Search

In this paper, a novel zonal machine learning (ML) approach for Reynolds-averaged Navier-Stokes (RANS) turbulence modelling based on the divide-and-conquer technique is introduced. This approach involves partitioning the flow domain into regions of flow physics called zones, training one ML model in each zone, then validating and testing them on their respective zones. The approach was demonstrated with the tensor basis neural network (TBNN) and another neural net called the turbulent kinetic energy neural network (TKENN). These were used to predict Reynolds stress anisotropy and turbulent kinetic energy respectively in test cases of flow over a solid block, which contain regions of different flow physics including separated flows. The results show that the combined predictions given by the zonal TBNNs and TKENNs were significantly more accurate than their corresponding standard non-zonal models. Most notably, shear anisotropy component in the test cases was predicted at least 20% and 55% more accurately on average by the zonal TBNNs compared to the non-zonal TBNN and RANS, respectively. The Reynolds stress constructed with the zonal predictions was also found to be at least 23% more accurate than those obtained with the non-zonal approach and 30% more accurate than the Reynolds stress predicted by RANS on average. These improvements were attributed to the shape of the zones enabling the zonal models to become highly locally optimized at predicting the output.

Recent growing interest in using machine learning for turbulence modelling has led to many proposed data-driven turbulence models in the literature. However, most of these models have not been developed with overcoming non-unique mapping (NUM) in mind, which is a significant source of training and prediction error. Only NUM caused by one-dimensional channel flow data has been well studied in the literature, despite most data-driven models having been trained on two-dimensional flow data. The present work aims to be the first detailed investigation on NUM caused by two-dimensional flows. A method for quantifying NUM is proposed and demonstrated on data from a flow over periodic hills, and an impinging jet. The former is a wall-bounded separated flow, and the latter is a shear flow containing stagnation and recirculation. This work confirms that data from two-dimensional flows can cause NUM in data-driven turbulence models with the commonly used invariant inputs. This finding was verified with both cases, which contain different flow phenomena, hence showing that NUM is not limited to specific flow physics. Furthermore, the proposed method revealed that regions containing low strain and rotation or near pure shear cause the majority of NUM in both cases: approximately 76% and 89% in the flow over periodic hills and impinging jet, respectively. These results led to viscosity ratio being selected as a supplementary input variable (SIV), demonstrating that SIVs can reduce NUM caused by data from two-dimensional flows and subsequently improve the accuracy of tensor-basis machine learning models for turbulence modelling.

Cyclic motions are fundamental patterns in robotic applications including industrial manipulation and legged robot locomotion. This paper proposes an approach for the online modulation of cyclic motions in robotic applications. For this purpose, we present an integrated programmable Central Pattern Generator (CPG) for the online generation of the reference joint trajectory of a robotic system out of a library of desired periodic motions. The reference trajectory is then followed by the lower-level controller of the robot. The proposed CPG generates a smooth reference joint trajectory convergence to the desired one while preserving the position and velocity joint limits of the robot. The integrated programmable CPG consists of one novel bounded output programmable oscillator. We design the programmable oscillator for encoding the desired multidimensional periodic trajectory as a stable limit cycle. We also use the state transformation method to ensure that the oscillator's output and its first-time derivative preserve the joint position and velocity limits of the robot. With the help of Lyapunov-based arguments, We prove that the proposed CPG provides the global stability and convergence of the desired trajectory. The effectiveness of the proposed integrated CPG for trajectory generation is shown in a passive rehabilitation scenario on the Kuka iiwa robot arm, and also in a walking simulation on a seven-link bipedal robot., Comment: https://ieeexplore.ieee.org/document/9756235

Despite extensive studies on motion stabilization of bipeds, they still suffer from the lack of disturbance coping capability on slippery surfaces. In this paper, a novel controller for stabilizing a bipedal motion in its sagittal plane is developed with regard to the surface friction limitations. By taking into account the physical limitation of the surface in the stabilization trend, a more advanced level of reliability is achieved that provides higher functionalities such as push recovery on low-friction surfaces and prevents the stabilizer from overreacting. The discrete event-based strategy consists of modifying the step length and time period at the beginning of each footstep in order to reestablish stability necessary conditions while taking into account the surface friction limitation as a constraint to prevent slippage. Adjusting footsteps to prevent slippage in confronting external disturbances is perceived as a novel strategy for keeping stability, quite similar to human reaction. The developed methodology consists of rough closed-form solutions utilizing elementary math operations for obtaining the control inputs, allowing to reach a balance between convergence and computational cost, which is quite suitable for real-time operations even with modest computational hardware. Several numerical simulations, including push recovery and switching between different gates on low-friction surfaces, are performed to demonstrate the effectiveness of the proposed controller. In correlation with human-gait experience, the results also reveal some physical aspects favoring stability and the fact of switching between gaits to reduce the risk of falling in confronting different conditions., Comment: for associated simulation video, see https://youtu.be/BWzUgHGdl3I

Recent advances in guiding and localizing light at the nanoscale exposed the enormous potential of ultra-scaled plasmonic devices. In this context, the decay of surface plasmons to hot carriers triggers a variety of applications in boosting the efficiency of energy-harvesting, photo-catalysis and photo-detection. However, a detailed understanding of plasmonic hot carrier generation and particularly the transfer at metal-semiconductor interfaces is still elusive. In this paper, we introduce a monolithic metal-semiconductor (Al-Ge) heterostructure device, providing a platform to examine surface plasmon decay and hot electron transfer at an atomically sharp Schottky nanojunction. The gated metal-semiconductor heterojunction device features electrostatic control of the Schottky barrier height at the Al-Ge interface, enabling hot electron filtering. The ability of momentum matching and to control the energy distribution of plasmon-driven hot electron injection is demonstrated by controlling the interband electron transfer in Ge leading to negative differential resistance.

Cyclic motions in vertebrates, including heart beating, breathing and walking, are derived by a network of biological oscillators having fascinating features such as entrainment, environment adaptation, and robustness. These features encouraged engineers to use oscillators for generating cyclic motions. To this end, it is crucial to have oscillators capable of characterizing any periodic signal via a stable limit cycle. In this paper, we propose a 2-dimensional oscillator whose limit cycle can be matched to any periodic signal depicting a non-self-intersecting curve in the state space. In particular, the proposed oscillator is designed as an autonomous vector field directed toward the desired limit cycle. To this purpose, the desired reference signal is parameterized with respect to a state-dependent phase variable, then the oscillator's states track the parameterized signal. We also present a state transformation technique to bound the oscillator's output and its first time derivative. The soundness of the proposed oscillator has been verified by carrying out a few simulations., Comment: 58th IEEE Conference on Decision and Control (CDC2019)

Approximating distributions over complicated manifolds, such as natural images, are conceptually attractive. The deep latent variable model, trained using variational autoencoders and generative adversarial networks, is now a key technique for representation learning. However, it is difficult to unify these two models for exact latent-variable inference and parallelize both reconstruction and sampling, partly due to the regularization under the latent variables, to match a simple explicit prior distribution. These approaches are prone to be oversimplified, and can only characterize a few modes of the true distribution. Based on the recently proposed Wasserstein autoencoder (WAE) with a new regularization as an optimal transport. The paper proposes a stacked Wasserstein autoencoder (SWAE) to learn a deep latent variable model. SWAE is a hierarchical model, which relaxes the optimal transport constraints at two stages. At the first stage, the SWAE flexibly learns a representation distribution, i.e., the encoded prior; and at the second stage, the encoded representation distribution is approximated with a latent variable model under the regularization encouraging the latent distribution to match the explicit prior. This model allows us to generate natural textual outputs as well as perform manipulations in the latent space to induce changes in the output space. Both quantitative and qualitative results demonstrate the superior performance of SWAE compared with the state-of-the-art approaches in terms of faithful reconstruction and generation quality., Comment: arXiv admin note: text overlap with arXiv:1902.05581

Image-to-image translation, which translates input images to a different domain with a learned one-to-one mapping, has achieved impressive success in recent years. The success of translation mainly relies on the network architecture to reserve the structural information while modify the appearance slightly at the pixel level through adversarial training. Although these networks are able to learn the mapping, the translated images are predictable without exclusion. It is more desirable to diversify them using image-to-image translation by introducing uncertainties, i.e., the generated images hold potential for variations in colors and textures in addition to the general similarity to the input images, and this happens in both the target and source domains. To this end, we propose a novel generative adversarial network (GAN) based model, InjectionGAN, to learn a many-to-many mapping. In this model, the input image is combined with latent variables, which comprise of domain-specific attribute and unspecific random variations. The domain-specific attribute indicates the target domain of the translation, while the unspecific random variations introduce uncertainty into the model. A unified framework is proposed to regroup these two parts and obtain diverse generations in each domain. Extensive experiments demonstrate that the diverse generations have high quality for the challenging image-to-image translation tasks where no pairing information of the training dataset exits. Both quantitative and qualitative results prove the superior performance of InjectionGAN over the state-of-the-art approaches.

Bipedal robots adapt to the environment of the modern society due to the similarity of movement to humans, and therefore they are a good partner for humans. However, maintaining the stability of these robots during walking/running motion is a challenging issue that, despite the development of new technologies and the advancement of knowledge, does not yet have a satisfactory solution. In most of the proposed methods by researchers, to maintain the stability of walking bipedal robots, it has been tried to ensure the momentary stability of motion by limiting the motion to multiple constraints. Although these methods have good performance in sustaining stability, they leave the robot away from the natural movement of humans, with low efficiency and high energy consumption. Hence, many researchers have turned to the walking techniques that follow a certain motion limit cycle, in which we can consider the overall stability rather than momentary. In this paper, a method is proposed to maintain the stability of the limit cycle against disturbance. For this purpose, the dynamical model of the biped robot is extracted in the space of total momentum variables and, according to the desired step length and speed, the motion limit cycle is designed. Subsequently, a motion stabilizer is proposed based on the idea of length shift, which is a natural human strategy for sustaining the balance in case of impact. The simulations show that this technique has a good performance in maintaining the stability of motion and has similar responses to human response., Comment: Paper in Persian (Farsi) Language (https://www.civilica.com/Paper-ISME27-ISME27_211.html)

Regularized autoencoders learn the latent codes, a structure with the regularization under the distribution, which enables them the capability to infer the latent codes given observations and generate new samples given the codes. However, they are sometimes ambiguous as they tend to produce reconstructions that are not necessarily faithful reproduction of the inputs. The main reason is to enforce the learned latent code distribution to match a prior distribution while the true distribution remains unknown. To improve the reconstruction quality and learn the latent space a manifold structure, this work present a novel approach using the adversarially approximated autoencoder (AAAE) to investigate the latent codes with adversarial approximation. Instead of regularizing the latent codes by penalizing on the distance between the distributions of the model and the target, AAAE learns the autoencoder flexibly and approximates the latent space with a simpler generator. The ratio is estimated using generative adversarial network (GAN) to enforce the similarity of the distributions. Additionally, the image space is regularized with an additional adversarial regularizer. The proposed approach unifies two deep generative models for both latent space inference and diverse generation. The learning scheme is realized without regularization on the latent codes, which also encourages faithful reconstruction. Extensive validation experiments on four real-world datasets demonstrate the superior performance of AAAE. In comparison to the state-of-the-art approaches, AAAE generates samples with better quality and shares the properties of regularized autoencoder with a nice latent manifold structure.

In this study, capillary-driven flow of different pure liquids and diluted bitumen samples were studied using microfluidic channel (width of 30 um and depth of 9 um). Capillary filling kinetics of liquids as a function of time were evaluated and compared with theoretical predictions. For pure liquids including water, toluene, hexane, and methanol experimental results agreed well with theoretical predictions. However, for bitumen samples, as concentration of bitumen increased the deviation between theoretical and experimental results became larger. The higher deviation for high concentrations (i.e. above 30%) can be due to the difference between dynamic contact angle and bulk contact angle. Microchannels are suitable experimental devices to study the flow of heavy oil and bitumen in porous structure such as those of reservoirs., Comment: The manuscript has been accepted in AIChE conference, 2016

This paper presents a minimalist neural regression network as an aggregate of independent identical regression blocks that are trained simultaneously. Moreover, it introduces a new multiplicative parameter, shared by all the neural units of a given layer, to maintain the quality of its gradients. Furthermore, it increases its estimation accuracy via learning a weight factor whose quantity captures the redundancy between the estimated and actual values at each training iteration. We choose the estimation of the direct weld parameters of different welding techniques to show a significant improvement in calculation of these parameters by our model in contrast to state-of-the-arts techniques in the literature. Furthermore, we demonstrate the ability of our model to retain its performance when presented with combined data of different welding techniques. This is a nontrivial result in attaining an scalable model whose quality of estimation is independent of adopted welding techniques.

We present an adaptive sampling approach to 3D reconstruction of the welding joint using the point cloud that is generated by a laser sensor. We start with a randomized strategy to approximate the surface of the volume of interest through selection of a number of pivotal candidates. Furthermore, we introduce three proposal distributions over the neighborhood of each of these pivots to adaptively sample from their neighbors to refine the original randomized approximation to incrementally reconstruct this welding space. We prevent our algorithm from being trapped in a neighborhood via permanently labeling the visited samples. In addition, we accumulate the accepted candidates along with their selected neighbors in a queue structure to allow every selected sample to contribute to the evolution of the reconstructed welding space as the algorithm progresses. We analyze the performance of our adaptive sampling algorithm in contrast to the random sampling, with and without replacement, to show a significant improvement in total number of samples that are drawn to identify the region of interest, thereby expanding upon neighboring samples to extract the entire region in a fewer iterations and a shorter computation time., Comment: Disapproval of funding organization

We present a deep learning approach to estimation of the bead parameters in welding tasks. Our model is based on a four-hidden-layer neural network architecture. More specifically, the first three hidden layers of this architecture utilize Sigmoid function to produce their respective intermediate outputs. On the other hand, the last hidden layer uses a linear transformation to generate the final output of this architecture. This transforms our deep network architecture from a classifier to a non-linear regression model. We compare the performance of our deep network with a selected number of results in the literature to show a considerable improvement in reducing the errors in estimation of these values. Furthermore, we show its scalability on estimating the weld bead parameters with same level of accuracy on combination of datasets that pertain to different welding techniques. This is a nontrivial result that is counter-intuitive to the general belief in this field of research., Comment: Disapproval of funding organization

This article presents a novel utilization of the concept of entropy in information theory to model-free 3D reconstruction of weld joint in presence of noise. We show that our formulation attains its global minimum at the upper edge of this joint. This property significantly simplifies the extraction of this welding joint. Furthermore, we present an approach to compute the volume of this extracted space to facilitate the monitoring of the progress of the welding task. Moreover, we provide a preliminary analysis of the effect of variation of the noise on the extraction process of this space to realize the impact of this noise on the computation of its area and volume., Comment: Disapproval of funding organization