Computational Burden Research Articles

Robust decentralized controller design for highly Maneuverable Aircraft

Large-scale control systems often encounter challenges due to their intricate control structures, leading to delays and uncertainties when traditional centralized control methods are implemented in engineering applications. In response to these challenges and with the aim of enhancing control efficiency, the exploration of decentralized control approaches has become increasingly prominent. This paper presents two decentralized control strategies: fixed structure control theory, which is built upon the foundational principles of traditional robust controller design, and the weighted model approximation method, which integrates weighted model reduction with optimization strategies. The fixed structure control theory predetermines architecture of the controllers, significantly alleviating the computational burden associated with the development of robust controllers. Conversely, the weighted model approximation method proposes a more intuitive and succinct pathway for controller design and engineering application. The efficacy of these strategies is evaluated through their application to the Highly Maneuverable Aircraft (HIMAT) system. The results demonstrate that, the fixed structure control theory generally exhibits good performance. However, in certain engineering scenarios, the conclusions derived from the weighted model approximation method for decentralized controller design are easier to comprehend and facilitate rapid application.

Robust speech command recognition in challenging industrial environments

Speech is among the main forms of communication between humans and robots in industrial settings, being the most natural way for a human worker to issue commands. However, the presence of pervasive and loud environmental noise poses significant challenges to the adoption of Speech-Command Recognition systems onboard manufacturing robots; indeed, they are expected to perform in real time on hardware with limited computational capabilities and also to be robust and accurate in such complex environments. In this paper, we propose an innovative system based on an End-to-End architecture with a Conformer backbone. Our system is specifically designed to achieve high accuracy in noisy industrial environments and to guarantee a minimal computational burden to meet stringent real-time requirements while running on computing devices that are embedded in robots. In order to increase the generalization capability of the system, the training procedure is driven by a Curriculum Learning strategy combined with dynamic data augmentation techniques, that progressively increase the complexity of input samples by increasing the noise during the training phase. We have conducted extensive experimentation to assess the effectiveness of our system, using a dataset composed of more than 50,000 samples, of which about 2,000 have been acquired during the daily operations of a Stellantis Italian factory. The results confirm the suitability of the proposed approach to be adopted in a real industrial environment; indeed, it is able to achieve, on both English and Italian commands, an accuracy higher than 90%, maintaining a compact model size (the network is 1.81 MB) and running in real-time on an industrial embedded device (namely 41ms over an NVIDIA Xavier NX).

Local Second Order Mo̷ller-Plesset Theory with a Single Threshold Using Orthogonal Virtual Orbitals: A Distributed Memory Implementation.

In order to alleviate the computational burden associated with superlinear compute scalings with molecular size in electron correlation methods, researchers have developed local correlation methods that wisely treat relatively small contributions as zeros but still yield accurate energy approximation. Such local correlation techniques can also be combined with parallel computing resources to obtain further efficiency and scalability. This work focuses on the distributed memory parallel implementation of a local correlation method for second order Mo̷ller-Plesset (MP2) theory. This method also only has a single threshold to control the dropping of terms and accuracy of different computing kernels in the algorithm. The process partitioning strategy and distributed parallel implementation with the message passing interface (MPI) are discussed. In particular, the algorithm relies on a fixed sparsity pattern matrix multiplication and a corresponding distributed conjugate gradient solver, which exhibits almost linear scaling in both strong and weak scaling analyses. Numerical experiments on a range of molecules, including linear chains and molecules with 2 and 3-dimensional characters, are reported. For example, with only 32 MPI ranks, this MP2 implementation can calculate the correlation energy of vancomycin in def2-TZVP basis within 0.003% accuracy (10-6.5 threshold) in half an hour, where the same problem is unfeasible to solve with sequential or pure shared memory implementations.

Insulator Defect Detection Based on YOLOv5s-KE

To tackle the issue of low detection accuracy in insulator images caused by intricate backgrounds and small defect sizes, as well as the requirement for real-time detection on embedded and mobile devices, this research introduces the YOLOv5s-KE model. Integrating multiple strategies, YOLOv5s-KE aims to boost detection accuracy significantly. Initially, an enhanced anchor generation method utilizing the K-means++ algorithm is proposed to generate more appropriate anchor boxes for insulator defects. Moreover, an attention mechanism is integrated into both the backbone and neck networks to enhance the model’s capacity to focus on defect features and resist interference. To improve the detection of small defects, the EIoU loss function is implemented in place of the original CIoU loss function. In order to meet the real-time detection needs on embedded and mobile devices, the model is further refined through the integration of Ghost convolution for lightweight feature extraction and a linear transformation to reduce the computational burden of standard convolution. A channel pruning strategy is deployed to optimize the sparsely trained network, diminishing redundancy, and improving model generalization. Additionally, the CARAFE operator replaces the original upsampling operator to minimize model parameters and elevate detection speed. Experimental outcomes demonstrate that YOLOv5s-KE achieves a detection accuracy of 92.3% on the Chinese transmission line insulator dataset, marking a 5.2% enhancement over the original YOLOv5s. The streamlined version of YOLOv5s-KE achieves a detection speed of 94.3 frames per second, indicating an improvement of 30.1 frames per second compared to the original model. Model parameters are condensed to 9.6 M, resulting in a detection accuracy of 91.1%. This study underscores the precision and efficiency of the proposed approach, suggesting that the advanced strategies explored introduce novel possibilities for insulator defect detection.

PCP-GC-LM: single-sequence-based protein contact prediction using dual graph convolutional neural network and convolutional neural network

BackgroundRecently, the process of evolution information and the deep learning network has promoted the improvement of protein contact prediction methods. Nevertheless, still remain some bottleneck: (1) One of the bottlenecks is the prediction of orphans and other fewer evolution information proteins. (2) The other bottleneck is the method of predicting single-sequence-based proteins mainly focuses on selecting protein sequence features and tuning the neural network architecture, However, while the deeper neural networks improve prediction accuracy, there is still the problem of increasing the computational burden. Compared with other neural networks in the field of protein prediction, the graph neural network has the following advantages: due to the advantage of revealing the topology structure via graph neural network and being able to take advantage of the hierarchical structure and local connectivity of graph neural networks has certain advantages in capturing the features of different levels of abstraction in protein molecules. When using protein sequence and structure information for joint training, the dependencies between the two kinds of information can be better captured. And it can process protein molecular structures of different lengths and shapes, while traditional neural networks need to convert proteins into fixed-size vectors or matrices for processing.ResultsHere, we propose a single-sequence-based protein contact map predictor PCP-GC-LM, with dual-level graph neural networks and convolution networks. Our method performs better with other single-sequence-based predictors in different independent tests. In addition, to verify the validity of our method against complex protein structures, we will also compare it with other methods in two homodimers protein test sets (DeepHomo test dataset and CASP-CAPRI target dataset). Furthermore, we also perform ablation experiments to demonstrate the necessity of a dual graph network. In all, our framework presents new modules to accurately predict inter-chain contact maps in protein and it’s also useful to analyze interactions in other types of protein complexes.

Practical prescribed time tracking control for a class of nonlinear systems with event triggering and output constraints

AbstractThis paper investigates the practical prescribed time tracking for a class of uncertain nonlinear systems based on neural networks and event‐triggered control. Introducing a time‐varying constraint function transforms the original practical prescribed time‐tracking control issue into a tracking error constraint problem. An event‐triggered adaptive control has been proposed, which can effectively reduce the communication burden between the controller and the actuator. Using neural networks to approximate unknown nonlinear functions avoids the differentiation of virtual controllers, thereby reducing the computational burden. In addition, users can independently choose preset time and tracking accuracy without changing the control structure, which remains independent of the initial conditions and any design parameters. Finally, the effectiveness of this method is verified through simulation examples.

Cloud-fog architecture-based control of smart island microgrid in master-slave organization using disturbance observer-based hybrid backstepping sliding mode controller

Distributed control is an effective method to coordinate the microgrid with various components, and also in a smart microgrid, communication graph layouts are essential since changing the topology unexpectedly could disrupt the operation of the distributed controllers, and also an imbalance may occur between the production and load. Hence, reducing the exchanged data between units and system operator is essential in order to reduce the transmitted data volume and computational burden. For this purpose, an islanded microgrid with multiple agents which is using cloud-fog computing is proposed here, in order to reduce the computing burden on the central control unit as well as reducing data exchange among units. To balance the production power and loads in a smart island with a stable voltage/frequency, a hybrid backstepping sliding mode controller (BSMC) with disturbance observer (DO) is suggested to control voltage/frequency and current in the MG-based master-slave organization. Therefore, this paper proposes a DO-driven BSMC for controlling voltage/frequency, and power of energy sources within a Master-Slave organization; in addition, the study proposes a clod-fog computing for enhancing performance, reducing transferred data volume, and processing information on time. In the extensive simulations, the suggested controller shows a reduction in steady-state error, a fast response, and a lower total harmonic distortion (THD) for nonlinear and linear loads less than 0.33 %. The fog layer serves as a local processing level, so it reduces the exchanged data between cloud and fog nodes.

Remote sensing image road network detection based on channel attention mechanism

Extracting and detecting road network consistency from high-resolution remote sensing images has been a hot and difficult problem in the computer vision. Although it has made significant progress, there is still a phenomenon of high training accuracy but unsatisfactory actual extraction and detection results. The attention mechanism is one of the efficient and practical mechanisms in deep learning. It improves the performance of deep learning by selectively focusing on a portion of all information while ignoring other visible information, while effectively utilizing computing resources. Numerous experiments have also confirmed that the attention mechanism is resource-saving and effective. Its plug and play feature brings great convenience to programmers. In order to provide better road network detection results and solve the above problem, this paper combines the channel attention mechanism with ResNet and proposes SE-ResNet and ECA-ResNet for remote sensing image road network detection, making networks extract and learn road network features and ignore some non-road network features. The experimental results show that on the Massachusetts roads (MR) and CHN6-CUG roads datasets, ECA-ResNet and SE-ResNet based on channel attention mechanism perform similar to LeNet7 and ResNet in terms of accuracy, loss, accuracy convergence, and loss convergence, and even increase a certain computational burden. However, their final road network detection results (including road network detection pixel count, precision, recall, accuracy, IOU, F1 score, and actual road network detection result) of the former are significantly better than those of the latter. The channel attention mechanism makes the deep neural network pay more attention to the extraction and learning of road network features, while ignoring the extraction and learning of some non-road network features, which improves the accuracy of containing road network samples and reduces the accuracy of not containing road network samples. Therefore, the performance of ECA-ResNet and SE-ResNet is similar to that of LeNet7 and ResNet in the accuracy, loss, accuracy convergence and loss convergence, but the final road network detection results of ECA-ResNet and SE-ResNet are significantly better than those of LeNet7 and ResNet. Therefore, the proposed ECA-ResNet and SE-ResNet have broad application prospects in road network detection, especially ECA-ResNet.

Improving Deep Neural Networks' Training for Image Classification With Nonlinear Conjugate Gradient-Style Adaptive Momentum.

Momentum is crucial in stochastic gradient-based optimization algorithms for accelerating or improving training deep neural networks (DNNs). In deep learning practice, the momentum is usually weighted by a well-calibrated constant. However, tuning the hyperparameter for momentum can be a significant computational burden. In this article, we propose a novel adaptive momentum for improving DNNs training; this adaptive momentum, with no momentum-related hyperparameter required, is motivated by the nonlinear conjugate gradient (NCG) method. Stochastic gradient descent (SGD) with this new adaptive momentum eliminates the need for the momentum hyperparameter calibration, allows using a significantly larger learning rate, accelerates DNN training, and improves the final accuracy and robustness of the trained DNNs. For instance, SGD with this adaptive momentum reduces classification errors for training ResNet110 for CIFAR10 and CIFAR100 from 5.25% to 4.64% and 23.75% to 20.03%, respectively. Furthermore, SGD, with the new adaptive momentum, also benefits adversarial training and, hence, improves the adversarial robustness of the trained DNNs.

The linear canonical W-transform

The time-frequency spectrum of seismic data is commonly used as an attribute in the analysis and interpretation of nonstationary seismic signals. To improve the capability of the W-transform to analyze nonstationary data, we introduce the linear canonical W-transform (LCWT) by implementing an affine matrix along with scaling parameters to generate high resolution and energy-concentrated time-frequency spectra. More features of nonstationary signals can be explored in the time-linear canonical frequency domain by transforming the time-frequency plane, which makes the algorithm more applicable to seismic signals. For the completeness of the LCWT, we also develop the inverse LCWT to extend its applications. Examples of synthetic and field seismic data show that a highly resolved and energy-concentrated time-frequency spectrum can be estimated with the LCWT with negligible additional computational burden. In addition, our algorithm is promising for several seismic data processing and interpretation techniques, such as reservoir characterization and thin layer identification.

Virtually coupled train set control subject to space-time separation: A distributed economic MPC approach with emergency braking configuration

The emerging virtual coupling technology aims to operate multiple train units in a Virtually Coupled Train Set (VCTS) at a minimal but safe distance. To guarantee collision avoidance, the safety distance should be calculated using the state-of-the-art space-time separation principle that separates the Emergency Braking (EB) trajectories of two successive units during the whole EB process. In this case, the minimal safety distance is usually numerically calculated without an analytic formulation. Thus, the constrained VCTS control problem is hard to address with space-time separation, which is still a gap in the existing literature. To solve this problem, we propose a Distributed Economic Model Predictive Control (DEMPC) approach with computation efficiency and theoretical guarantee. Specifically, to alleviate the computation burden, we transform implicit safety constraints into explicitly linear ones, such that the optimal control problem in DEMPC is a quadratic programming problem that can be solved efficiently. For theoretical analysis, sufficient conditions are derived to guarantee the recursive feasibility and stability of DEMPC, employing compatibility constraints, tube techniques and terminal ingredient tuning. Moreover, we extend our approach with globally optimal and distributed online EB configuration methods to shorten the minimal distance among VCTS. Finally, experimental results demonstrate the performance and advantages of the proposed approaches.

Combining optical flow and Swin Transformer for Space-Time video super-resolution

Space–time video super-resolution is a task that aims to interpolate low frame rate, low resolution videos to high frame rate, high resolution ones. While existing Transformer-based methods have achieved results comparable to convolutional neural networks-based methods, the computational cost of Transformer limits its performance with constrained computational resources. Moreover, Swin Transformer may fail to fully exploit the spatio-temporal information of video frames due to the limitation of window size, impeding its effectiveness in handling large motions. To address these limitations, we propose an end-to-end space–time video super-resolution architecture based on optical flow alignment and Swin Transformer. The alignment module is introduced to extract spatio-temporal information from adjacent frames without significantly increasing the computational burden. Additionally, we design a residual convolution layer to enhance the translational invariance of the features extracted by Swin Transformer and introduces additional nonlinear transformations. Experimental results demonstrate that our proposed method achieves superior performance on various benchmark datasets compared to state-of-the-art methods. In terms of Peak Signal-to-Noise Ratio, our method outperforms the state-of-the-art methods by at least 0.15 dB on Vimeo-Medium dataset.

Event-driven nearshore and shoreline coastline detection on SpiNNaker neuromorphic hardware

Abstract Coastline detection is vital for coastal management, involving frequent observation and assessment to understand coastal dynamics and inform decisions on environmental protection. 
Continuous streaming of high-resolution images demands robust data processing and storage solutions to manage large datasets efficiently, posing challenges that require innovative solutions for real-time analysis and meaningful insights extraction.
This work leverages low-latency event-based vision sensors coupled with neuromorphic hardware in an attempt to decrease a two-fold challenge, reducing the computational burden to ~0.375 mW whilst obtaining a coastline detection map in as little as 20 ms.
The proposed Spiking Neural Network (SNN) runs on the SpiNNaker neuromorphic platform using a total of 18040 neurons reaching 98.33% accuracy.
The model has been characterised and evaluated by computing the accuracy of Intersection over Union (IoU) scores over the ground truth of a real-world coastline dataset across different time windows. The system's robustness was further assessed by evaluating its ability to avoid coastline detection in non-coastline profiles and funny shapes, achieving a success rate of 97.3%.

A Low Computational Burden Model Predictive Control for Dynamic Wireless Charging

A Low Computational Burden Model Predictive Control for Dynamic Wireless Charging

Finite domain solution of a hydraulic fracture in a permeable rock

In this work, we present a domain-based algorithm to simulate the propagation of a plane-strain hydraulic fracture in a zero-toughness permeable elastic medium. The algorithm utilizes a domain-based method to solve the elasticity equations and integrates a multi-scale tip asymptote, which is particular to hydraulic fractures, into this framework. This integration is key to accurately model the energy dissipation and the fluid leak-off in the fracture tip region. The algorithm combines a 2D finite volume method (FVM) for solving the elasticity equation with a 1D FVM for solving the nonlinear lubrication equation. Incorporating the far-field asymptotics and using a moving-mesh scheme reduces the computational burden while improving the accuracy of the scheme. The paper concludes with an analysis of the numerical results. This study demonstrates the potential of this domain-based approach for modeling hydraulic fractures in poroelastic media.

A Novel Model Predictive Current Control With Reduced Computational Burden Based on Discrete Space Vector Modulation for PMSM Drives

A Novel Model Predictive Current Control With Reduced Computational Burden Based on Discrete Space Vector Modulation for PMSM Drives

Prescribed performance dynamic surface control based on dual extended state observer for 2-dof hydraulic cutting arm

In tunnel section forming operations, the boom-type roadheader tracking target trajectory with high precision is greatly significant in avoiding over and under excavation and improving excavation efficiency. However, there exist complex cutting loads, measurement noise, and model uncertainties, seriously degrading the tracking performance of traditional nominal model-based controllers. Hence, this study first fully analyzes the kinematics of all members of the cutting mechanism and establishes its complete multi-body dynamic model using the Lagrange method. Furthermore, a dual extended state observer is designed to estimate the mechanical system’s angular velocity and unmodeled disturbances and actuators’ uncertain nonlinearities. In particular, introducing a nonlinear filter replaces the traditional first-order filter in dynamic surface technology, overcoming the “explosion of complexity” while attenuating the conservatism of gains tuning. Then, a dual extended state observer-based prescribed performance dynamic surface controller is developed for roadheaders for the first time. Simultaneously, integrating an improved error transformation function into controller design effectively avoids the online computational burden caused by traditional logarithmic operations. Utilizing Lyapunov theory, the cutting system’s prescribed transient response and steady-state performance are guaranteed. Finally, the proposed controller’s effectiveness is verified by comparative experiments on the roadheader.

Envelope Inversion with Source encoding for Ultrasound Computed Tomography

Abstract Ultrasound computed tomography (USCT) is a noninvasive and non-ionizing imaging technique for soft tissue and limb bones. Full waveform inversion (FWI) has received increased interest due to its high resolution. The difficulties in FWI are twofold: high computational burden and poor convergence. To address these issues, an envelope inversion with source coding (EI-SE) algorithm is proposed in this paper. The envelope-based objective function measures the matching degree between the predicted and measured envelopes. It can provide the low-frequency components of the signal that are not available to FWI. Therefore, the EI can provide an accurate solution even when the initial model is far from the ground truth and low-frequency data are missing. The simulations are conducted to demonstrate the validity of the proposed algorithm. The root mean squared error (RMSE) of the proposed algorithm is much smaller than that of conventional FWI. The results show that EI-SE is effective in avoiding cycle skipping.

Adaptive formulation for probabilistic storm surge predictions through sharing of numerical simulation results across storm advisories

As a tropical storm/cyclone approaches landfall, real-time probabilistic predictions for the anticipated surge provide valuable information for emergency preparedness/response decisions. These probabilistic predictions are made through an uncertainty quantification process that involves: (i) generating a sufficiently large ensemble of storm scenarios based on the nominal storm advisory and the anticipated forecast errors; (ii) performing high-fidelity numerical simulations to obtain surge predictions for each storm scenario; and (iii) estimating surge statistics of interest by assembling the simulation results. This process is repeated whenever the nominal storm advisory is updated. The number of storm scenarios utilized in the analysis directly impacts the statistical accuracy of the probabilistic predictions; a larger ensemble improves accuracy but requires greater computational resources to provide predictions with the desired expediency to guide real-time decisions. This paper revisits two recently proposed Monte-Carlo (MC) frameworks that aim to improve accuracy without increasing the computational burden: adaptive importance sampling (AIS) and adaptive multi-fidelity Monte Carlo (AMFMC). The foundational concept behind them is similar: share numerical simulation results across the probabilistic predictions performed for different storm advisories to accelerate the MC estimation. This is achieved differently for each approach, through adaptive development of an importance sampling proposal density (for AIS) or a surrogate model (for AMFMC). Here, a direct comparison between these frameworks is established, focusing on the mechanisms for the information sharing and the challenges encountered in tuning the algorithm adaptive characteristics to provide probabilistic estimates across a large number of quantities of interest (QoIs), corresponding to the surge predictions for different locations within the coastal region of interest. As this large number results in conflicting choices for the adaptive characteristics, a compromise solution needs to be promoted. The efficacy of the two frameworks is examined in detail in this setting, comparing the accuracy of idealized implementations (adaptive decisions independently made for each QoI) to the accuracy of practical implementations (single, compromise decision within the MC implementation). The study also showcases the importance of information sharing across storm advisories in real-time probabilistic storm surge predictions and provides guidelines for an efficient adaptive MC formulation in such settings.

Sound speed imaging of cortical bone and soft tissue based on frequency-domain ultrasound waveform tomography

Abstract As one of the ultrasound computed tomography (UCT) algorithms, full-waveform inversion (FWI) can recover clear and detailed internal structures of bones by iteratively minimizing the misfit between observed and numerical data. However, time domain full-waveform inversion (TDFWI) often lacks sufficient low-frequency information, and the computation of full-time data imposes a significant computational burden. Besides, there are few studies on whole-medium reconstruction that jointly invert the bone and surrounding soft tissues. In this study, an FWI-based frequency-domain UCT (FD-UCT) is utilized for simultaneously imaging the sound speed of bones and soft tissues, which facilitates the inversion efficiency while ensuring the existence of low-frequency information. Simulated studies show that the FD-UCT can both reconstruct bones with large acoustic impedance and distinguish subtle impedance differences within soft tissues to reveal lesions.