Fast Convergence Research Articles

Adaptive fault-tolerant control of uncertain systems with unknown actuator failures and input delay

Unknown failures and time delays of actuators which may degrade system performance seem inevitable in practical systems. However, the available results to compensate for unknown failures of time delay actuators based on adaptive approaches are very limited. In this paper, we address such a problem by considering controlling a class of second-order systems with unknown actuator failures and input delays. Firstly, the controlled system is transformed into a triangular structure model. Meanwhile, the input time delay is transformed into dynamics of the output signal. Then, an adaptive controller is developed using backstepping. Not only can the uncertainties due to actuator failure be compensated, but the unknown input delay has also been effectively restrained under the proposed control scheme. The upper bound condition of strength scalar [Formula: see text] is proposed. It is a sufficient condition for system stability. When the strength scalar satisfies this condition, the design parameters exist and the system is stable under the controlling of the proposed controller. Finally, the effectiveness of the proposed control scheme is verified through simulation results, including numerical simulation and actual system simulation. Through the comparative simulation, it can be seen that the control scheme proposed in this paper has faster convergence speed.

Learning-based adaptive neural control for safer navigation of unmanned surface vehicle with variable mass

This paper presents a novel approach to the precise control of variable mass unmanned surface vehicles (USVs) during payload deployment, where both mass and draught undergo unpredictable changes. We propose a draught observation method and an adaptive control strategy that leverages the strong coupling between the USV's motion states, mass, and draught. Our method employs a radial basis function neural network (RBF-NN) for real-time draught observation, using an offline training strategy based on gradient descent, combined with an adaptive online training strategy to improve observation accuracy. An adaptive control strategy based on the Backstepping method is then developed, incorporating real-time draught data from the RBF-NN to address unknown variations in mass and draught. The stability of both the RBF-NN observer and the adaptive control algorithm is rigorously verified using the Lyapunov method. Simulation results demonstrate that the proposed draught observation method achieves up to 30% faster convergence compared to traditional methods, with a significant improvement in observation accuracy. Furthermore, the adaptive control strategy effectively manages real-time adjustments in dynamic scenarios, maintaining robust control performance even under significant mass changes, where conventional approaches fail.

The Calibrated Safety Constraints Optimal Power Flow for the Operation of Wind-Integrated Power Systems

As the penetration of renewable energy sources (RESs), particularly wind power, continues to rise, the uncertainty in power systems increases. This challenges traditional optimal power flow (OPF) methods. This paper proposes a Calibrated Safety Constraints Optimal Power Flow (CSCOPF) model that uses the Improved Acceleration Coefficient-Based Bee Swarm algorithm (IACBS) in combination with the equivalent current injection (ECI) model. The proposed method addresses key challenges in wind-integrated power systems by ensuring preventive safety scheduling and enabling effective power incident safety analysis (PISA). This improves system reliability and stability. This method incorporates mixed-integer programming, with continuous and discrete variables representing power outputs and control mechanisms. Detailed numerical simulations were conducted on the IEEE 30-bus test system, and the feasibility of the proposed method was further validated on the IEEE 118-bus test system. The results show that the IACBS algorithm outperforms the existing methods in both computational efficiency and robustness. It achieves lower generation costs and faster convergence times. Additionally, the CSCOPF model effectively prevents power grid disruptions during critical incidents, ensuring that wind farms remain operational within predefined safety limits, even in fault scenarios. These findings suggest that the CSCOPF model provides a reliable solution for optimizing power flow in renewable energy-integrated systems, significantly contributing to grid stability and operational safety.

A proportional fusion adaptation algorithm to reduce noise in sEMG signals of the lower limb

Abstract To address issues related to unknown noise pollution and the inadequate performance of single adaptive noise reduction algorithms in measuring lower limb surface electromyography (sEMG) signals, this paper proposes an algorithm that combines the fast convergence speed and strong noise reduction capability of recursive least-squares (RLS) with the low computational complexity of the normalized least-mean-square (NLMS) and improved proportionate NLMS (IPNLMS). Through the proportional fusion of RLS with NLMS and RLS with IPNLMS, the proposed algorithm greatly improves convergence speed, stability, and noise reduction performance while effectively reducing computational complexity. Moreover, considering the influence of the initial value of weights on the noise reduction performance during the updating process of the adaptive noise reduction algorithm, a weight initial value setting (WIS) module is proposed to optimize the initial value of the weights by the known amount of data. Based on 50 independent experiments, an adaptive noise reduction algorithm and WIS module were used to reduce the unknown noise in the lower limb sEMG signals, which was generated by white Gaussian noise, power line interference, or hybrid noise interfered by an unknown environment. The noise reduction performance was evaluated by using the average value of the signal-to-noise ratio (SNR), the root-mean-square error, and R-square. Compared with the RLS, NLMS, and IPNLMS algorithms for noise reduction of vastus lateralis, rectus femoris, and biceps femoris signals containing unknown noise, the SNR of RLS-NLMS, RLS-IPNLMS, WIS-RLS-NLMS, and WIS-RLS-IPNLMS is improved by an average of [7.92%, 55.54%, 55.63%], [7.45%, 54.90%, 54.99%], [19.70%, 72.38%, 72.71%], [19.32%, 71.84%, 72.19%]. The simulation results verify that the proportional fusion adaptive noise reduction algorithm and the WIS module effectively accelerate the convergence speed, enhance the noise reduction capability, and reduce the computational complexity.

A novel collaborative collision avoidance decision method for multi-ship encounters in complex waterways

With the continuous growth of maritime traffic volume, multi-ship collision avoidance has gradually become one of the most crucial issues in ensuring the safety of ship navigation. This study proposes a multi-ship collaborative collision avoidance decision model (MCCA) to address the issue of multi-ship encounters in complex waterways. The model takes into account the ship spatio-temporal collision risk, relative motion trends, as well as the safety and economic considerations of ship navigation. A comprehensive collision avoidance method is designed based on the velocity obstacle method, enabling simultaneous adjustments both course and speed, with the aim of minimizing economic losses incurred by ships due to avoidance operations while ensuring ship navigation safety. Meanwhile, the NSGA-II algorithm, which has faster convergence and better effect, is used to calculate the optimal collaborative collision avoidance decision of multiple ships. Besides, both simulation and example validation are used to test the validity of the model. The results indicate that the proposed model can effectively achieve multi-ship collaborative collision avoidance in the region. Simultaneously, it holds significant reference value for guaranteeing the safety of ship navigation, enhancing supervision efficiency, and promoting the development of intelligent ship navigation systems.

Data Quality-Aware Client Selection in Heterogeneous Federated Learning

Federated Learning (FL) enables decentralized data utilization while maintaining edge user privacy, but it faces challenges due to statistical heterogeneity. Existing approaches address client drift and data heterogeneity issues. However, real-world settings often involve low-quality data with noisy features, such as covariate drift or adversarial samples, which are usually ignored. Noisy samples significantly impact the global model’s accuracy and convergence rate. Assessing data quality and selectively aggregating updates from high-quality clients is crucial, but dynamically perceiving data quality without additional computations or data exchanges is challenging. In this paper, we introduce the FedDQA (Federated learning via Data Quality-Aware) (FedDQA) framework. We discover increased data noise leads to slower loss reduction during local model training. We propose a loss sharpness-based Data-Quality-Awareness (DQA) metric to differentiate between high-quality and low-quality data. Based on the DQA, we design a client selection algorithm that strategically selects participant clients to reduce the negative impact of noisy clients. Experiment results indicate that FedDQA significantly outperforms the baselines. Notably, it achieves up to a 4% increase in global model accuracy and demonstrates faster convergence rates.

Sample efficient nonparametric regression via low-rank regularization

Nonparametric regression suffers from curse of dimensionality, requiring a relatively large sample size for accurate estimation beyond the univariate case. In this paper, we consider a simple method of dimension reduction in nonparametric regression via series estimation, based on the concept of low-rankness which was previously studied in parametric multivariate reduced-rank regression and matrix regression. For d > 2 , the low-rank assumption is realized via tensor regression. We establish a faster convergence rate of the estimator in the (approximate) low-rank case. Limitations of the model are also discussed. Through simulation studies and real data analysis, we compare the estimation accuracy of the proposed method with that of existing approaches. The results demonstrate that the proposed method yields estimates with lower RMSE compared to existing methods.

Rolling bearing fault diagnosis based on optimized A-BiLSTM

In order to improve the efficiency of hyperparameter setting and its adaptability to the model, and to reduce the high cost and low efficiency of manually setting model parameters, a rolling bearing fault diagnosis method based on Honey Badger Algorithm (HBA) optimized attention bidirectional long short-term memory network (HBA-A-BiLSTM) is proposed. Firstly, the optimal hyperparameter combination of A-BiLSTM model is searched by HBA, and then the fault diagnosis performance of A-BiLSTM model under the optimal hyperparameter is tested. Finally, the generalization ability of the model is tested based on data sets under different working conditions. The fault diagnosis effect of the proposed method is verified by using CWRU data set, and the diagnosis accuracy and confusion matrix are used for evaluation. The experimental results show that compared with other swarm intelligence optimization algorithms, the Honey Badger algorithm has good global search performance and fast convergence speed. The fault diagnosis accuracy of the optimized final model reaches 99.5%, which has good effects. It can also achieve stable and accurate fault diagnosis performance under different working conditions and has strong generalization ability.

Grain storage temperature prediction based on chaos and enhanced RBF neural network

Grain storage has very strict temperature requirements. Aiming at the problems of nonlinear characteristics and poor prediction accuracy of temperature parameters in grain storage, a combination of chaos theory and enhanced radial basis neural network is proposed as a temperature prediction model for grain storage (C-ERBF). The model first determines the embedding dimension and time delay of the grain storage temperature sequence using chaos theory. It then calculates the Lyapunov exponent to confirm its chaotic properties and reconstructs the sequence in the phase space to extract the hidden dynamic information and structure behind the sequence. Furthermore, the q-Normalized Least Mean Square Fourth (qXE-NLMF) algorithm is designed to enhance the radial basis function (RBF) neural network model for weight updating, to improve its prediction accuracy, and to accelerate the training speed of the model. As verified by the simulation experiments of Mackey–Glass chaotic time series prediction, the enhanced RBF (ERBF) network has faster convergence speed and lower steady-state error compared to the traditional RBF network. Finally, the optimized dataset from chaos theory is input into the model to achieve accurate predictions of grain storage temperature series. The experimental results show that the proposed C-ERBF model has higher prediction accuracy compared to other time series prediction methods. It can realize the grain pile temperature in advance, and take control measures in advance. This proactive approach significantly reduces the consumption of stored grain and prevents issues before they arise.

Analysis of Fractional Order-Adaptive Systems Represented by Error Model 1 Using a Fractional-Order Gradient Approach

In adaptive control, error models use system output error and adaptive laws to update controller parameters for control or identification tasks. Fractional-order calculus, involving non-integer-order derivatives and integrals, is increasingly important for modeling, estimation, and control due to its ability to generalize classical methods and offer improved robustness to disturbances. This paper addresses the gap in the literature where fractional-order gradient methods have not yet been extensively applied in identification and adaptive control schemes. We introduce a fractional-order error model with fractional-order gradient (FOEM1-FG), which integrates fractional gradient operators based on the Caputo fractional derivative. By using theoretical analysis and simulations, we confirm that FOEM1-FG maintains stability and ensures bounded output errors across a variety of input signals. Notably, the fractional gradient’s performance improves as the order, β, increases with β>1, leading to faster convergence. Compared to existing integer-order methods, the proposed approach provides a more flexible and efficient solution in adaptive identification and control schemes. Our results show that FOEM1-FG offers superior stability and convergence characteristics, contributing new insights to the field of fractional calculus in adaptive systems.

Developing a Container Ship Loading-Planning Program Using Reinforcement Learning

This study presents an optimized container-stowage plan using reinforcement learning to tackle the complex logistical challenges in maritime shipping. Traditional stowage-planning methods often rely on manual processes that account for factors like container weight, unloading order, and balance, which results in significant time and resource consumption. To address these inefficiencies, we developed a two-phase stowage plan: Phase 1 involves bay selection using a Proximal Policy Optimization (PPO) algorithm, while Phase 2 focuses on row and tier placement. The proposed model was evaluated against traditional methods, demonstrating that the PPO algorithm provides more efficient loading plans with faster convergence compared to Deep Q-Learning (DQN). Additionally, the model successfully minimized rehandling and maintained an even distribution of weight across the vessel, ensuring operational safety and stability. This approach shows great potential for enhancing stowage efficiency and can be applied to real-world shipping scenarios, improving productivity. Future work will aim to incorporate additional factors, such as container size, type, and cargo fragility, to further improve the robustness and adaptability of the stowage-planning system. By integrating these additional considerations, the system will become even more capable of handling the complexities of modern maritime logistics.

Advanced Optimization Techniques for Federated Learning on Non-IID Data

Federated learning enables model training on multiple clients locally, without the need to transfer their data to a central server, thus ensuring data privacy. In this paper, we investigate the impact of Non-Independent and Identically Distributed (non-IID) data on the performance of federated training, where we find a reduction in accuracy of up to 29% for neural networks trained in environments with skewed non-IID data. Two optimization strategies are presented to address this issue. The first strategy focuses on applying a cyclical learning rate to determine the learning rate during federated training, while the second strategy develops a sharing and pre-training method on augmented data in order to improve the efficiency of the algorithm in the case of non-IID data. By combining these two methods, experiments show that the accuracy on the CIFAR-10 dataset increased by about 36% while achieving faster convergence by reducing the number of required communication rounds by 5.33 times. The proposed techniques lead to improved accuracy and faster model convergence, thus representing a significant advance in the field of federated learning and facilitating its application to real-world scenarios.

Multi-UAVs task allocation method based on MPSO-SA-DQN

Multi-UAVs play an important role in the battlefield. Although many methods are proposed to solve the Multi-UAV task allocation, there still existing the problems of complex time constraints and uncertain solution space. The reason is that multi-UAVs usually face changing environmental factors. Aiming at solving such problem, this paper proposes a multi-UAV task assignment method based on Deep Q-based evolutionary reinforcement learning algorithms (MPSO-SA-DQN). Specifically, this method builds a multi-agent training framework based on the deep evolutionary reinforcement learning mechanism and SA-DQN. Its aim is to improve the global exploration and optimization capabilities of multi-agents. At the same time, the multi-dimensional particle swarm optimization algorithm is introduced to optimize the state space. Based on task priority mapping, the MPSO-SA-DQN algorithm framework is proposed. As a result, multi-agents can optimize the execution state in real time in the environment interaction. Besides, it also has the ability to reach optimal state and maximum reward. According to the characteristics of multi-UAV global task assignment, this paper designs a priority state space autoencoder strategy and global task feature. A multi-UAVs tasks allocation and iterative optimization method based on MPSO-SA-DQN algorithm is proposed, so as to continuously optimize the task allocation scheme. The simulation results show that the multi-UAV task allocation method based on MPSO-SA-DQN can effectively solve the problem of uncertainty in the optimal solution space of task allocation. At the same time, the algorithm achieves faster convergence result, and a good prospect of promotion in the field of UAV swarm cooperative task planning.

A Hybrid Prediction Model for Short-Term Load Forecasting in Power Systems

Short-term load forecasting (STLF) plays a vital role in effective power system management by assisting power dispatch centers in developing generation plans and ensuring smooth system operation. This study introduces a novel hybrid prediction model called iSSA-LSSVM to tackle the STLF challenge. By integrating the Salp Swarm Algorithm (SSA) with Least Squares Support Vector Machines (LSSVM), the iSSA-LSSVM model significantly improves LSSVM's prediction accuracy. One of the key contributions is the model's ability to autonomously ne-tune LSSVM hyperparameters, eliminating the need for manual adjustments and optimizing performance. Modifying the SSA within iSSA-LSSVM enhances the original algorithm's exploration and exploitation capabilities, ensuring better search efficiency and precision. Using a dataset with four independent variables as input and electrical power output as the target variable, the model demonstrates superior predictive performance. Comparative analysis with three other models shows that iSSA-LSSVM achieves a lower Mean Square Error (MSE) and faster convergence. This improvement in accuracy and efficiency enhances STLF, allowing power dispatch centers to develop more precise generation plans and ensure more reliable power system operation.

A distributed end-to-end fair bandwidth allocation algorithm for multi-path networks

Multi-path transmission significantly improves network performance, yet it complicates the problem of fair resource allocation. While traditional fair bandwidth allocation schemes thrive in single-path settings, they often falter when applied to multi-path environments, highlighting the challenge of achieving fair bandwidth sharing in such networks. To tackle this issue, the concept of "max-min similarity" of queuing delays has been introduced based on insight into the intrinsic interactions between queuing packets, delays, and bandwidth allocation, which leads to a formal definition of max-min fair bandwidth allocation for multi-path environments. Theoretical analysis shows that the max-min similarity of queuing delays is a sufficient condition for max-min fair bandwidth allocation in single bottleneck environments. A novel distributed end-to-end fair bandwidth allocation algorithm, named DMFBA, is then proposed, which separates the control into flow-level and transmission path-level. In achieving max-min similarity in queuing delays by dynamically adjusting the distribution of flows’ queuing packet quotas across paths it achieves the goal of max-min fair bandwidth allocation. Two sets of numerical simulation experiments were conducted and the results show that DMFBA has less overhead and faster convergence than the traditional utility fair algorithms.

A virtual scene reconstruction algorithm for 3D digital images based on machine learning

In order to obtain a better quality image of virtual scene reconstruction of three-dimensional digital image, a virtual scene reconstruction algorithm of three-dimensional digital image based on machine learning is proposed. Firstly, the state information and presentation instructions of the scene are analyzed to obtain the distribution position of the vertices of the mesh model of the image reconstruction. The global image is approximately calculated by the local coordinate method, and the local details are corrected to complete the rendering of the three-dimensional digital image. Then, the space and scale are used as feature points to build a window detection template on the image, and the classifier is applied to suppress discrete feature points and remove redundant features. Finally, the smoothed three-dimensional coordinates are obtained according to the fitting function method to reconstruct the three-dimensional surface, and the local two-dimensional triangle is segmented and mapped to the three-dimensional space to realize the reconstruction of the virtual scene of the three-dimensional digital image. The experimental results show that the algorithm has a fast convergence speed, the reconstructed image details and edge contours are complete, and the overall effect is good.

Towards value-sensitive and poisoning-proof model aggregation for federated learning on heterogeneous data

Federated Learning (FL) enables collaborative model training without sharing data, but traditional static averaging of local updates leads to poor performance on heterogeneous data. The following remedies, either by scheduling data distribution or mitigating local discrepancies, predominately fail to handle fine-grained heterogeneity (e.g., local imbalanced labels). To commence, we reveal that static averaging leads to the global model suffering from the mean fallacy. That is, the averaging process favors the local model with large parameters numerically rather than knowledge. To tackle this, we introduce FedVSA, a simple-yet-effective model aggregation framework sensitive to heterogeneous local data merits. Specifically, we invent a new global loss function for FL by prioritizing the valuable local updates, facilitating efficient convergence. We deduce a softmax-based aggregation rule and prove its convergence property via rigorous theoretical analysis. Additionally, we expose poisoning threats of model replacement that utilize the mean fallacy for attacks. To mitigate this threat, we propose a two-step mechanism involving auditing historic local training statistics and analyzing the Shapley Value. Through extensive experiments, we show that FedVSA achieves faster convergence (~1.52×) and higher accuracy (~1.6%) compared to the baselines. It also effectively mitigates poisoning attacks by agilely recovering and returning to normal aggregation.

Topology optimization based on the improved high-order RAMP interpolation model and bending properties research for curved square honeycomb sandwich structures

Curved honeycomb sandwich structures with larger surface areas effectively reduce the number of fasteners and connectors, resulting in weight reduction, cost savings, and reliability improvement. Square honeycombs exhibit higher in-plane tensile strength, and are more compatible with mechanical components. Topology optimization can realize the variable-density design of square honeycombs, enhancing the strength and stiffness of curved sandwich structures, but the high-order Rational Approximation of Material Properties (RAMP) interpolation model with a fast convergence rate has the relatively poor clarity and stability in topology boundaries. Hence, a variable-density topology optimization method based on the improved high-order RAMP model is developed for curved square honeycomb sandwich structures. The high-order RAMP interpolation model is improved by incorporating a minimum modulus term into the material interpolation function and employing the Bi-directional Evolutionary Structural Optimization (BESO) to refine the Optimality Criteria (OC) method. A functional relationship between the wall thickness of cross-shaped cells (i.e., simplified models of four adjacent square cells arranged in a cross) and the relative density of topology units is constructed using a density mapping method, and the topology optimization with the relative density of cross-shaped cells as the design variable is performed to minimize the compliance of the core. Three-point bending tests are conducted on 3D printed non-optimized and optimized curved honeycomb sandwich structures with different core material retention rates and panel thicknesses, and the experimental results are compared with those of simulations to explore the bending properties and failure behaviors. The results indicate that the modified high-order RAMP interpolation model enhances the clarity and stability of topology structures, the variable-density topology optimization significantly improves the bending properties of curved square honeycomb sandwich structures, and the experimental and numerical results are largely consistent.

Implementation of a low-cost current perturbation-based improved PO MPPT approach using Arduino board for photovoltaic systems

In photovoltaic (PV) systems, the conversion of solar energy into electrical energy by the PV module is influenced by various factors, including sunlight intensity and temperature. To achieve optimal performance, it is crucial to accurately track the maximum power point (MPP) of the PV module. Among the numerous MPP tracking (MPPT) techniques that have been developed, the perturbation and observation (PO) method has gained significant attention due to its simplicity and reliability. However, the fixed perturbation step size used in the traditional PO algorithm can result in poor tracking capability, excessive ripple, and drift, leading to high power loss and low tracking efficiency. To address these limitations, this paper proposes an improved version of the PO strategy that introduces an adaptable step-magnitude mechanism, utilizing current perturbation instead of the voltage perturbation typically employed in the classical PO method. This enhanced indirect PO approach maintains low complexity and can be easily implemented on a cost-effective Arduino Uno board. A streamlined C++ code integrates the improved PO MPPT strategy with a Proportional Integral Derivative (PID) controller, eliminating the need for separate PID blocks and further reducing system complexity. To evaluate the effectiveness of the proposed technique, comparative analyses are conducted against the traditional PO algorithm, particle swarm optimization (PSO), fuzzy logic control (FLC), and a recently introduced approach, the zone voltage (ZV) method. Simulation results using Proteus software demonstrate that the improved PO approach outperforms the other techniques in various aspects, including achieving the highest static and dynamic tracking efficiencies of 99.38% and 99.88%, respectively, negligible power loss and fluctuations, the fastest convergence speed, and the shortest tracking time of 0.19 seconds.

An analysis and solution of ill-conditioning in physics-informed neural networks

Physics-informed neural networks (PINNs) have recently emerged as a novel and popular approach for solving forward and inverse problems involving partial differential equations (PDEs). However, ensuring stable training and obtaining accurate results remain challenging in many scenarios, often attributed to the ill-conditioning of PINNs. Despite this, a deeper analysis is still lacking, which hampers progress and application of PINNs in complex engineering problems. Drawing inspiration from the ill-conditioning analysis in traditional numerical methods, we establish a strong connection between the ill-conditioning of PINNs and the Jacobian matrix of the PDE system. Specifically, for any given PDE system, we construct a controlled system that allows for the adjustment of the Jacobian matrix's condition number while retaining the same solution as the original system. Our numerical experiments show that as the condition number of the Jacobian matrix decreases, PINNs exhibit faster convergence and higher accuracy. Building upon this principle and the extension of controlled systems, we propose a general approach to mitigate the ill-conditioning in PINNs, leading to successful simulations of three-dimensional flow around the M6 wing at a Reynolds number of 5,000. To the best of our knowledge, this is the first time that PINNs have successfully simulated such complex systems, offering a promising new technique for addressing industrial complexity problems. Our findings also provide valuable insights to guide the future development of PINNs.