Hydrodynamic object identification with artificial neural models

@article{Lakkam2019HydrodynamicOI,
  title={Hydrodynamic object identification with artificial neural models},
  author={Sreetej Lakkam and B. T. Balamurali and Roland Bouffanais},
  journal={Scientific Reports},
  year={2019},
  volume={9}
}
The lateral-line system that has evolved in many aquatic animals enables them to navigate murky fluid environments, locate and discriminate obstacles. Here, we present a data-driven model that uses artificial neural networks to process flow data originating from a stationary sensor array located away from an obstacle placed in a potential flow. The ability of neural networks to estimate complex underlying relationships between parameters, in the absence of any explicit mathematical description… 

Deep learning model inspired by lateral line system for underwater object detection

A deep learning-based object localization model that can detect the location of objects using flow information measured from a moving sensor array is developed that achieves impressive accuracy in predicting the locations of the hydrofoil and objects with only 40$\% of the sensors used in the original model.

Shape Classification Using Hydrodynamic Detection via a Sparse Large-Scale 2D-Sensitive Artificial Lateral Line

This work presents measurements using a large-scale artificial lateral line of 3.5 meters, consisting of eight all-optical 2D-sensitive flow sensors, and finds that, compared to the traditional sensing dimension parallel to the sensor array, the novel transverse fluid velocity component bears more information about the object shape.

An Artificial Lateral Line Sensor Using Polyvinylidene Fluoride (PVDF) Membrane for Oscillatory Flow Sensing

Flow sensing is an essential technology used in marine science. Fish live in fluid environments. Therefore, it is not surprising that fish have developed abilities to sense flow. We designed an

Enhancing Performance of Reservoir Computing System Based on Coupled MEMS Resonators

A novel RC structure based on the coupled MEMS resonators with the enhanced dynamic richness to optimize the performance of the RC system both on the system level and data set level is proposed.

References

SHOWING 1-10 OF 40 REFERENCES

Lateral-line inspired sensor arrays for navigation and object identification

Found to affect numerous aspects of behavior, including maneuvering in complex fluid environments with poor visibility, the lateral line is a critical component of fish sensory systems. This sensory

Recognition of an obstacle in a flow using artificial neural networks.

Although the ANN showed problems with the classification of very small obstacles, the general results show a very good capacity for prediction.

A fish perspective: detecting flow features while moving using an artificial lateral line in steady and unsteady flow

Results highlight that moving in the flow is advantageous to characterize the flow environment when compared with static analysis and provide a useful measure of transition from steady to unsteady flow.

Information Processing by the Lateral Line System

This review covers four areas of research that have fruitfully contributed to the understanding of lateral line function within the past 10 years and the recently documented roles of the lateral line system in natural behaviors, including courtship and prey capture.

A Machine Learning Strategy to Assist Turbulence Model Development

This work investigates the feasibility of a new data-driven approach to turbulence model development by attempting to reproduce, through a machine learning methodology, the results obtained with the well-established Spalart-Allmaras model.

Machine Learning Methods for Data-Driven Turbulence Modeling

This paper investigates machine learning models in their capability to reconstruct the functional forms of spatially distributed quantities extracted from high fidelity simulation and experimental data and highlights the potential of machine learning as an enabling tool in data-driven turbulence modeling.

Deep learning in fluid dynamics

  • J. Kutz
  • Computer Science
    Journal of Fluid Mechanics
  • 2017
Although neural networks have been applied previously to complex fluid flows, the article featured here is the first to apply a true DNN architecture, specifically to Reynolds averaged Navier Stokes turbulence models, suggesting that DNNs may play a critically enabling role in the future of modelling complex flows.

Development and testing of bio-inspired microelectromechanical pressure sensor arrays for increased situational awareness for marine vehicles

The lateral line found on most species of fish is a sensory organ without analog in humans. Using sensory feedback from the lateral line, fish are able to track prey, school, avoid obstacles, and

Touch at a distance sensing: lateral-line inspired MEMS flow sensors

Experimental results demonstrate that the biological canal inspired polymer encapsulation on the array of artificial superficial neuromast sensors is capable of filtering steady-state flows that could otherwise significantly mask the relevant oscillatory flow signals of high importance.

Application of supervised learning to quantify uncertainties in turbulence and combustion modeling

The accuracy of low-fidelity models of turbulent flow such as those based on the Reynolds Averaged Navier–Stokes (RANS) equations can be questionable, especially when these models are applied in