Virtual sensing method for monitoring vibration of continuously variable configuration structures using long short-term memory networks

Yue, Zhenjiang; Liu, Li; Li, Teng; Ma, Yuanchen

doi:10.1016/j.cja.2019.09.013

Cited by 5 publications

(4 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 13a shows the variation in the surface hardness of the workpiece after ultrasonic-assisted processing at different ultrasonic power levels. The hardness increased with increasing ultrasonic power; however, the change in hardness was not significant when the power exceeded 100 W. Figure 13b shows the variation in the surface hardness of the workpiece after different processing times at an ultrasonic power of 100 W. With an increase in processing time, the surface hardness of the workpiece increased slightly, indicating that although electrochemical polishing could maintain the metallurgical properties of the workpiece surface intact, the impact of highspeed microjets and cavitation collapse shock waves on the surface hardness of the materials was affected by ultrasonic action [17]. High-energy cavitation collapse releases highspeed microjets and shock waves, causing gigapascal pressure and microplastic deformation of the material surface.…”

Section: The Change In Surface Hardness and Residual Stressmentioning

confidence: 99%

“…Research has shown that ultrasonic vibrations can accelerate the discharge of electrochemical products through cavitation and liquid-phase mass-transfer effects, thereby promoting electrochemical dissolution [12][13][14][15]. The micro/nano surface morphology of metals was modified through cavitation collapse, demonstrating the ability of cavitation to modify metal surfaces [16][17][18]. Li et al [19] found that the ultrasonic-assisted electrodeposition of nickel/diamond coatings exhibited be er corrosion resistance than coatings prepared under mechanical stirring conditions.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Material Removal and Surface Modification of Copper under Ultrasonic-Assisted Electrochemical Polishing

Zhang,

Wang,

Chen

et al. 2024

Processes

View full text Add to dashboard Cite

Electrochemical polishing exhibits high efficiency and simplicity of operation and presents broad prospects in metal field processing. However, the poor conductivity of the surface oxides generated during electrochemical polishing may lead to uneven electrolysis and surface protrusions if not promptly removed. This study combined ultrasonic treatment with electrochemical polishing and adjusted the angle of the ultrasonic jet to investigate the effect of ultrasonic-assisted electrochemical polishing on the removal of protruding microstructures. The study examined the surface morphology, hardness, residual stress, and workpiece contact angle before and after processing. The results demonstrated that ultrasonic assistance can effectively promote electrochemical reactions and improve the removal efficiency of the workpiece surface. With an increase in ultrasonic power and processing time, the corrosion potential of the workpiece decreased, which accelerated the material removal rate. The roughness of the workpiece surface increased within the threshold. Additionally, the surface hardness increased to 105.3 HV, the residual stress was enhanced by 517.89 MPa, and the contact angle increased to 104.7°. The erosion characteristics and hydrophobicity of the workpiece were also enhanced.

show abstract

Section: The Change In Surface Hardness and Residual Stressmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Material Removal and Surface Modification of Copper under Ultrasonic-Assisted Electrochemical Polishing

Zhang,

Wang,

Chen

et al. 2024

Processes

View full text Add to dashboard Cite

show abstract

“…The experiment structure is a liquid-filled pipe suspended on a bracket by four polyester ropes (Figure 20). 47 It is made of stainless steel with length of 2.4 m, diameter of 0.1 m, and thickness of 1 mm. The structural modal parameters change continuously with the release of the liquid in the pipe.…”

Section: Description Of the Experiments Systemmentioning

confidence: 99%

A single‐mode recursive validation method for modal identification of linear time‐varying structures based on prior knowledge

Yue

Liu

2021

Struct Control Health Monit

Self Cite

View full text Add to dashboard Cite

Discerning the spurious modes for time-invariant or extremely slow timevarying structures with time-consuming tools (stabilization diagram and clustering), which is the main task of the automated modal identification, has been developed in last years. However, there is still a challenge the recursive identification of the linear time-varying structures. This study presents a single-mode recursive validation method for the recursive identification of the linear timevarying structures. Since one major issue is that the properties of the physical modes are time-varying, the proposed method extracts the information about the current state of the time-varying structures from the nonstationary vibration responses via deep learning method for the separation between physical and spurious modes. For the sake of effective elimination to spurious modes and control of computation efforts, the proposed method utilizes the application-dependent prior knowledge rather than iterations or highdimensional optimizations, with robustness to hyperparameters. It can be combined with any parametric system identification method. A time-varying stiffness numerical example and a time-varying mass distribution experimental example illustrate the performance of the proposed modal validation method under various time-varying processes.

show abstract

“…In chemical process monitoring, Long Short-Term Memory (LSTM) networks were applied in [8,9], while [10] compares recurrent neural networks and LSTM networks and features an approach for transfer learning. Regarding VS in structural mechanics, Rouss et al [11] employs a non-linear autoregressive exogenous model (NARX) for response estimation in a non-linear dynamic system while [12] applies LSTM networks to model linear time varying systems. The aim of this paper is to provide a black box virtual sensing framework based on LSTM networks which is suitable for multiaxial fatigue applications in non-linear mechanical systems.…”

Section: Introductionmentioning

confidence: 99%

A hybrid virtual sensing approach for approximating non-linear dynamic system behavior using LSTM networks

Heindel¹,

Hantschke²,

Kästner³

2021

Preprint

View full text Add to dashboard Cite

Modern Internet of Things solutions are used in a variety of different areas, ranging from connected vehicles and healthcare to industrial applications. They rely on a large amount of interconnected sensors, which can lead to both technical and economical challenges. Virtual sensing techniques aim to reduce the number of physical sensors in a system by using data from available measurements to estimate additional unknown quantities of interest. Successful model-based solutions include Kalman filters or the combination of finite element models and modal analysis, while many data-driven methods rely on machine learning algorithms. The presented hybrid virtual sensing approach combines Long Short-Term Memory networks with frequency response function models in order to estimate the behavior of non-linear dynamic systems with multiple input and output channels. Network training and prediction make use of short signal subsequences, which are later recombined by applying a windowing technique. The frequency response function model acts as a baseline estimate which perfectly captures linear dynamic systems and is augmented by the non-linear Long Short-Term Memory network following two different hybrid modeling strategies. The approach is tested using a non-linear experimental dataset, which results from measurements of a threecomponent servo-hydraulic fatigue test bench. A variety of metrics in time and frequency domains, as well as fatigue strength under variable amplitudes are used to evaluate the approximation quality of the proposed method. In addition to virtual sensing, the algorithm is also applied to a forward prediction task. Synthetic data are used in a separate study to estimate the prediction quality on datasets of different size.

show abstract

Virtual sensing method for monitoring vibration of continuously variable configuration structures using long short-term memory networks

Cited by 5 publications

References 32 publications

Material Removal and Surface Modification of Copper under Ultrasonic-Assisted Electrochemical Polishing

Material Removal and Surface Modification of Copper under Ultrasonic-Assisted Electrochemical Polishing

A single‐mode recursive validation method for modal identification of linear time‐varying structures based on prior knowledge

A hybrid virtual sensing approach for approximating non-linear dynamic system behavior using LSTM networks

Contact Info

Product

Resources

About