Speed Tracking Research Articles

Fusion of Multiple Attention Mechanisms and Background Feature Adaptive Update Strategies in Siamese Networks for Single-Object Tracking

Single-object tracking algorithms based on Siamese full convolutional networks have attracted much attention from researchers owing to their improvement in precision and speed. Since this tracking model only learns a similarity model offline, it is not able to obtain more useful feature discrimination information to adapt to the various variations of targets in complex scenes. To improve the performance of this tracking model, we propose a Siamese network tracking algorithm that incorporates multiple attention mechanisms and an adaptive updating strategy for background features. First, a backbone feature extraction network is proposed that utilizes a small convolutional kernel to fuse jump-layer connectivity features, thereby improving the feature representation capability of the network. Second, an adaptive update strategy for background features is proposed to improve the model’s ability to discriminate between the object and background features. Third, the fusion of multiple attention mechanisms is proposed so that the model learns to focus on the channel, spatial, and coordinate features. Fourth, the response fusion operation is proposed after the inter-correlation operation to enrich the output response of the model. Finally, our algorithm is trained using the GOT-10K dataset and evaluated by testing on the object tracking benchmark datasets OTB100 and VOT2018. The test results show that compared with other algorithms, our algorithm can effectively cope with the problem of degradation of the tracking performance in complex environments, and it can further improve the tracking precision and precision under the premise of ensuring the tracking speed.

Effects of Technique Asymmetry on 500 m Speed Skating Performance.

This study aimed to determine the effects of technique asymmetry on 500 m straight-track speed skating performance. We analyzed 20 elite skaters, measuring their joint angles, center of mass shift, and times and speeds during the gliding and push-off phases. The technique asymmetry index (ASI) was calculated for each parameter, and paired t-tests were used to compare bilateral asymmetry. Spearman correlation coefficients assessed the relationship between the ASI and both the average straight track speed and overall performance. Significant bilateral asymmetries in the knee, push-off, trunk, and hip angles were found in both male and female participants (p < 0.05). The male participants demonstrated a higher right push-off speed (p = 0.029) and a longer left gliding time (p = 0.048). Significant asymmetry was also observed in the lateral shift of the center of mass during each phase of the straight-track skating gait cycle (p < 0.001). No significant correlation was found between the ASIs and the overall performance (p ≥ 0.067). These findings indicate that while elite speed skaters demonstrated significant bilateral technique asymmetry in straight track skating, these asymmetries did not significantly impact their overall performance.

Research on design and control methods of a lightweight upper limb joint isokinetic rehabilitation training equipment.

Isokinetic exercise can improve joint muscle strength and stability, making it suitable for early rehabilitation of stroke patients. However, traditional isokinetic equipment is bulky and costly, and cannot effectively avoid external environmental interference. This paper designed a lightweight upper limb joint isokinetic rehabilitation training equipment, with a control system that includes a speed planning strategy and speed control with disturbance rejection. Based on the established human-machine kinematic closed-loop model between the equipment and the user, a dynamic evaluation method of torque at the joint level was proposed. To validate the effectiveness of the equipment, experiments were conducted by manually applying random disturbances to the equipment operated at an isokinetic speed. The results showed that the root mean square error between the observed torque curve of the second-order linear extended state observer used in this paper and the actual disturbance curve was 0.52, and the maximum speed tracking error of the speed control algorithm was 1.27%. In fast and slow sinusoidal speed curve tracking experiments, the root mean square errors of the speed tracking results for this algorithm were 9.65 and 5.27, respectively, while the tracking errors for the PID speed control algorithm under the same environment were 19.94 and 12.11. The research results indicate that compared with traditional PID control method, the proposed control strategy demonstrates superior performance in achieving isokinetic control and suppressing external disturbances, thereby exhibiting significant potential in promoting upper limb rehabilitation among patients.

Experimental Implementation of a TD3 Agent Based Speed Controller for Direct Torque Control of PMSM Drives

This manuscript presents a novel control approach for Permanent Magnet Synchronous Motors (PMSMs) by integrating the widely used Direct Torque Control (DTC) method with Deep Reinforcement Learning (DRL), specifically the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm. The TD3 algorithm is well-suited to address the challenges posed by high-dimensional state and action spaces in PMSM drives. The conventional Proportional–Integral (PI) controller in the outer loop of DTC is replaced with the DRL based TD3 agent to overcome the limitations of traditional PI controllers, such as model dependency and complex parameter tuning. The DRL technique allows the agent to learn optimal control policies from experience, making it suitable for complex and nonlinear control problems. Extensive simulation studies demonstrate the effectiveness of the TD3-based control in achieving accurate speed tracking under varying operating conditions. Real-time experimental validation using a TMS320F28379D digital signal processor confirms the feasibility of the proposed DRL based approach. The research offers new insights into improving the performance of PMSM drives and paves the way for future advancements in electric drive control.

A Comparison of Model Predictive Control Architectures for Application to Electrified Aircraft Propulsion Systems

Abstract As electrified aircraft propulsion (EAP) systems continue to mature, more sophisticated hardware and software are being developed to balance operations among electric machines and gas-turbine engines. In hybrid-electric propulsion systems, the increased complexity resulting from integrating turbine-engine shafts with electric machines necessitates control methodologies to account for various physical domains. Ideal controllers for hybrid-electric engines manage systems, subsystems, and their interactions in a coordinated fashion, able to account for safety and performance goals while being computationally efficient. In a previous work, linear model predictive control (MPC) schemes were implemented in centralized and distributed frameworks on a nonlinear turbofan engine model as a proof of concept. However, these schemes were not evaluated for computational complexity, prompting further study. The research presented here develops hierarchical MPC schemes to reduce the computational burden of the previous MPC schemes. A two-tier framework is implemented, where a slower sampling MPC controls electric machines and determines fan-speed tracking goals for a faster sampling controller, which is either a MPC or a proportional-integral (PI) controller. The proposed designs are compared to the centralized MPC investigated previously, and performance is measured via fan speed tracking error, energy storage state-of-charge, and computation time. Results reveal that the hierarchical MPC scheme employing a lower-level PI controller improves computation time while maintaining comparable tracking and state-of-charge regulation to the centralized scheme.

Integer PI, fractional PI and fractional PI data trained ANFIS speed controllers for indirect field oriented control of induction motor

Induction motor drives with variable speed applications that employ vector control are quite popular nowadays because they provide strong dynamic performance and flexible speed control. By decoupling the torque-producing current components of stator current from the rotor flux, Indirect Field Oriented Control is recognized for generating excellent performance in induction motor drives. This investigation is being done to show the effectiveness of the novel FPI input-output data-trained ANFIS controller and compare the three controllers' performance in terms of load variation capabilities, motor parameter variation, and speed tracking. Consequently, a comparison of the three controllers is important to select which controller performs high in induction motor drive. Indirect Field Oriented Control of induction motor with Fractional Proportional Integral (FPI), Integer Proportional Integral (IPI), and Adaptive Neuro-Fuzzy Inference System (ANFIS) controllers are all discussed in this work along with their designs and comparative analysis. The square of error was used as a fitness function to genetically optimize the FPI and IPI controller parameters. The suggested Adaptive Neuro-Fuzzy Inference System (ANFIS) controller uses a hybrid learning approach. It is trained by the FPI controller's input-output data. Using the results of MATLAB simulations under various operating situations, the performance of the ANFIS controller was compared with FPI and IPI controllers. Because of FPI controller includes an extra parameter for adjustment, namely integration order, it performed better than IPI controller for speed control of the induction motor. According to the simulation findings, the percentage peak overshoots while employing ANFIS, FPI, and IPI controllers were 0.495 %, 12.062 %, and 14.699 % respectively. As a result, ANFIS exhibits a drastic reduction in overshoot. Additionally, with the ANFIS controlled induction motor drive, the speed achieves the required set value at 0.14 s. For no load, constant, and changing loads, the induction motor drive's performance has been examined.

A modified particle swarm optimization-based adaptive maximum power point tracking approach for proton exchange membrane fuel cells

Fuel cells are one of the most promising renewable energy sources, offering advantages like reliability, eco-friendliness, and low pollutant emissions, which have spurred rapid advancements in power generation technologies. However, fuel cells face significant challenges, including high initial costs, limited fuel availability, and the difficulty of maintaining operation at the maximum power point, which hinders their use in stand-alone applications. In this paper, a Modified Particle Swarm Optimization (MPSO) method is proposed for maximum power point tracking (MPPT) to optimize the power output of Proton Exchange Membrane Fuel Cells (PEMFCs). The proposed method dynamically adjusts to key operational parameters such as cell temperature, hydrogen partial pressure, and membrane water content, areas that have not been comprehensively addressed in previous research. In this paper, an MPSO algorithm-based MPPT tracking approach without a PID controller is proposed to achieve the maximum power point (MPP) of a PEMFC. Under rapid temperature fluctuations in the fuel cell, the proposed MPSO MPPT method achieved a maximum power of 1223.5 W with an average of 5.66 iterations. In comparison, the meta-heuristic particle swarm optimization (PSO) method and the conventional perturb and observe (P&O) method achieved maximum power outputs of 1218.5 W and 1213.65 W, respectively, with PSO requiring 12.33 iterations. Additionally, the proposed approach showed improvements in power efficiency by 2.47 %, 2.87 %, and 13.58 % for the Jaya algorithm. demonstrating effective MPPT tracking under different operating conditions and perturbations. The MPSO method is implemented in the Simulink/MATLAB environment and is compared with the Perturb & Observe (P&O) and Conventional PSO (CPSO) methods. The results demonstrate that the proposed MPSO approach outperforms these traditional techniques in terms of tracking speed, efficiency, and stability under varying conditions. This successful implementation lays a strong foundation for future integration into real-world PEMFC systems.

A DDoS Tracking Scheme Utilizing Adaptive Beam Search with Unmanned Aerial Vehicles in Smart Grid

As IoT technology advances, the smart grid (SG) has become crucial to industrial infrastructure. However, SG faces security challenges, particularly from distributed denial of service (DDoS) attacks, due to inadequate security mechanisms for IoT devices. Moreover, the extensive deployment of SG exposes communication links to attacks, potentially disrupting communications and power supply. Link flooding attacks (LFAs) targeting congested backbone links have increasingly become a focal point of DDoS attacks. To address LFAs, we propose integrating unmanned aerial vehicles (UAVs) into the Smart Grid (SG) to offer a three-dimensional defense perspective. This strategy includes enhancing the speed and accuracy of attack path tracking as well as alleviating communication congestion. Therefore, our new DDoS tracking scheme leverages UAV mobility and employs beam search with adaptive beam width to reconstruct attack paths and pinpoint attack sources. This scheme features a threshold iterative update mechanism that refines the threshold each round based on prior results, improving attack path reconstruction accuracy. An adaptive beam width method evaluates the number of abnormal nodes based on the current threshold, enabling precise tracking of multiple attack paths and enhancing scheme automation. Additionally, our path-checking and merging method optimizes path reconstruction by merging overlapping paths and excluding previously searched nodes, thus avoiding redundant searches and infinite loops. Simulation results on the Keysight Ixia platform demonstrate a 98.89% attack path coverage with a minimal error tracking rate of 2.05%. Furthermore, simulations on the NS-3 platform show that drone integration not only bolsters security but also significantly enhances network performance, with communication effectiveness improving by 88.05% and recovering to 82.70% of normal levels under attack conditions.

A new neuro-fuzzy controller based maximum power point tracking for a partially shaded grid-connected photovoltaic system

Today, renewable energy systems like photovoltaic system are widely used in various applications. Among the different types of microgrids, hybrid microgrids are the most used type, therefore, inverters should be used to exchange power between DC and AC sides. According to the existing economic issues, extracting the maximum possible power from these systems are an important issue. This paper presents a new neuro-fuzzy controller for achieving maximum power point tracking (MPPT) in a grid-connected PV system under partially shaded conditions. This controller uses the Gravity Search Algorithm (GSA) to track the global maximum power point (GMPP) of the presented grid-connected PV system. The method controls the grid-connected inverter at the desired voltage to achieve maximum power after receiving its required specifications from the system. The Matlab/Simulink software is used to evaluate the performance of the proposed method. The results show that the proposed method can track the maximum power point under uniform and partial shading conditions with high speed and accuracy. Specifically, the proposed algorithm improves the tracking speed and increases the power output compared to traditional methods. The neuro-fuzzy controller's adaptive capabilities allow it to respond efficiently to dynamic changes in shading, ensuring stable and optimal power output. These advantages make the proposed method a significant improvement over existing MPPT techniques.

Fast fixed-time extended state observer based command filtering backstepping control of free-flying flexible-joint space robots

System parameter perturbations, external disturbances, and input saturation issues seriously affect the on-orbit operation precision and rapid response capabilities of the free-flying flexible-joint space robots (FFSR). To this end, a fixed-time extended state observer (ESO) based non-singular command filtering backstepping controller is proposed. The fast fixed-time ESO is designed to estimate the parameter perturbations and external disturbances. To avoid the “computational explosion” caused by multiple derivatives of the virtual control law in backstepping control, a second-order command filter is employed to obtain the derivative of virtual control laws. Meanwhile, to reduce the filtering errors induced by the command filter, a non-singular fixed-time filtering error compensation algorithm is developed. Furthermore, considering the constraints of control moment gyroscope (CMG) and joint motors, an anti-saturation compensation algorithm is introduced to drive the system out of the saturated region rapidly, thus reducing actuator saturation effects on the control system performance. Theoretical analysis shows the proposed controller can ensure the system tracking error converges to any arbitrarily small neighborhood of the origin within fixed time. Simulation results demonstrate that the designed non-singular fixed-time command filtering backstepping controller exhibits fast convergence speed and high tracking accuracy.

Improving Robustness and Dynamic Performance of Sensor less Vector-Controlled IM Drives with ANFIS-Enhanced MRAS

The Model Reference Adaptive System (MRAS) enables effective speed control of sensorless Induction Motor (IM) drives at zero and very low speeds. This study aims to enhance the resilience and dynamic performance of MRAS by integrating an Adaptive Neuro-Fuzzy Inference System (ANFIS) controller into sensorless vector-controlled IM drives. To address issues related to parameter uncertainties, load variations, and disturbances, the combination of MRAS and ANFIS is investigated. The ANFIS controller improves the dynamic performance by adapting its parameters based on the error between estimated and measured rotor speeds. This allows for better tracking of the reference speed and smoother drive operation. The proposed MRAS scheme with ANFIS reduces the sensitivity of the sensorless control system to parameter variations, such as changes in motor parameters or load torque, thereby enhancing stability. The primary goal of this system is to maintain stability and reduce the impact of parameter variations on the sensorless control system. The performance of the proposed system is evaluated using the MATLAB platform and compared with existing systems. Results indicate that the ANFIS-enhanced MRAS offers superior dynamic performance and robustness, making it a viable solution for applications requiring precise speed control and high reliability.

Research on energy consumption optimization of predictive cruise control considering the state of the leading vehicle

To comprehensively assess the economic performance of electric vehicles (EVs) cruise planning and mitigate conflicts with leading vehicles, a dynamic programming-based predictive cruise speed optimization control system was developed. This system comprises two layers: an upper V2X-based LSTM-DP cruise speed planning system and a lower adaptive cruise control system based on sliding mode control (SMC), and the mode switching strategy of the speed and distance tracking controller is designed. Initially, a segmented uniform variable motion algorithm processed the historical driving data of the leading vehicle, significantly enhancing the LSTM neural network's acceleration prediction capability, particularly on inclines, with an improvement in accuracy of 37.8 %. Subsequently, an adaptive cruise tracking controller was implemented to track the planned vehicle speed. Simulation tests on actual roads demonstrated that the LSTM-DP approach not only ensures driving safety but also markedly improves fuel efficiency over conventional constant speed cruising methods when planning is effective. Moreover, even in scenarios where planning fails, the LSTM-DP strategy can still achieve energy savings of up to 37 % without compromising the safety distance between vehicles. Finally, hardware-in-the-loop (HIL) testing confirmed the system's efficacy under real-time operational conditions.

Time-optimal constrained kinematic control of robotic manipulators by recurrent neural network

Time-optimal kinematic control is a vital concern for industrial manipulators to save allocated motion task time as much as possible. This requires maximizing the end-effector velocity to minimize the time required for path tracking. Nonetheless, it remains a challenge to ensure that joint motion constraints are not violated during this process, even with the aim of maximizing end-effector velocity simultaneously. This paper introduces a novel approach, which for the first time leverages dynamic recurrent neural networks (RNNs) within a constrained optimization framework to attain time-optimal kinematic control for manipulators. The theoretical analysis of the RNN-based kinematic control solver is addressed, ensuring both its optimality and convergence for achieving time-optimal kinematic control. The proposed method enables the maximization of end-effector velocity to achieve time-optimal kinematic control without violating all joint velocity limits simultaneously. In contrast to previous kinematic control schemes, the proposed method can enhance the end-effector path tracking speed of completion by 100% around, we substantiate the effectiveness and superiority of the proposed approach via simulation and V-Rep experiment on the manipulators.

Template‐Refine Network for Siamese Object Tracking

Various mainstream target tracking algorithms based on Siamese networks are gradually becoming a trend in the field of deep learning tracking due to their concurrent advantages of accuracy and speed. Most Siamese network‐based trackers describe the tracking of a target object as a similar matching problem, and these trackers have achieved more advanced performance in several public tests. Most trackers often suffer from tracking drift or performance degradation owing to the non‐updating of the template in the first frame and the target appearance encounters disturbing environments such as occlusion and drastic deformation. Therefore, to address this problem, this paper introduces a template updating mechanism and proposes a refine structure network based on the template updating of Siamese networks as well as the greater similarity of target features in two adjacent frames, which improves the tracking accuracy while limiting the amount of computation using an anchor‐free method in order not to lose the tracking speed, and only needs to be trained by selecting the most suitable pre‐training network, thus greatly reducing the amount of network computation. Meanwhile, in the application of the refine structure, with the aim of making the weight design of the target localisation module more reasonable, we propose a new Refine Head section and analyze and design the update threshold to optimize the overall network. This method is practiced in SiamFC++ algorithm, which firstly designs the template refine module, inputs the image that needs to be improved, and then outputs it to the Refine Head to complete the template update and applies it to the tracking of the subsequent frames, thereby constituting the SiamTRN (Template‐Refine Network). According to the experiments, the improved structure of the method can effectively implement the refine module function and enhance the performance of the tracker on public datasets, such as OTB100, VOT2016, UAV123 and GOT‐10 k. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

Drive Control using Multilevel Inverter for Electric Vehicle Application: A Hybrid SCSO-SNN Technique

This manuscript proposes a hybrid method for drive control using a multilevel inverter (MLI) for electric vehicle (EV) applications. The proposed technique is the joint execution of spiking neural network (SNN), and sand cat swarm optimization (SCSO), hence it is named as SCSO-SNN technique. The primary goal of the proposed technique is to improve the speed tracking performance and, energy efficiency and lessen the torque ripple of the EV. The set of control signals is generated by SCSO and the SNN is used to forecast the optimal control signal of the cascaded multilevel inverter (CMLI). The proposed technique is implemented in the MATLAB software and is evaluated their performance with various present methods. The results show that the proposed method can achieve better performance than current techniques based on speed tracking, energy efficiency, and torque ripple. The proposed method enhanced the total efficiency of the system (96%) and reduced the torque ripple (0.5%) when contrasted with current techniques like Genetic Algorithm (GA), Spotted Hyena Optimizer (SHO), Particle Swarm Optimization (PSO). The proposed method shows a mean of 1.269, a median of 1.212, and a standard deviation of 0.015, indicating high stability and consistency. It also demonstrates lower switching losses (0.159 W) and conduction losses (0.370 W) compared to existing methods, underscoring its superior energy efficiency and effectiveness.

Experimental validation of a low-cost maximum power point tracking technique based on artificial neural network for photovoltaic systems

Maximum power point tracking (MPPT) is a technique involved in photovoltaic (PV) systems for optimizing the output power of solar panels. Traditional solutions like perturb and observe (P&O) and Incremental Conductance (IC) are commonly utilized to follow the MPP under various environmental circumstances. However, these algorithms suffer from slow tracking speed and low dynamics under fast-changing environment conditions. To cope with these demerits, a data-driven artificial neural network (ANN) algorithm for MPPT is proposed in this paper. By leveraging the learning capabilities of the ANN, the PV operating point can be adapted to dynamic changes in solar irradiation and temperature. Consequently, it offers promising solutions for MPPT in fast-changing environments as well as overcoming the limitations of traditional MPPT techniques. In this paper, simulations verification and experimental validation of a proposed data-driven ANN-MPPT technique are presented. Additionally, the proposed technique is analyzed and compared to traditional MPPT methods. The numerical and experimental findings indicate that, of the examined MPPT methods, the proposed ANN-MPPT approach achieves the highest MPPT efficiency at 98.16% and the shortest tracking time of 1.3 s.

Data driven digital twin system for the cross-domain vehicle

The Cross-Domain Vehicle (CDV) is a sophisticated marine equipment capable of performing tasks across different domains. This paper aims to develop a data-driven digital twin system for the CDV to achieve precise motion control and data monitoring during its operation. Leveraging the kinematic physical characteristics of the CDV, the digital twin system constructs a virtual counterpart of the vehicle, establishing a mapping relationship between the physical and virtual entities. The use of a Long Short-Term Memory (LSTM) network model is proposed for forecasting the motion state of the CDV within the digital twin framework, supporting the vehicle's autonomous motion decision-making process. Additionally, an innovative model predictive control strategy is employed to achieve surface speed tracking control for the CDV, leveraging predictive data within the digital twin system. Utilizing the digital twin system to optimize control parameters, better underwater depth control effects can be achieved for the CDV. Finally, through the system implementation and experiment verification, the effectiveness of the digital twin system is successfully demonstrated, providing reliable results for both surface speed tracking control and underwater depth control.

Research on the control of thrust vectoring turbojet aircraft with uncertainties and input saturation based on fixed‐time control

AbstractOne‐dimensional thrust vectoring turbojet vertical takeoff and landing (VTOL) aircraft have attracted research attention due to their high thrust‐to‐weight ratios and their solution for the slow speed response of turbojet engines. However, there are some uncertainties and physical limitations in their systems, such as external disturbances, unknown parameters and input saturation. To improve the accuracy and convergence speed of trajectory tracking, a fixed‐time control method that is robust to saturation is proposed. The system dynamics are established, and an auxiliary system is built within a fixed time control framework to address the influence of input saturation and increase the error convergence rate. Nonsingular fast terminal sliding mode technology is combined with a few adaptive laws to ensure the robustness of the closed‐loop system against dynamic uncertainties and improve the precision of steady‐state control. The stability of the control system is proven based on Lyapunov, and the controller parameters are optimized based on particle swarm optimization (PSO). The proposed method based on fixed‐time stability guarantees that the states of the closed‐loop system can reach the residual set around zero within the designed time, and an expression for the upper bound on the convergence time is given. Finally, numerical simulations demonstrate the superiority of the proposed method based on the error integral criterion.

A learning-based model predictive control scheme for injection speed tracking in injection molding process

Injection molding is a pivotal industrial process renowned for its high production speed, efficiency, and automation. Controlling the motion speed of injection molding machines is a crucial factor that influences production processes, directly affecting product quality and efficiency. This paper aims to tackle the challenge of achieving optimal tracking control of injection speed in a standard class of injection molding machines (IMMs) characterized by nonlinear dynamics. To achieve this goal, we propose a learning-based model predictive control (LMPC) scheme that incorporates Gaussian process regression (GPR) to predict and model uncertainty in the injection molding process (IMP). Specifically, the scheme formulates a nonlinear tracking control problem for injection speed, utilizing a GPR-based learning residual model to capture uncertainty and provide accurate predictions. It learns the dynamics model and historical data of the IMM, automatically adjusting the injection speed according to target requirements for optimal production control. Additionally, the optimization problem is efficiently solved using a control-constrained differential dynamic programming approach. Finally, we conduct comprehensive numerical experiments to demonstrate the effectiveness and efficiency of the proposed LMPC scheme for controlling injection speed in IMP.

Design of an observer-based anti-disturbance speed tracking controller for integrated motor-transmission systems under uncertain parameters and road slope variation

Design of an observer-based anti-disturbance speed tracking controller for integrated motor-transmission systems under uncertain parameters and road slope variation