupled vibration.

scholarly journals Two-point observations of low-frequency waves at 67P/Churyumov-Gerasimenko during the descent of PHILAE: comparison of RPCMAG and ROMAP

2016 ◽  
Vol 34 (7) ◽  
pp. 609-622 ◽  
Author(s):  
Ingo Richter ◽  
Hans-Ulrich Auster ◽  
Gerhard Berghofer ◽  
Chris Carr ◽  
Emanuele Cupido ◽  
...  
Keyword(s):  
Low Frequency ◽  
Minimum Variance ◽  
Wave Source ◽  
Frequency Wave ◽  
Final Destination ◽  
Connection Line ◽  
New Type ◽  
Current Instability ◽  
Comet 67P ◽  
Low Frequency Waves

Abstract. The European Space Agency's spacecraft ROSETTA has reached its final destination, comet 67P/Churyumov-Gerasimenko. Whilst orbiting in the close vicinity of the nucleus the ROSETTA magnetometers detected a new type of low-frequency wave possibly generated by a cross-field current instability due to freshly ionized cometary water group particles. During separation, descent and landing of the lander PHILAE on comet 67P/Churyumov-Gerasimenko, we used the unique opportunity to perform combined measurements with the magnetometers onboard ROSETTA (RPCMAG) and its lander PHILAE (ROMAP). New details about the spatial distribution of wave properties along the connection line of the ROSETTA orbiter and the lander PHILAE are revealed. An estimation of the observed amplitude, phase and wavelength distribution will be presented as well as the measured dispersion relation, characterizing the new type of low-frequency waves. The propagation direction and polarization features will be discussed using the results of a minimum variance analysis. Thoughts about the size of the wave source will complete our study.

scholarly journals The Old and the New: Can Physics-Informed Deep-Learning Replace Traditional Linear Solvers?

2021 ◽  
Vol 4 ◽  
Author(s):  
Stefano Markidis
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
High Performance ◽  
Critical Role ◽  
Low Frequency ◽  
Accurate Solution ◽  
Limiting Factor ◽  
Data Set ◽  
Linear Solvers ◽  
Computational Performance

Physics-Informed Neural Networks (PINN) are neural networks encoding the problem governing equations, such as Partial Differential Equations (PDE), as a part of the neural network. PINNs have emerged as a new essential tool to solve various challenging problems, including computing linear systems arising from PDEs, a task for which several traditional methods exist. In this work, we focus first on evaluating the potential of PINNs as linear solvers in the case of the Poisson equation, an omnipresent equation in scientific computing. We characterize PINN linear solvers in terms of accuracy and performance under different network configurations (depth, activation functions, input data set distribution). We highlight the critical role of transfer learning. Our results show that low-frequency components of the solution converge quickly as an effect of the F-principle. In contrast, an accurate solution of the high frequencies requires an exceedingly long time. To address this limitation, we propose integrating PINNs into traditional linear solvers. We show that this integration leads to the development of new solvers whose performance is on par with other high-performance solvers, such as PETSc conjugate gradient linear solvers, in terms of performance and accuracy. Overall, while the accuracy and computational performance are still a limiting factor for the direct use of PINN linear solvers, hybrid strategies combining old traditional linear solver approaches with new emerging deep-learning techniques are among the most promising methods for developing a new class of linear solvers.

scholarly journals Early bearing fault diagnosis based on improved SFLA and ELM network

2018 ◽  
Vol 42 (2) ◽  
pp. 187-193 ◽  
Author(s):  
Jingwen Xu ◽  
Yunxuan Zhang ◽  
Ziqi Yin
Keyword(s):  
Neural Networks ◽  
Fault Diagnosis ◽  
Single Layer ◽  
Shuffled Frog Leaping Algorithm ◽  
Bearing Fault ◽  
Bearing Fault Diagnosis ◽  
Chaotic Mapping ◽  
New Type ◽  
Shuffled Frog Leaping ◽  
Learning Machine

In this paper, an extreme learning machine (ELM) network based on an improved shuffled frog leaping algorithm (CCSFLA) is applied in early bearing fault diagnosis. ELM is a new type of single layer forward network. Although the generalization is stronger compared with traditional neural networks, a random setup of initial parameters increases instability of the network. An improved SFLA based on sinusoidal chaotic mapping with infinite collapses and constriction factors (CCSFLA) is proposed in this paper to optimize the ELM and obtain a CCSFLA–ELM model. Results show that the CCSFLA–ELM model can be used for optimization and that it improved the recognition of early bearing fault diagnosis.

scholarly journals Vehicle classification from low-frequency GPS data with recurrent neural networks

2018 ◽  
Vol 91 ◽  
pp. 176-191 ◽  
Author(s):  
Matteo Simoncini ◽  
Leonardo Taccari ◽  
Francesco Sambo ◽  
Luca Bravi ◽  
Samuele Salti ◽  
...  
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Low Frequency ◽  
Vehicle Classification ◽  
Gps Data

scholarly journals C1-Almost Periodic Solutions of BAM Neural Networks with Time-Varying Delays on Time Scales

2015 ◽  
Vol 2015 ◽  
pp. 1-15 ◽  
Author(s):  
Yongkun Li ◽  
Lili Zhao ◽  
Li Yang
Keyword(s):  
Neural Networks ◽  
Periodic Solutions ◽  
Time Scales ◽  
Sufficient Conditions ◽  
Time Varying ◽  
Bam Neural Networks ◽  
Almost Periodic Solutions ◽  
Almost Periodic ◽  
New Type ◽  
Inequality Techniques

On a new type of almost periodic time scales, a class of BAM neural networks is considered. By employing a fixed point theorem and differential inequality techniques, some sufficient conditions ensuring the existence and global exponential stability ofC1-almost periodic solutions for this class of networks with time-varying delays are established. Two examples are given to show the effectiveness of the proposed method and results.

Sign in / Sign up

Export Citation Format

Share Document