This paper presents a novel model-free control approach, Flower Pollination Algorithm-based Model-Free Control (FPA-MFC), for trajectory tracking of mini-drone quadrotor unmanned aerial vehicles (UAVs). The proposed a...
详细信息
This paper presents a novel model-free control approach, Flower Pollination Algorithm-based Model-Free Control (FPA-MFC), for trajectory tracking of mini-drone quadrotor unmanned aerial vehicles (UAVs). The proposed approach employs an adaptive estimator based on filtered signals to approximate the nonlinear dynamic functions of the system. This approximator allows the development of a robust decentralized control law able to separately manage the position and attitude dynamics of the drone. The controller design is free of any prior knowledge of the system dynamics, and the control inputs are computed solely from instantaneous input and output measurements. Indeed, this can significantly reduce the computational burden and improve the efficiency of the control algorithm while preserving its simplicity. The design gains of the control law are selected using the metaheuristic flower pollination algorithm to achieve greater trajectory tracking performance and ensure closed-loop system stability. Simulation tests conducted on the Parrot mini drone platform validate the effectiveness and superior performance of FPA-MFC, compared to similar controllers without optimization and using the particle swarm optimization algorithm.
Drive electrification is one major development area to decrease greenhouse emissions. Especially computer aided synthesis and optimization tools are necessary for early drive concept development as well as the concept...
详细信息
ISBN:
(纸本)9798350317671;9798350317664
Drive electrification is one major development area to decrease greenhouse emissions. Especially computer aided synthesis and optimization tools are necessary for early drive concept development as well as the concept definition. Depending on the investigation and boundary parameters, the number of possible variants is in the millions. Hence the result quality as well as the investigation time depend significantly on the used optimization and control algorithm of the synthesis. In this paper we introduce an algorithm, comprising of a fuzzy logic in combination with a search space algorithm for controlling a drive system synthesis as well as optimizations. In a first application of the algorithm for a D-segment parallel hybrid topology optimization, the global optimum was found within 1.33 % of all possible simulations. Furthermore, the algorithm was able to find additional solutions close to the global optimum.
Ferroelectric Random Access Memory (FRAM) by Texas Instruments (TI) is a non-volatile memory which allows lower power and faster data throughput compared to other nonvolatile solutions. These features have accelerated...
详细信息
ISBN:
(纸本)9781479968435
Ferroelectric Random Access Memory (FRAM) by Texas Instruments (TI) is a non-volatile memory which allows lower power and faster data throughput compared to other nonvolatile solutions. These features have accelerated the interest in this technology as the future of embedded unified memory, in particular in data logging, remote sensing and Wireless Sensor Network (WSN). The application of Model Predictive Control (MPC) in WSN has gained lot of attention in the last years and it requires solving convex optimization problems in real-time. In this paper several convex optimization algorithms have been implemented and compared on a FRAM-based MSP-EXP430FR5739 node by TI, to evaluate its suitability in extending the potentialities of onboard volatile Static Random Access Memory (SRAM) for embedded optimization-based control.
Four optimization algorithms (genetic algorithm, simulated annealing, particle swarm optimization and random forest) were applied with an MLP based auto associative neural network on two classification datasets and on...
详细信息
ISBN:
(纸本)9781479938407
Four optimization algorithms (genetic algorithm, simulated annealing, particle swarm optimization and random forest) were applied with an MLP based auto associative neural network on two classification datasets and one prediction dataset. This work was undertaken to investigate the effectiveness of using auto associative neural networks and optimization algorithms in missing data prediction and classification tasks. If performed appropriately, computational intelligence and optimization algorithm systems could lead to consistent, accurate and trustworthy predictions and classifications resulting in more adequate decisions. The results reveal GA, SA and PSO to be more efficient when compared to RF in terms of predicting the forest area to be affected by fire. GA, SA, and PSO had the same accuracy of 93.3%, while RF showed 92.99% accuracy. For the classification problems, RF showed 93.66% and 92.11% accuracy on the German credit and Heart disease datasets respectively, outperforming GA, SA and PSO.
This paper studies the application of information sharing technology in distributed photovoltaic aggregation optimization control, and proposes an optimization control strategy based on distributed gradient descent al...
详细信息
Given the shortcomings of the traditional Golden Jackal optimization (GJO) algorithm, including limited accuracy and slow convergence speed in solving mobile robot path planning problems, an improved adaptive Golden J...
详细信息
The biological world is an ideal place for seeking inspiration for developing mathematical optimization algorithms. In this paper we propose two hybrid stochastic optimization algorithms that bear resemblance to the s...
详细信息
ISBN:
(纸本)9781479954964
The biological world is an ideal place for seeking inspiration for developing mathematical optimization algorithms. In this paper we propose two hybrid stochastic optimization algorithms that bear resemblance to the sexual reproduction cycle of Jellyfish and asexual reproductive cycle of species of Hydra. The performance of these two algorithms are investigated against other common optimization algorithms on a set of benchmark optimization problems. The results show that the proposed algorithms perform well.
A so-called solid-state (i.e., mechanism-free) ornithopter can be achieved by utilizing induced-strain actuators such as piezoelectric material-based devices - specifically piezocomposite devices. Such ornithopters wi...
详细信息
ISBN:
(纸本)9780791888322
A so-called solid-state (i.e., mechanism-free) ornithopter can be achieved by utilizing induced-strain actuators such as piezoelectric material-based devices - specifically piezocomposite devices. Such ornithopters with induced-strain actuated wings eliminate the need for electromagnetic motors and conventional power transmission mechanisms, potentially saving weight and energy consumption, improving reliability and flexibility, and reducing overall mechanical complexity. Given the complexity of such system, featuring a high number of design variables and nonlinearities, achieving an optimized configuration is crucial. In their previous research, the authors developed a novel model to account for dynamic two-way coupling and nonlinearities using a state space representation for mechanismfree ornithopters. The model considered (1) two-way fluidstructure interaction, (2) body-wing coupling, and (3) wing bend-twist coupling. Based on the state space representation of the ornithopter, the current paper focuses on a design optimization framework utilizing a multi-objective genetic algorithm. The design variables considered include ornithopter body inertia, piezocomposite device positions and orientations, excitation voltage, frequency, etc. The optimization algorithm is initially validated for convergence using established test functions. Subsequently, the optimization procedure is carried out for multiple case studies with a variation of fitness metrics that represent the aerodynamic and structural performance of the ornithopter. The selected objective functions encompass structural metrics such as wing weight and compliance, as well as aerodynamic metrics such as lift and thrust force amplitudes.
Sharp-Edged Width Constrictions (SEWC) are hydraulic structures designed to measure flow in open channels. Accurate prediction of the discharge coefficient (Cd) in SEWC is crucial for determining water discharge in th...
详细信息
Sharp-Edged Width Constrictions (SEWC) are hydraulic structures designed to measure flow in open channels. Accurate prediction of the discharge coefficient (Cd) in SEWC is crucial for determining water discharge in these channels. This information plays a key role in effective water resource management, supporting decision-making regarding the allocation and conservation of water for agricultural, industrial, and municipal purposes. This study introduces a novel hybrid machine learning model, combining Support Vector Regression (SVR) with the Improved Whale optimization Algorithm (IWOA). Additionally, advanced machine learning models such as NGBoost, AutoInt, and TabNet were employed to predict Cd in SEWC. The SVR-IWOA model offers automatic hyperparameter tuning, significantly enhancing prediction accuracy in complex flow conditions. To develop these models, a dataset consisting of 156 laboratory data points from SEWC experiments was utilized, with 75 % of the data allocated for training and 25 % for testing. The Isolation Forest (IF) algorithm was applied to detect and remove outliers, leading to the exclusion of 5.1 % of the original dataset. Dimensional analysis identified critical factors influencing Cd, including the ratio of upstream depth to opening width (h/b) and the constriction ratio (beta = b/B, where B is the channel width). The validity of these dimensionless parameters was confirmed using ANOVA and SHAP analyses, which highlighted beta as the most influential factor affecting Cd. Model performance was rigorously evaluated using multiple metrics, including the coefficient of determination (R2), Root Mean Squared Error (RMSE), Scatter Index (SI), Weighted Mean Absolute Percentage Error (WMAPE), and symmetric Mean Absolute Percentage Error (sMAPE). Comparative evaluations were conducted using Taylor Diagrams, Residual Error Curves (REC), and the Performance Index (PI). In the training stage, NGBoost demonstrated superior performance with a PI of 4994 an
Proton exchange membrane fuel cells (PEMFCs) are energy conversion devices that utilize renewable hydrogen energy. The reaction process in PEMFCs generates water and releases substantial heat, achieving high energy de...
详细信息
Proton exchange membrane fuel cells (PEMFCs) are energy conversion devices that utilize renewable hydrogen energy. The reaction process in PEMFCs generates water and releases substantial heat, achieving high energy density while effectively reducing environmental pollution, making PEMFCs a focal point of research. However, the complexity of internal reactions and the multitude of parameters in PEMFC mathematical models result in nonlinear output characteristics, posing challenges to the accuracy and efficiency of identifying unknown parameters in these models. To address these challenges, this study proposes an Improved Black Kite Algorithm (IBKA). Using a 30 kW PEMFC stack testing platform, four datasets under different operating conditions were collected, and a static model suitable for high-power PEMFCs was established. To validate the effectiveness of IBKA, performance tests were conducted on benchmark functions, and the algorithm was applied to identify seven unknown parameters in both high-power and conventional static PEMFC models. The objective function for parameter identification was defined as the sum of squared errors between experimental and model outputs. Additionally, datasets from two commercial fuel cell stacks with different parameter specifications (NedStack PS6 and BCS500W) were used to compare the parameter identification results obtained from various algorithms with those of IBKA. The performance tests and model parameter identification results demonstrate that IBKA excels in accuracy, convergence speed, adaptability, and robust stability. For the high-power PEMFC static model, the combination of IBKA and the model achieved a mean squared error (MSE) below 0.15 between model and experimental outputs, enabling accurate predictions of high-power PEMFC outputs under various operating conditions and parameter specifications. For conventional PEMFCs, the objective function results based on the NedStack PS6 dataset were 1.2558, and 0.0119 for the BCS
暂无评论