Rotorcraft virtual sensors via deep regression

Martinez, Daniel; Brewer, Wesley; Strelzoff, Andrew; Wilson, Andrew Gordon; Wade, Daniel

doi:10.1016/j.jpdc.2019.08.008

Cited by 10 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The VSN method was used to reconstruct accelerometer spectra of physical sensors on rotorcraft from operating conditions and on-board generated statistical values of the sensor readings [19]. The motivation of the study is based on the circumstance that data transfer and storage capabilities are limited in rotorcraft while ample raw sensor spectra are desired for machine diagnostics with more advanced post-processing methods.…”

Section: Virtual Sensor Implementation With Neural Networkmentioning

confidence: 99%

Self-Protected Virtual Sensor Network for Microcontroller Fault Detection

Sternharz

Skackauskas

Elhalwagy

et al. 2022

Sensors

View full text Add to dashboard Cite

This paper introduces a procedure to compare the functional behaviour of individual units of electronic hardware of the same type. The primary use case for this method is to estimate the functional integrity of an unknown device unit based on the behaviour of a known and proven reference unit. This method is based on the so-called virtual sensor network (VSN) approach, where the output quantity of a physical sensor measurement is replicated by a virtual model output. In the present study, this approach is extended to model the functional behaviour of electronic hardware by a neural network (NN) with Long-Short-Term-Memory (LSTM) layers to encapsulate potential time-dependence of the signals. The proposed method is illustrated and validated on measurements from a remote-controlled drone, which is operated with two variants of controller hardware: a reference controller unit and a malfunctioning counterpart. It is demonstrated that the presented approach successfully identifies and describes the unexpected behaviour of the test device. In the presented case study, the model outputs a signal sample prediction in 0.14 ms and achieves a reconstruction accuracy of the validation data with a root mean square error (RMSE) below 0.04 relative to the data range. In addition, three self-protection features (multidimensional boundary-check, Mahalanobis distance, auxiliary autoencoder NN) are introduced to gauge the certainty of the VSN model output.

show abstract

Section: Virtual Sensor Implementation With Neural Networkmentioning

confidence: 99%

Self-Protected Virtual Sensor Network for Microcontroller Fault Detection

Sternharz

Skackauskas

Elhalwagy

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Tsai and Chou (2019) applied deep regression to Printed Circuit Board (PCB) positioning task, where the networks require only one single reference sample with a manually marked template window. Martı´nez et al (2020) performed deep regression to infer rotorcraft component vibration spectra, where the network architecture hyperparameters were optimized using an evolutionary genetic algorithm. Dornaika et al (2020) used two robust loss functions in deep regression networks for age estimation, where the influence of aberrant and outlier observations on the final model is considered.…”

Section: Introductionmentioning

confidence: 99%

Deep regression of convolutional neural network applied to resolved acceleration control for a robot manipulator

Kuo

Tang

2021

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

This paper presents a modified resolved acceleration control scheme based on deep regression of the convolutional neural network. The resolved acceleration control scheme can achieve precise motion control of robot manipulators by regulating the accelerations of the end-effector, and the conventional scheme needs the position and orientation of the end-effector, which are obtained through the direct kinematics of the robot manipulator. This scheme increases the computational loads and might obtain inaccurate position and orientation due to mechanical errors. To overcome the drawbacks, a camera is used to capture the images of the robot manipulator, and then a deep regression of convolutional neural network is imposed into the resolved acceleration control to obtain the position and orientation of the end-effector. The proposed approach aims to enhance the positioning accuracy, to reduce the computational loads, and to facilitate the deep regression in real-time control. In this study, the proposed approach is applied to a 3-DOF planar parallel robot manipulator, and the results are compared with those by the conventional resolved acceleration control and a visual servo-based control. The results show that those objectives are achieved. Furthermore, the robustness of the proposed approach is tested through only the partial image of the end-effector available, and the proposed approach still works functionally and effectively.

show abstract

“…Although machine learning (for example, radial basis function neural network [29], recurrent neural network and multi-layer perceptron [30]) has been employed in solving inverse problems (for example, structural health monitoring, damage detection and model updating) for rotor blade applications previously, however, we observed that the literature is scarce when it comes to the application of ML for forward stochastic aeroelastic response analysis of rotors. In this context, it is worth mentioning a recent work which has employed deep learning to emulate and extrapolate from the limited experimental responses of rotorcraft available as raw sensor (accelerometer) data and create a 'virtual sensor' for better understanding of their vibration behaviour [36]. A data-driven framework was proposed to develop safety-based diagnostics for rotorcrafts and to define the process of selecting a single, airworthy MLbased diagnostic classifier that replaces a suite of fielded condition indicators (CI) [54].…”

Section: Introductionmentioning

confidence: 99%

The stochastic aeroelastic response analysis of helicopter rotors using deep and shallow machine learning

Chatterjee

Essien

Ganguli

et al. 2021

Neural Comput & Applic

View full text Add to dashboard Cite

This paper addresses the influence of manufacturing variability of a helicopter rotor blade on its aeroelastic responses. An aeroelastic analysis using finite elements in spatial and temporal domains is used to compute the helicopter rotor frequencies, vibratory hub loads, power required and stability in forward flight. The novelty of the work lies in the application of advanced data-driven machine learning (ML) techniques, such as convolution neural networks (CNN), multi-layer perceptron (MLP), random forests, support vector machines and adaptive Gaussian process (GP) for capturing the nonlinear responses of these complex spatio-temporal models to develop an efficient physics-informed ML framework for stochastic rotor analysis. Thus, the work is of practical significance as (i) it accounts for manufacturing uncertainties, (ii) accurately quantifies their effects on nonlinear response of rotor blade and (iii) makes the computationally expensive simulations viable by the use of ML. A rigorous performance assessment of the aforementioned approaches is presented by demonstrating validation on the training dataset and prediction on the test dataset. The contribution of the study lies in the following findings: (i) The uncertainty in composite material and geometric properties can lead to significant variations in the rotor aeroelastic responses and thereby highlighting that the consideration of manufacturing variability in analyzing helicopter rotors is crucial for assessing their behaviour in real-life scenarios. (ii) Precisely, the substantial effect of uncertainty has been observed on the six vibratory hub loads and the damping with the highest impact on the yawing hub moment. Therefore, sufficient factor of safety should be considered in the design to alleviate the effects of perturbation in the simulation results. (iii) Although advanced ML techniques are harder to train, the optimal model configuration is capable of approximating the nonlinear response trends accurately. GP and CNN followed by MLP achieved satisfactory performance. Excellent accuracy achieved by the above ML techniques demonstrates their potential for application in the optimization of rotors under uncertainty.

show abstract

Rotorcraft virtual sensors via deep regression

Cited by 10 publications

References 5 publications

Self-Protected Virtual Sensor Network for Microcontroller Fault Detection

Self-Protected Virtual Sensor Network for Microcontroller Fault Detection

Deep regression of convolutional neural network applied to resolved acceleration control for a robot manipulator

The stochastic aeroelastic response analysis of helicopter rotors using deep and shallow machine learning

Contact Info

Product

Resources

About