Parameter Adjustment Mechanism Research Articles

An Improved BGE-Adam Optimization Algorithm Based on Entropy Weighting and Adaptive Gradient Strategy

This paper introduces an enhanced variant of the Adam optimizer—the BGE-Adam optimization algorithm—that integrates three innovative technologies to augment the adaptability, convergence, and robustness of the original algorithm under various training conditions. Firstly, the BGE-Adam algorithm incorporates a dynamic β parameter adjustment mechanism that utilizes the rate of gradient variations to dynamically adjust the exponential decay rates of the first and second moment estimates (β1 and β2), the adjustment of β1 and β2 is symmetrical, which means that the rules that the algorithm considers when adjusting β1 and β2 are the same. This design helps to maintain the consistency and balance of the algorithm, allowing the optimization algorithm to adaptively capture the trending movements of gradients. Secondly, it estimates the direction of future gradients by a simple gradient prediction model, combining historic gradient information with the current gradient. Lastly, entropy weighting is integrated into the gradient update step. This strategy enhances the model’s exploratory nature by introducing a certain amount of noise, thereby improving its adaptability to complex loss surfaces. Experimental results on classical datasets, MNIST and CIFAR10, and gastrointestinal disease medical datasets demonstrate that the BGE-Adam algorithm has improved convergence and generalization capabilities. In particular, on the specific medical image gastrointestinal disease test dataset, the BGE-Adam optimization algorithm achieved an accuracy of 69.36%, a significant improvement over the 67.66% accuracy attained using the standard Adam algorithm; on the CIFAR10 test dataset, the accuracy of the BGE-Adam algorithm reached 71.4%, which is higher than the 70.65% accuracy of the Adam optimization algorithm; and on the MNIST dataset, the BGE-Adam algorithm’s accuracy was 99.34%, surpassing the Adam optimization algorithm’s accuracy of 99.23%. The BGE-Adam optimization algorithm exhibits better convergence and robustness. This research not only demonstrates the effectiveness of the combination of these three technologies but also provides new perspectives for the future development of deep learning optimization algorithms.

Speed Tracking and Anti-Slip Control for Heavy Freight Trains Considering the Conicity of the Wheel

To ensure the safe and punctual transportation of freight trains, it is crucial for the train to travel at the targeted speed on the track. This paper proposes a scheme for speed tracking and anti-slip control for freight trains. The speed tracking is implemented through predictive auto disturbance rejection control (PADRC), which includes a flexible Smith estimation module capable of accurately predicting the output of large time delay systems, such as freight trains. The key to anti-slip control relies on the precise observation of the radial velocity and slip rate. Therefore, an unscented Kalman filter observer is designed in this article, incorporating an adaptive parameter adjustment mechanism to enhance observation accuracy. The anti-slip parameters obtained from this observer can then be used to determine the anti-slip control scheme. The effectiveness of this scheme is demonstrated through simulations of the HXD1 electric traction locomotive’s driving process, using line data from the Geku line section in China. Compared to conventional active disturbance rejection control, PADRC reduces speed fluctuation by 55%, and freight trains under anti-slip control decrease the slip speed by 90%.

A Multi-Dimensional Node Importance Evaluation Method Based on Graph Convolutional Networks

This paper addresses the problem of identifying, evaluating, and ranking key nodes in complex networks by introducing a novel Multi-Parameter Control Graph Convolutional Network (MPC-GCN) for assessing node importance. Drawing inspiration from the multidimensional and hierarchical interactions between nodes in physical systems, this approach integrates the automatic feature learning capabilities of Graph Convolutional Networks (GCNs) with a comprehensive analysis of nodes’ intrinsic properties, their interactions with neighbors, and their roles within the broader network. The MPC-GCN model offers an innovative framework for key node identification, leveraging GCNs to iteratively aggregate node and neighbor features across layers. This process captures and combines local, global, and positional characteristics, enabling a more nuanced, multidimensional assessment of node importance. Moreover, the model incorporates a flexible parameter adjustment mechanism, allowing the relative weights of different dimensions to be tuned, thereby adapting the evaluation process to various network structures. To validate the model’s effectiveness, we first tested the influence of model parameters on randomly generated small networks. We then conducted extensive simulations on eight large-scale networks using the Susceptible-Infected-Recovered (SIR) model. Evaluation metrics, including the M(R) score, Kendall’s tau correlation, the proportion of infected nodes, and the relative size of the largest connected component, were used to assess the model’s performance. The results demonstrate that MPC-GCN outperforms existing methods in terms of monotonicity, accuracy, applicability, and robustness, providing more precise differentiation of node importance. By addressing the limitations of current methods—such as their reliance on single-dimensional perspectives and lack of adaptability—MPC-GCN offers a more comprehensive and flexible approach to node importance evaluation. This method significantly improves the breadth and applicability of node ranking in complex networks.

Edge Collaborative Compressed Sensing in Wireless Sensor Networks for Mechanical Vibration Monitoring

This paper proposes a novel edge collaborative compressed sensing for mechanical vibration monitoring (MVM) to address the severe shortage of storage and computational resources and long delay in transmitting massive vibration data in wireless sensor networks (WSN) for MVM. It first combines compressed sensing (CS) and edge computing (EC) into a WSN to effectively solve the above problems. Based on the self-developed acquisition node (AN) and edge computing node (ECN), the proposed approach is implemented in the AN and ECN respectively. This enhances the acquisition efficiency and computing capacity of the WSN. Meanwhile, the sparse pattern of a mechanical fault signal is analyzed. In addition, the adaptive parameter adjustment mechanism (APA) for the alternating direction of multiplier method based on Anderson acceleration is proposed to generate a convex optimization algorithm with fast convergence to realize data reconstruction in the ECN. The results of comprehensive experiments demonstrate that the proposed method can reduce the transmission data by 70%, while maintaining high-precision bearing fault feature detection, compared with the Shannon sampling theory. Furthermore, the acquisition and transmission efficiencies are improved significantly. This provides a potential solution for practical engineering applications.

Study on Adaptive Parameter Internal Mode Control Method for Argon–Oxygen Refining Ferrochrome Alloy

In order to determine a way to be able to shorten the smelting time of low-carbon ferrochrome alloys and to strengthen the temperature control capability of the AOD converter during the smelting process, this article establishes a mechanism model of the rate of oxygen supply and carbon content change in the smelting process as well as the temperature of the reaction fluid in the converter. The physical and chemical reactions of the smelting process and the actual smelting data are used as the basis. The temperature and carbon content in the smelting converter are considered as the output quantity and the rate of oxygen supply is considered as the input quantity. An expert internal model control framework is built. In addition, an adaptive parameter adjustment mechanism is added to the control framework, taking into account data such as the maximum gas supply rate and the maximum limiting temperature of the actual production process. This method improves the smelting speed and smelting accuracy compared to the general internal mode control method. Finally, according to this method, with the use of the built low-carbon ferrochrome alloy centralized control system for smelting, the system shortens the smelting time by 12.79% compared with the general method and controls the converter temperature below 1950 K, which achieves the expected goal according to the simulation and actual smelting results.

Study on adaptive parameter internal mode control method for argon-oxygen refining ferrochrome alloy

To enhance the rate of argon–oxygen refining of ferroalloys, this article is based on the physical and chemical reactions of the smelting process as well as the actual smelting data. A mechanistic model of the rate of change of oxygen supply and carbon content in the smelting process and the temperature of the reaction fluid in the furnace is established. An expert internal model control framework with furnace temperature and carbon content as output and oxygen supply rate as input is constructed. An adaptive parameter adjustment mechanism is added to the control framework by combining data on the maximum gas supply rate and temperature threshold of the stage in the actual production process. The method improves smelting speed and smelting accuracy compared to the general method. It is also able to adjust the furnace temperature according to the actual smelting situation. The actual smelting was carried out according to this method, the improved method reduced the smelting time by 12.79% compared to the general method, and the furnace temperature was controlled below 1950 K.

Biomedical extractive question answering based on dynamic routing and answer voting

Many existing biomedical extractive question answering methods are based on pre-trained models, which do not take full advantage of the hidden layer knowledge of pretrained models and do not consider span overlap between answers when predicting. To address these issues, we propose a new question answering model, called ALBERT with Dynamic Routing and Answer Voting (ADRAV). The ADRAV can reasonably utilize hidden layer knowledge through dynamic routing, and consider span similarity between answers through answer voting. To improve the performance of the model, we also carry out pre-fine-tuning, and add a dynamic parameter adjustment mechanism in the process of pre-fine-tuning. Experimental results show that our model achieves significant performance improvement with fewer parameters on BioASQ 4b, 5b, 6b, 9b, and outperforms SOTA baselines on BioASQ 4b, 6b.

Adaptive multiple selection strategy for multi-objective particle swarm optimization

Multiple-swarm approach is a quite successful evolutionary computation framework for multi-objective particle swarm optimization algorithm (MOPSO) to solve multi-objective optimization problems (MOPs). However, the main challenge of using this framework lies in the lack of leader selection, resulting in the optimal solutions being distributed loosely, as well as far away from the true Pareto-optimal front. To overcome this problem, a multi-swarm MOPSO with an adaptive multiple selection strategy (MOPSO-AMS) is investigated in this paper. This proposed MOPSO-AMS is able to guide each swarm with a suitable leader to improve the evolutionary performance. The novelties and advantages of MOPSO-AMS include the following three aspects. First, a hierarchical evolutionary state detection mechanism, based on the distribution and dominance information of non-dominated solutions, is designed to obtain the evolutionary state of current iteration. Then, the requirements of evolutionary process can be detected. Second, an adaptive multiple selection strategy, using the evolutionary state information and spatial features of candidate solutions, is developed to select leaders of sub-swarms in multiple evolutionary states. Then, suitable leaders can be selected to keep the balance between convergence and diversity. Third, an adaptive parameter adjustment mechanism, based on the dominance relationship of each particle, is introduced to further improve the evolutionary performance of MOPSO-AMS. Finally, numerical simulations and a practical application are used to validate the analytical results and demonstrate the significant improvement of MOPSO-AMS.

Risk Assessment of User Aggregators in Demand Bidding Markets

This paper mainly discusses the demand bidding and risk management of user aggregators by considering profit and risk. The covariance matrix of demand price was used to analyze the risk model under an uncertain demand price. By considering revenue and cost, the demand bidding strategy of user aggregators was derived to obtain the maximum profit. By using a risk-tolerance parameter β, a new demand bidding model for the user aggregators that takes both risk and profit into consideration was formulated. We simulated the risk posed by fluctuating demand prices for user aggregators using this model. Finally, this paper proposes Feasible Particle Swarm Optimization (FPSO) to solve the demand bidding model of user aggregators. Through the dynamic adjustment of control factor parameters in the FPSO, we changed the behavioral characteristics of various types of particles, improved the search efficiency and stability of particles in high-dimensional space, and sought the optimal solution for the system as a whole. This paper provides a parameter adjustment mechanism, improves the capability of algorithm implementation, and increases the probability of finding the optimal solution. The simulation results suggest that a tradeoff between profit and risk needs to be considered in the search process. By doing so, enterprises’ abilities in terms of operation and management control can be enhanced, and effective demand management can be achieved.

Parameter adaptation-based ant colony optimization with dynamic hybrid mechanism

In this paper, a parameter adaptation-based ant colony optimization (ACO) algorithm based on particle swarm optimization (PSO) algorithm with the global optimization ability, fuzzy system with the fuzzy reasoning ability and 3-Opt algorithm with local search ability, namely PF3SACO is proposed to improve the optimization ability and convergence, avoid to fall into local optimum. In the PF3SACO, a new dynamic parameter adjustment mechanism by the PSO and the fuzzy system is designed to adaptively adjust the pheromone importance factor α, pheromone volatilization coefficient ρ and the heuristic function importance factor β to accelerate the convergence, improve the search ability, enhance the local search ability and avoid premature. This is achievable by parameter adaptation to reflect the dynamic search characteristic by exploring and exploiting in the search process for the parameter values to be close to the optimal values. In addition, 3-Opt algorithm is applied to optimize the generated path to eliminate the cross path, obtain the optimal path and avoid to fall into local optimum. The optimization performance of the PF3SACO is investigated on fifteen travelling salesman problems (TSPs) with the scales from 42 to 783 cities. The experiment results show that the PF3SACO has better optimization performance by comparing with ABC, NACO, HYBRID, ACO-3Opt, PACO-3Opt, PSO-ACO-3Opt and some other well-known algorithms in most TSP in term of the solution quality, robustness and space distribution. It provides a reference to solve the large-scale TSP for obtaining better path length.

Multi-Objective Dynamic Economic Emission Dispatch with Electric Vehicle–Wind Power Interaction Based on a Self-Adaptive Multiple-Learning Harmony-Search Algorithm

Dynamic economic emission dispatch (DEED) in combination with renewable energy has recently attracted much attention. However, when wind power is considered in DEED, due to its generation uncertainty, some additional costs will be introduced and the stability of the dispatch system will be affected. To address this problem, in this paper, the energy-storage characteristic of electric vehicles (EVs) is utilized to smooth the uncertainty of wind power and reduce its impact on the system. As a result, an interaction model between wind power and EV (IWEv) is proposed to effectively reduce the impact of wind power uncertainty. Further, a DEED model based on the IWEv system (DEEDIWEv) is proposed. For solving the complex model, a self-adaptive multiple-learning multi-objective harmony-search algorithm is proposed. Both elite-learning and experience-learning operators are introduced into the algorithm to enhance its learning ability. Meanwhile, a self-adaptive parameter adjustment mechanism is proposed to adaptively select the two operators to improve search efficiency. Experimental results demonstrate the effectiveness of the proposed model and the superiority of the proposed method in solving the DEEDIWEv model.

A C[formula omitted]-dominance-based solution estimation evolutionary algorithm for many-objective optimization

Balancing convergence and diversity is a key issue for many-objective optimization problems (MaOPs), which is a great challenge to the classical Pareto-based multi-objective algorithms due to its severe lack of selection pressure. To relieve the above challenge, a Cα-dominance-based solution estimation evolutionary algorithm is proposed for MaOPs. In the proposed algorithm, a new dominance method, called Cα-dominance, is proposed to provide reasonable selection pressure for MaOPs. By designing a nonlinear function to transform the original objectives, Cα-dominance expands the dominated area where dominance resistant solutions located, while remains the solutions to be non-dominated in area close to Pareto optimal solutions. Furthermore, an adaptive parameter adjustment mechanism on the unique parameter α of Cα-dominance is designed to control the expansion degree of the dominance area based on the number of objectives and the stages of evolution. Finally, a new solution estimation scheme based on Cα-dominance is designed to evaluate the quality of each solution, which incorporates convergence information and diversity information of each solution. The experimental results on widely used benchmark problems having 5–20 objectives have shown the proposed algorithm is more effective in terms of both convergence enhancement and diversity maintenance.

On Online Adaptive Direct Data Driven Control

Based on our recent contributions on direct data driven control scheme, this paper continues to do some new research on direct data driven control, paving another way for latter future work on advanced control theory. Firstly, adaptive idea is combined with direct data driven control, one parameter adjustment mechanism is constructed to design the parameterized controller online. Secondly, to show the input-output property for the considered closed loop system, passive analysis is studied to be similar with stability. Thirdly, to validate whether the designed controller is better or not, another safety controller modular is added to achieve the designed or expected control input with the essence of model predictive control. Finally, one simulation example confirms our proposed theories. More generally, this paper studies not only the controller design and passive analysis, but also some online algorithm, such as recursive parameter identification and online subgradient descent algorithm. Furthermore, safety controller modular is firstly introduced in direct data driven control scheme.

Path planning of surgical needle: A new adaptive intelligent particle swarm optimization method

Percutaneous puncture interventional therapy is an important method for pathological examination, local anesthesia, and local drug delivery in modern clinics. Due to the existence of complex obstacles such as nerves, arteries, bones and so on in the puncture path, it is a challenging work to design the optimal path for surgical needle. In this paper, we propose a new path planning method based on the adaptive intelligent particle swarm optimization (PSO) algorithm with parameter adjustment mechanism. First, force and motion analysis are carried out on the bevel-tip flexible needle after piercing into human tissues, the motion model of the needle and the spatial transformation model of puncture route in three-dimensional space are obtained, respectively. Then, a multi-objective function is established, which includes puncture path length function, puncture error function and collision detection function. Finally, the optimal puncture path is obtained based on the adaptive intelligent PSO algorithm. The simulation results show that the newly proposed path planning method has higher efficiency, better adaptability to complex environments and higher accuracy than other path planning methods in literature.

Adaptive iterative correlation tuning for closed loop system with two parametrised controllers

In this paper, we study the problem of controller design for one closed loop system with feedforward controller and feedback controller simultaneously. After parametrised these two controllers by two unknown parameter vectors, iterative correlation tuning control is proposed to design these unknown controller parameters through one process of finding roots with respect to one correlation function. As no identification process is needed for the unknown plant in iterative correlation tuning control, the unknown controller parameters are identified by using only input–output measured data. Through applying the adaptive idea to guarantee iterative parameter estimators converge to their true values, MIT rule is regarded as a gradient scheme for the constructed correlation in the parameter adjustment mechanism. Further, Lyapunov stability is applied to derive one parameter adjustment law satisfying the stability for the whole adaptive system. From the point of adaptive analysis, some new results about the sensitivity functions are derived for three types of disturbances to consider tracking and regulation with independent object. Generally, iterative correlation tuning control can design controllers directly without any knowledge about the unknown plant and adjust the unknown controller parameters adaptively through one established parameter adjustment mechanism. Finally two simulation examples are performed to demonstrate the effectiveness of the theories.

A vectorized bimodal distribution based micro differential evolution algorithm (VB-mDE)

Micro differential evolution (mDE) refers to algorithms that evolve with a small population to search for good solutions. Although mDEs are very useful for resource-constrained optimization tasks, the research on mDEs is still limited. In this paper, we propose a new mDE, i.e., vectorized bimodal distribution based mDE (called VB-mDE). The main idea is to employ a vectorized bimodal distribution parameter adjustment mechanism in mDE for performance enhancement. Specifically, in the VB-mDE, two important control parameters, i.e., scale factor F and crossover rate C⁢R, are adjusted by bimodal Cauchy distribution. At the same time, to increase the population diversity, the scale factor F is vectorized. The proposed VB-mDE is evaluated on the CEC2014 benchmark functions and compared with the state-of-the-art mDEs and normal DEs. The results show that the proposed VB-mDE has advantages in terms of solution accuracy and convergence speed.

Research on Self-Learning Fuzzy Control of Controllable Excitation Magnetic Suspension Linear Synchronous Motor

This paper studies the problem of different parameters adjustment and poor anti-interference capability for the magnetic suspension control system of controllable excitation linear synchronous motor (CELSM). Based on operating mechanism of CELSM, the mathematical model of magnetic suspension system is established. In addition, based on the Takagi–Sugeno fuzzy model-based approach, a self-learning fuzzy controller with parameter adjustment mechanism is designed. The controller includes a reference model that displays the desired characteristics of the magnetic suspension control system, a fuzzy inverse model that adjusts the fuzzy rules in real time and reduces the errors between the reference model output and the system output to zero, the rules and parameters adjustment units that change the adjustment degree of the rules according to the output proportion factor of the fuzzy inverse model, and the errors between the system output and the reference model output. A self-learning mechanism for modifying the output value of a standard fuzzy controller. At last, the simulation model is set up and compared with other control methods, the result shows that the suspension height control system has better anti-interference ability and tracking effect under the self-learning fuzzy control strategy, as well as the ability to deal with the change of the internal parameters of the magnetic suspension system. And the feasibility and the superiority of the modified control method are verified.

Physical configuration-based feedforward active noise control using adaptive second-order truncated Volterra filter

This paper presents a physical configuration-based feedforward active noise control scheme with an adaptive second-order truncated Volterra filter for point source cancellation in three-dimensional free-field acoustic environment. The inertial particle swarm optimization (PSO) algorithm is used as the parameter adjustment mechanism for tuning the coefficients of the adaptive Volterra filter. The first motivation of this paper is to provide a precise description of the relationship between the degree of cancellation and the physical distances between system components. The second motivation is to improve the cancellation performance in the presence of nonlinearities with the adaptive Volterra filter in light of the characteristics of sensing microphone and actuating loudspeaker. The reason for choosing the inertial PSO algorithm is that it can avoid the trap of local optima. The work thus presented makes two main contributions. The first is using the degree of cancellation as a function of the physical distances between system components to provide a quantitative analysis of system performance. The second is the application of the adaptive Volterra filter, which achieves improvements in the cancellation performance of the system under different physical configurations with a reasonable compromise with complexity. For consistency with the numerical analysis, several simulation experiments are conducted using MATLAB/Simulink.

Meta-heuristic inspired by the behavior of the humpback whale tuned by a fuzzy inference system

The Whale Optimization Algorithm (WOA) is a recent meta-heuristic that can be explored in global optimization problems. This paper proposes a new parameter adjustment mechanism that influences the probability of the food recognition process in the whale algorithm. The adjustment is performed using a fuzzy inference system that uses the current iteration number as input information. Our simulation results are compared with other meta-heuristics such as the conventional version of WOA, Particle Swarm Optimization (PSO) and Differential Evolution (DE). All algorithms are used to optimize ten test functions (Sphere, Schwefel 2.22, Quartic, Rosenbrock, Ackley, Rastrigin, Penalty 1, Schwefel 2.21, Six hump camel back and Shekel 1) in order to obtain their respective optimal values for be used as criteria for analysis and comparison. The results of the simulations show that the proposed fuzzy inference system improves the convergence of WOA and also is competitive in relation to the other algorithms, i.e., classical WOA, PSO and DE.

Adaptive neural network finite time control for quadrotor UAV with unknown input saturation

This study presents a novel adaptive robust control strategy for the position and attitude tracking of quadrotor unmanned aerial vehicles (UAVs) in the presence of input saturation, unmodeled nonlinear dynamics, and external disturbances. To deal with the negative effects of completely unknown input saturation constraints, a nonsymmetric saturation nonlinearity approxiator constructed by the hyperbolic tangent function attached with a parameter adjustment mechanism is incorporated into the controller design. Then, a novel neural network (NN) finite time backstepping-based anti-saturation control approach is proposed by introducing the NN finite time backstepping, designing the new virtual control signals and the modified error compensation mechanism. The proposed approach not only holds the advantages of the NN finite time backstepping control, but also prevents the system from degradation or even instability caused by unknown nonsymmetric saturation nonlinearities in actuator. The finite time convergence of all signals in the closed-loop aircraft system is guaranteed via Lyapunov finite time methodology despite the input saturations, unmodeled dynamics, and external disturbances. Finally, numerical simulations are carried out to illustrate the effectiveness and robustness of the proposed controller.