Traditional Adaptive Methods Research Articles

Fixed-Time Adaptive Neural Network Compensation Control for Electric Cylinder Erection Systems

Abstract This paper proposed a fixed-time adaptive neural network compensation control (FTANN) strategy for electric cylinder erection systems with unknown system dynamics and external time-varying disturbances. This method fully leveraged the estimation capabilities of neural networks and the rapid convergence of fixed-time control. Compared to traditional adaptive fixed-time neural network control methods, the proposed controller exploited the neural network’s ability to approximate arbitrary nonlinear functions, maximizing the neural network’s potential while avoiding the high gain issues that traditional controllers might have encountered. The Lyapunov stability theory was used to prove that the closed-loop system was fixed-time stable, and simulations verified the effectiveness of the proposed method.

A novel adaptive parameter zeroing neural network for the synchronization of complex chaotic systems and its field programmable gate array implementation

This article proposes a novel adaptive-parameter zeroing neural network (NAP-ZNN) to control the synchronization of complex chaotic systems. Different from previous zeroing neural networks (ZNNs), the NAP-ZNN model incorporates adaptive-parameter, a unique blend of time-varying convergence factor and fuzzy control parameter, which is adjusted continuously according to the real-time synchronizing error, offering greater flexibility. The NAP-ZNN model aims to address the time-varying problem in complex-valued domain, which is scarcely explored, it rapidly impels two complex chaotic systems to synchronize within predetermined time and effectively mitigates noise interference. Moreover, the upper bound of the convergence time is theoretically calculated in noiseless environments, and the disturbance-resistant property is demonstrated under various noisy disturbances. The control performance of NAP-ZNN model has been separately compared to other general ZNNs (NAP-ZNN synchronizes at 0.097 s while three general ZNNs spend 0.43 s, 0.78 s and 0.84 s, and only NAP-ZNN complete synchronization within 0.1 s under noisy interferences while general ZNNs fail) and the traditional adaptive control method through two synchronization simulation (RMSE of NAP-ZNN under sinusoidal noise is 3.165 × 10-3 while traditional is 3.383 at t = 1 s). The numerical outcomes clearly illustrate the superior performance of the NAP-ZNN model in comparison to other synchronization strategies. The hardware implementation of the NAP-ZNN model has been successfully realized through the Field Programmable Gate Array (FPGA), and the chaos synchronization process has been vividly captured via an oscilloscope, further reinforcing the practicality and effectiveness of the NAP-ZNN model.

Simple and efficient step detection algorithm for foot-mounted IMU

Abstract This paper presents a concise, efficient, and adaptive step detection algorithm based on foot-mounted inertial measurement unit sensors. The proposed method maps the temporal values of pedestrian motion and gait diversity into two variables: the distance between peaks and valleys, and the slope. Compared to traditional sliding window methods, this approach amplifies the differences between normal and abnormal steps, allowing it to adapt to various indoor activities such as fast walking, slow walking, running, jogging, standing still, and turning. By incorporating adaptive factors, it addresses the challenge of detecting steps while going up and down stairs. The proposed algorithm overcomes the limitations of traditional adaptive threshold methods that require different temporal and peak thresholds for various gait conditions. By utilizing the significant differences in distance and slope, it effectively resolves the issue of detecting steps during stationary periods. Unlike neural network-based gait classifiers, this algorithm does not need to account for multiple gait conditions, thereby simplifying the training process. Experimental results demonstrate that the algorithm achieves an average accuracy of over 99% under mixed indoor walking conditions and over 98% accuracy in long-term outdoor walking conditions.

PLIC-FSR-SYS: System reliability analysis based on parallel learning of influential components with filtered sample region

In practical engineering, system reliability analysis is highly concerned since many structures or products have multiple failure modes. Accordingly, this paper develops an innovative method for system reliability analysis by parallel learning of influential component limit-state functions with filtered sample region (PLIC-FSR-SYS) based on Kriging modeling. Different from the traditional adaptive learning methods that train only one component in each iteration when constructing the surrogate of the composite limit-state function, a new strategy is explored to adaptively identify several important components in one iteration so as to train them simultaneously. In the meanwhile, a filtering formula is explored to determine the fatal region so that the unimportant samples can be removed to further accelerate the training process. Based on the join forces of parallel learning of influential components and avoiding the training at unimportant samples, PLIC-FSR-SYS can achieve a fairly efficient system reliability analysis with multiple failure modes. Finally, four different case studies, including an engineering application to the ultra-voltage on-load tap-changer, are conducted to prove the effectiveness of the proposed method. The results indicate that compared to traditional adaptive learning methods, the proposed method makes a significant efficiency improvement for system reliability analysis with multiple failure modes.

Adaptive position control using backstepping technique for the leader‐follower multiple quadrotor unmanned aerial vehicle formation

SummaryThis article addresses the position control issue of multi‐quadrotor unmanned aerial vehicle (QUAV) formation. Concerning the translational dynamic of a multi‐QUAV system, on the one hand, it is an under‐actuation dynamic; on the other hand, it does not satisfy the matching condition. These features will cause inevitable thorny in the formation position control design. Furthermore, because of the state coupling problem, the formation control of multi‐QUAV system is more challenging and knotty than the control of single QUAV system. To achieve this control, both backstepping technique and neural network (NN) approximation strategy are combined by introducing an intermediary control, where NN is employed to compensate the system uncertainty. However, since the traditional adaptive NN control methods need to train a large number of adaptive parameters for the high approximation accuracy, it will cause the heavy computing burden if traditional adaptive method is used for the QUAV formation control. The proposed adaptive NN strategy in this paper only requires training a scalar adaptive parameter, which is generated from the norm of NN weight vector or matrix, thereby significantly reducing computational burden. Finally, according to Lyapunov stability proof and computer simulation, it is demonstrated that the control tasks can be successfully accomplished.

An improved adaptive position tracking strategy for automatic shift actuator with uncertain parameters

Realizing precise and fast position control of the gear is a challenging issue because of its nonlinearity, parameter uncertainty and external disturbance. Therefore, this paper researches the clutch position control considering the influence because of the factor on the system performance. By virtue of the traditional adaptive control method, an improved strategy based on finite time theory is proposed to further improve the convergence rate as well as the position tracking precision. First, a model of electromechanical clutch actuator system is established by theoretical analysis. Then, an enhanced adaptive controller is designed using finite time idea by introducing power function in the virtual control. And parameter update rate is adopted in the control action. Next, the stability of the control system is proved theoretically. Finally, Matlab simulations and experimental bench test are carried out to exhibit the effectiveness of the presented method. The results show that the satisfactory performance has been achieved with accurate position tracking and fast convergence speed.

Data Adaptive Traceback for Vision-Language Foundation Models in Image Classification

Vision-language foundation models have been incredibly successful in a wide range of downstream computer vision tasks using adaptation methods. However, due to the high cost of obtaining pre-training datasets, pairs with weak image-text correlation in the data exist in large numbers. We call them weak-paired samples. Due to the limitations of these weak-paired samples, the pre-training model are unable to mine all the knowledge from pre-training data. The existing adaptation methods do not consider the missing knowledge, which may lead to crucial task-related knowledge for the downstream tasks being ignored. To address this issue, we propose a new adaptation framework called Data Adaptive Traceback (DAT). Specifically, we utilize a zero-shot-based method to extract the most downstream task-related subset of the pre-training data to enable the downstream tasks. Furthermore, we adopt a pseudo-label-based semi-supervised technique to reuse the pre-training images and a vision-language contrastive learning method to address the confirmation bias issue in semi-supervised learning. We conduct extensive experiments that show our proposed DAT approach meaningfully improves various benchmark datasets’ performance over traditional adaptation methods by simply.

Active transfer learning for audiogram estimation.

Computational audiology (CA) has grown over the last few years with the improvement of computing power and the growth of machine learning (ML) models. There are today several audiogram databases which have been used to improve the accuracy of CA models as well as reduce testing time and diagnostic complexity. However, these CA models have mainly been trained on single populations. This study integrated contextual and prior knowledge from audiogram databases of multiple populations as informative priors to estimate audiograms more precisely using two mechanisms: (1) a mapping function drawn from feature-based homogeneous Transfer Learning (TL) also known as Domain Adaptation (DA) and (2) Active Learning (Uncertainty Sampling) using a stream-based query mechanism. Simulations of the Active Transfer Learning (ATL) model were tested against a traditional adaptive staircase method akin to the Hughson-Westlake (HW) method for the left ear at frequencies kHz, resulting in accuracy and reliability improvements. ATL improved HW tests from a mean of 41.3 sound stimuli presentations and reliability of dB down to dB. Integrating multiple databases also resulted in classifying the audiograms into 18 phenotypes, which means that with increasing data-driven CA, higher precision is achievable, and a possible re-conceptualisation of the notion of phenotype classifications might be required. The study contributes to CA in identifying an ATL mechanism to leverage existing audiogram databases and CA models across different population groups. Further studies can be done for other psychophysical phenomena using ATL.

DRFM Repeater Jamming Suppression Method Based on Joint Range-Angle Sparse Recovery and Beamforming for Distributed Array Radar

Distributed array radar achieves high angular resolution and measurement accuracy, which could provide a solution to suppress digital radio frequency memory (DRFM) repeater jamming. However, owing to the large aperture of a distributed radar, the far-field plane wave assumption is no longer satisfied. Consequently, traditional adaptive beamforming methods cannot work effectively due to mismatched steering vectors. To address this issue, a DRFM repeater jamming suppression method based on joint range-angle sparse recovery and beamforming for distributed array radar is proposed in this paper. First, the steering vectors of the distributed array are reconstructed according to the spherical wave model under near-field conditions. Then, a joint range-angle sparse dictionary is generated using reconstructed steering vectors, and the range-angle position of jamming is estimated using the weighted L1-norm singular value decomposition (W-L1-SVD) algorithm. Finally, beamforming with joint range-angle nulling is implemented based on the linear constrained minimum variance (LCMV) algorithm for jamming suppression. The performance and effectiveness of proposed method is validated by simulations and experiments on an actual ground-based distributed array radar system.

GNSS/accelerometer integrated deformation monitoring algorithm based on sensors adaptive noise modeling

The Global Navigation Satellite System (GNSS) and accelerometer integrated system can obtain more stable and reliable deformation displacement with the full use of the complementary technical characteristics of these two types of sensors. The Kalman Filter (KF) method is often applied to integrate GNSS three-dimensional (3D) coordinates and high-rate accelerometer measurements. The key to obtaining accurate solutions is the reasonable setting of measurement noise and process noise of KF. However, in some complex deformation monitoring scenarios such as landslides, both GNSS and accelerometers are susceptible to interference from factors like vegetation cover and external dynamic disturbance. Traditional adaptive filtering methods is hard to simultaneously and appropriately adjust the two types of noise matrices. To address this problem, an adaptive noise model based on sensors is proposed. The adaptive measurement noise is constructed using the posterior coordinate covariance derived from GNSS-RTK process. The random walk coefficient corresponding to the process noise is estimated online via the standard deviation (STD) of acceleration time-varying information. A series of numerical experiments about simulated three-dimensional (3D) deformation displacement are carried out to validate the proposed algorithm. The results show that: (1) When the GNSS signal is disturbed by complex environment, the adaptive measurement noise model effectively contributes to the accuracy improvement, from decimeter level to centimeter level. (2) In the presence of unstable deformable bodies, the adaptive process noise algorithm significantly suppresses the divergent deformation time series caused by external accelerometer disturbances. (3) Even if suffering the overlying effects of electromagnetic interference and external disturbance, the centimeter-level deformation monitoring accuracy can be achieved by using the joint adaptive measurement and process noise model. The improvement effect is particularly significant in the main deformation direction.

Autonomous Game Control for Spacecraft Rendezvous via Adaptive Perception and Interaction

This article studies the autonomous game control problem for spacecraft rendezvous by using the adaptive perception and interaction. The rendezvous mission involves two spacecraft (named by autonomous spacecraft <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">a</i> , and the other spacecraft <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">o</i> , respectively), in which the control strategy of spacecraft <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">o</i> is determined by only itself and cannot be intervened, but the control law of spacecraft <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">a</i> needs to be designed to achieve the rendezvous under the condition that only the relative position and velocity of spacecraft in the rendezvous system are available. By formulating the rendezvous system as a two-player linear quadratic differential game (DG) with unknown intent of spacecraft <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">o</i> , an autonomous game control method is proposed for spacecraft <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">a</i> by using the adaptive perception and interaction. This game control approach removes the requirement for knowing the intent of spacecraft <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">o</i> , relaxes the persistent excitation condition in traditional adaptive estimation methods, and guarantees the asymptotic stability of the rendezvous system. Furthermore, the intent (i.e., the weighting matrix in the cost function) of spacecraft <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">o</i> is inferred by solving a residual minimization problem. Finally, a simulation study is carried out to verify the effectiveness of the developed autonomous game control strategy.

Composite adaptive online inverse optimal control approach to human behavior learning

There have been broad ranges of human-in-the-loop (HiTL) control systems, like fly-by-wire aircraft, share driving, and energy management. To develop advanced HiTL control systems with augmented intelligence, it is desirable that the machine is empowered to understand how a skilled human operator determines the control actions. It is common to model the human operator as an optimal controller with an unknown weighting matrix which depicts the tradeoff between multiple control objectives. Our aim is thus to learn the weighting matrix of the human objective function using only the system state measurement. Accordingly, for the HiTL system, a composite adaptive inverse optimal control (IOC) approach, which integrates concurrent learning (CL) based composite adaptive estimation and linear matrix inequality (LMI) optimization techniques, is proposed to learn human behavior online. The proposed composite adaptive IOC method consists of two steps: first, a composite adaptive update law is proposed to online estimate the human feedback gain matrix, which removes the persistent excitation condition required by traditional adaptive estimation methods, and then, an LMI optimization problem is solved to retrieve the weighting matrix of the human objective function with the learned feedback gain. The applicability and effectiveness of the proposed method are demonstrated with a steering control simulation.

Chaotic van der Pol Oscillator Control Algorithm Comparison

The damped van der Pol oscillator is a chaotic non-linear system. Small perturbations in initial conditions may result in wildly different trajectories. Controlling, or forcing, the behavior of a van der Pol oscillator is difficult to achieve through traditional adaptive control methods. Connecting two van der Pol oscillators together where the output of one oscillator, the driver, drives the behavior of its partner, the responder, is a proven technique for controlling the van der Pol oscillator. Deterministic artificial intelligence is a feedforward and feedback control method that leverages the known physics of the van der Pol system to learn optimal system parameters for the forcing function. We assessed the performance of deterministic artificial intelligence employing three different online parameter estimation algorithms. Our evaluation criteria include mean absolute error between the target trajectory and the response oscillator trajectory over time. Two algorithms performed better than the benchmark with necessary discussion of the conditions under which they perform best. Recursive least squares with exponential forgetting had the lowest mean absolute error overall, with a 2.46% reduction in error compared to the baseline, feedforward without deterministic artificial intelligence. While least mean squares with normalized gradient adaptation had worse initial error in the first 10% of the simulation, after that point it exhibited consistently lower error. Over the last 90% of the simulation, deterministic artificial intelligence with least mean squares with normalized gradient adaptation achieved a 48.7% reduction in mean absolute error compared to baseline.

Adaptive backstepping position tracking control of quadrotor unmanned aerial vehicle system

&lt;abstract&gt;&lt;p&gt;In this work, an adaptive backstepping position tracking control using neural network (NN) approximation mechanism is proposed with respect to the translational system of quadrotor unmanned aerial vehicle (QUAV). Concerning the translational system of QUAV, on the one hand, it does not satisfy the matching condition and is an under-actuation dynamic system; on the other hand, it is with strong nonlinearity containing some uncertainty. To achieve the control objective, an intermediary control is introduced to handle the under-actuation problem, then the backstepping technique is combined with NN approximation strategy, which is employed to compensate the uncertainty of the system. Compared with traditional adaptive methods, the proposed adaptive NN position control of QUAV can alleviate the computation burden effectively, because it only trains a scalar adaptive parameter instead of the adaptive parameter vector or matrix. Finally, according to Lyapunov stability proof and computer simulation, it is proved that the control tasks can be accomplished.&lt;/p&gt;&lt;/abstract&gt;

Trajectory Optimization for High-Speed and Long-Range Interceptor Based on Improved Adaptive hp Pseudospectral Method

The trajectory optimization design of interceptor is very important in the defense combat against a class of high-speed and strong-maneuvering aircraft. At present, an important idea is to use hp pseudospectral method to offline optimizes the trajectory of interceptor, but the solving efficiency of this method needs to be further improved. Aiming at this issue, an improved adaptive hp pseudospectral method is proposed in this paper. In order to shorten the solving time of the algorithm, the proposed method has two main improvements on the basis of the traditional hp pseudospectral method: on one hand, by judging the positions of the control sudden change points, prerefine the mesh around them according to certain rules. On the other hand, the curvature of the system state curve is used as the criterion to segment the original mesh nonuniformly so that more mesh points can be allocated where the curvature is large. These two points together ensure that the collocation point resources can be used more efficiently in the mesh refinement process. The simulation results show that the proposed method can solve the optimized trajectory of interceptor effectively, and it also proves that this method has higher solving efficiency than the traditional adaptive hp method.

Characterization of the in-focus droplets in shadowgraphy systems via deep learning-based image processing method

It is important to accurately identify and measure in-focus droplets from shadowgraph droplet images that typically contain a large number of defocused droplets for the research of multiphase flow. However, conventional in-focus droplet identification methods are time-consuming and laborious due to the noise and background illumination in experimental data. In this paper, a deep learning-based method called focus-droplet generative adversarial network (FocGAN) is developed to automatically detect and characterize the focused droplets in shadow images. A generative adversarial network framework is adopted by our model to output binarized images containing only in-focus droplets, and inception blocks are used in the generator to enhance the extraction of multi-scale features. To emulate the real shadow images, an algorithm based on the Gauss blur method is developed to generate paired datasets to train the networks. The detailed architecture and performance of the model were investigated and evaluated by both the synthetic data and spray experimental data. The results show that the present learning-based method is far superior to the traditional adaptive threshold method in terms of effective extraction rate and accuracy. The comprehensive performance of FocGAN, including detection accuracy and robustness to noise, is higher than that of the model based on a convolutional neural network. Moreover, the identification results of spray images with different droplet number densities clearly exhibit the feasibility of FocGAN in real experiments. This work indicates that the proposed learning-based approach is promising to be widely applied as an efficient and universal tool for processing particle shadowgraph images.

An adaptive tracking control method for offshore cranes with unknown gravity parameters

The offshore crane system is a typical underactuated system which is installed on the ship and carried out the payload transportation in the offshore environment. The payload transportation for offshore cranes is extremely sensitive to the influence of the ship motion. High couplings also exist between the offshore crane state variables. These factors may lead to large payload swing, and the offshore crane control problem is very difficult. In addition, since some physical parameters of the offshore crane system are difficult to be measured, there usually exist parameter uncertainties, which may lead to positioning errors. In order to tackle the above problems, a new adaptive tracking control method for offshore crane system is proposed, which brings satisfactory tracking performance of the reference trajectories and realizes the control objectives of the payload accurate and fast transportation, the payload swing elimination, and the accurate gravity compensation. Unlike the traditional adaptive control method, an elaborately designed adaptive estimation update law is proposed, which is used to ensure the accurate online estimation for gravity-related parameters. By using Lyapunov stability theory, it is proved that the proposed adaptive tracking controller is effective. Simulations are included to further show the performance of the proposed method.

A Robust Deep Neural Network for Rolling Element Fault Diagnosis under Various Operating and Noisy Conditions

This study proposes a new intelligent diagnostic method for bearing faults in rotating machinery. The method uses a combination of nonlinear mode decomposition based on the improved fast kurtogram, gramian angular field, and convolutional neural network to detect the bearing state of rotating machinery. The nonlinear mode decomposition based on the improved fast kurtogram inherits the advantages of the original algorithm while improving the computational efficiency and signal-to-noise ratio. The gramian angular field can construct a two-dimensional image without destroying the time relationship of the signal. Therefore, the proposed method can perform fault diagnosis on rotating machinery under complex operating conditions. The proposed method is verified on the Paderborn dataset under heavy noise and multiple operating conditions to evaluate its effectiveness. Experimental results show that the proposed model outperforms wavelet denoising and the traditional adaptive decomposition method. The proposed model achieves over 99.6% accuracy in all four operating conditions provided by this dataset, and 93.8% accuracy in a strong noise environment with a signal-to-noise ratio of −4 dB.

Fast Determination of Satellite-to-Moon Visibility Using an Adaptive Interpolation Method Based on Vertex Protection.

Fast determination of satellite visibility with respect to a target area is important for satellite navigation and positioning. In this paper, we propose an adaptive interpolation algorithm based on vertex protection to solve the satellite visibility period problem more accurately and quickly, where “vertex” refers to the local extremum point. The algorithm can avoid the error in the visibility period calculation caused by skimming the vertices when fitting the multi-hump visibility function under certain fitting accuracy requirements with the traditional adaptive interpolation method. The algorithm does not need to construct a cubic polynomial in each subinterval to determine whether the satellite is visible or not; it only constructs a cubic polynomial to solve the problem if the visibility function of that subinterval is judged to have a solution from the existence theorem of zero points, which can improve the computational efficiency. For the lunar navigation problem, a solution to satellite–Moon visibility calculations based on a vertex-protected adaptive interpolation is given, and the experimental results show that the computation time of the algorithm can be reduced by approximately 98% compared with the brute force method and by approximately 30% compared with the traditional adaptive interpolation algorithm.

Statistically robust estimation of source bearing via minimizing the Bhattacharyya distance.

Source bearing estimation is a common technique in acoustic array processing. Many methods have been developed and most of them exploit some underlying statistical model. When applied to a practical system, the robustness to model mismatch is of major concern. Traditional adaptive methods, such as the minimum power distortionless response processor, are notoriously known for their sensitivity to model mismatch. In this paper, a parameter estimator is developed via the minimum Bhattacharyya distance estimator (MBDE), which provides a measure of the divergence between the assumed and true probability distributions and is, thus, capable of statistically matching. Under a Gaussian random signal model typical of source bearing estimation, the MBDE is derived in terms of the data-based and modeled covariance matrices without involving matrix inversion. The performance of the MBDE, regarding the robustness and resolution, is analyzed in comparison with some of the existing methods. A connection with the Weiss-Weinstein bound is also discussed, which gives the MBDE an interpretation of closely approaching a large-error performance bound. Theoretical analysis and simulations of bearing estimation using a uniform linear array show that the proposed method owns a considerable resolution comparable to an adaptive method while being robust against statistical mismatch, including covariance mismatch caused by snapshot deficiency and/or noise model mismatch.