The command filtered adaptive fuzzy backstepping control method has been proposed in this study. By using the filter, it is not only states, actuator constraints, and problem of 'explosion complexity' conventional have solved, but also calculation partial derivatives unnecessary, so that law update become succinct. Fuzzy logic systems, designed study, are utilised real-time identification uncertain non-linear functions. Throughout process controller design, transformed style Butterworth...

This paper presents a model predictive control (MPC) method for redundant robots controlling multiple hierarchical tasks formulated as multi-layer constrained optimal problems (OCPs). The proposed method, named incremental MPC (HIMPC), is robust to dynamic uncertainties, untethered from kinematic/algorithmic singularities, and capable of handling input state constraints such joint torque position limits. To this end, we first derive systems that approximate uncertain system dynamics without...

This article investigates the tracking problem of an uncertain <inline-formula> <tex-math notation="LaTeX">$n$ </tex-math></inline-formula>-link robot manipulator with guaranteed safety and performance. To tackle parametric uncertainties, torque filtering-augmented concurrent learning (CL) method is introduced for online identification unknown system without requirements joints acceleration. By using CL, parameter convergence by exploiting current historical data simultaneously. technique...

This article proposes a new incremental model predictive control (IMPC) strategy, which allows for constrained of robot manipulator, while the resulting is derived without concrete mathematical system model. First, to reduce dependence on nominal manipulators, continuous-time nonlinear approximated by an using time-delay estimation (TDE). Then, based system, tracking IMPC designed in framework MPC terminal ingredients. Thus, compared with existing methods, not required. Moreover, we...

Unmanned aerial vehicle (UAV) image detection algorithms are critical in performing military countermeasures and disaster search rescue. The state-of-the-art object algorithm known as you only look once (YOLO) is widely used for detecting UAV images. However, it faces challenges such high floating-point operations (FLOPs), redundant parameters, slow inference speed, poor performance small objects. To address the above issues, an improved, lightweight, real-time was proposed based on edge...

Abstract This article presents a new formulation for model‐free robust optimal regulation of continuous‐time nonlinear systems. The proposed reinforcement learning based approach, referred to as incremental adaptive dynamic programming (IADP), utilizes measured input‐state data allow the design approximate control strategy, stabilizing controlled system incrementally under model uncertainties, environmental disturbances, and input saturation. By leveraging time delay estimation (TDE)...

A robust control allocation scheme is developed for rigid spacecraft attitude stabilization in the presence of actuator partial loss fault, failure, and misalignment. First, a neural network fault detection proposed, Second, an adaptive tracking strategy employed which can realize tolerance under failure within<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"...

With the continuous development and innovation in field of global magnetic levitation technology, suspended permanent magnet maglev rail transit system has emerged. At present, no mature relevant technical standard references are available world. To study electromagnetic radiation problem train system, we use finite element method to simulate analyze Halbach array track different combinations suspension modules, six-channel high-precision test is used compare actual engineering fields. The...

In this study, a command-filtered sensor-based backstepping controller is proposed for small unmanned aerial vehicles (UAVs) with actuator dynamics. The command filter introduced to prompt the virtual control law be limited in certain range and corresponding state subsequently restricted area. When using recursive method, precise models of UAVs are not required because sensitive external disturbance. dynamics compensated without prior knowledge mathematical model executing agency. Besides,...

In suspended permanent magnet maglev trains, the magnetic field generated by hollow-type synchronous linear motors is one of main sources low-frequency electromagnetic fields. To investigate motor in train, this paper first establishes 2D and 3D models using ANSYS EM software. Then, simulation performed under conditions no load full load. Next, measured a six-channel high-precision test system, measurement results are compared. The result analysis indicates that energy distribution uniform...

The aim of this study was to evaluate the effects wheat gluten as a substitute for fish meal (FM) and soy protein concentrate (SPC) in low-fishmeal-based extruded diet red spotted grouper Epinephelus akaara. Eight isonitrogenous (441–456 g kg−1) isocaloric (21.5–22.0 MJ diets were produced, including control (R0), three with 33.3, 66.7, 100% FM being replaced by mixture gluten, wheat, taurine (GWT) (RF1, RF2, RF3), SPC GWT (RS2, RS2, RS3) one 50% (RFS). Results showed that feed intake (FI),...

Traffic flow prediction is a vital component of Intelligent Transportation Systems (ITS). However, it extremely challenging to predict traffic accurately for large-scale road network over multiple time horizons, due the complex and dynamic spatiotemporal dependencies involved. To address this issue, we propose Spatiotemporal Exogenous Variables Enhanced Transformer (SEE-Transformer) model, which leverages Graph Attention Networks architectures incorporates exogenous variables data....

In this paper, a data-driven time-delayed control (TDC) approach is developed for Euler-Lagrange systems. The TDC kind of approaches and can handle model uncertainties, unmodelled dynamics or unknown disturbances in the system conveniently, whose basic idea to use measurement information at last time instant approximately estimate all factors current instant. A user specified constant gain matrix main design parameter influences both closed-loop stability tracking performance. Currently...

To enhance the accuracy and efficiency of color matching for opaque products, a relevant model is employed to predict their schemes. By extracting spectral reflectance dyed panels as input dyeing ratios output, it possible reduce errors improve production efficiency, thereby advancing technology products achieving freedom. This study initially applies logarithmic transformation K/S (absorption coefficient/scattering coefficient) ratio concentration, converting resultant equations into linear...

Lightweight object detection algorithms play a paramount role in unmanned aerial vehicles (UAVs) remote sensing. However, UAV sensing requires target to have higher inference speeds and greater accuracy detection. At present, most lightweight achieved fast speed, but their precision is not satisfactory. Consequently, this paper presents refined iteration of the algorithm address above issues. The MobileNetV3 based on efficient channel attention (ECA) module used as backbone network model. In...

This paper proposed a novel sensor based backstepping control mthod for hypersonic vehicle with actuator compensator. The method will apply the so-called "approximate dynamic inversion" to design virtual law each subsystem, not just last subsystem. Compared traditional method, it does need all of precise aerodynamic parameters system and is sensitive external disturbance, so has strong robustness. To accommodate influence dynamics, compensator designed. performance stability analysis...