The Brushless DC motors are used in various industries such as home appliances, electric vehicles, Medical, Industrial automation equipment and so on. Because they have advantages of low noise, simple control and high...
详细信息
ISBN:
(纸本)9788993215144
The Brushless DC motors are used in various industries such as home appliances, electric vehicles, Medical, Industrial automation equipment and so on. Because they have advantages of low noise, simple control and high power density. But, in a high-speed motor drive, current lagging which is induced by the impedance of the motor inductor reduces the motor efficiency. To solve this problem, we propose an auto lead angle control algorithm based on a gradient descent algorithm. With this algorithm, the motor current and motor Back-EMF have an identical phase angle. Thus, the efficiency of the motor can be increased. In order to verify the proposed algorithm, we implemented the hardware with FPGA and board including analog circuit. As a result, it was confirmed that the optimum lead angle was found with only one current value without various parameters, and the efficiency of the motor was improved. Also, it is confirmed that the efficiency is further increased at high load and high speed.
In this paper, we focus on the path following control of a fixed-wing UAV and investigate how to avoid pop-up threats by onboard optimization. It contains two subproblems: how to bypass threat areas in time and how to...
详细信息
In this paper, we focus on the path following control of a fixed-wing UAV and investigate how to avoid pop-up threats by onboard optimization. It contains two subproblems: how to bypass threat areas in time and how to minimize deviations from the desired path. More importantly, the calculation must be completed in real-time. To address this, we design an accelerated model predictive controller with two stages. First, we incorporate multiple control objectives into the prediction model in a weighted manner. Then, by introducing the rectified linear unit penalties, it is transformed into an unconstrained problem, which is solved by gradient-based optimizers. Six state-of-the-art optimizers are compared in simulations. The results prove that the proposed control method can well deal with multiple static or moving threats, is robust to wind disturbance, and has high real-time performance.
Conversion from dc to the 10th Nyquist band is enabled in a SHA-less, 10-b, 100-MS/s pipelined ADC by digitally calibrating the clock skew in the 3.5-b front-end stage. Architectural redundancy of pipelined ADC is exp...
详细信息
ISBN:
(纸本)9781424457601
Conversion from dc to the 10th Nyquist band is enabled in a SHA-less, 10-b, 100-MS/s pipelined ADC by digitally calibrating the clock skew in the 3.5-b front-end stage. Architectural redundancy of pipelined ADC is exploited to extract skew information from the first-stage residue output with two out-of-range comparators and some simple digital logic;a gradient-descentalgorithm is used to adaptively adjust the timing of the front-end sub-ADC to synchronize with that of the S/H. The 90-nm prototype consumes 12.2 mW and digitizes inputs up to 480 MHz (limited by testing equipment) without skew errors in experiments, whereas the same ADC fails at 130 MHz when the calibration is disabled. The measured SFDR is 71 dB at 20 MHz and 55 dB at 480 MHz.
A recursive network is proposed by introducing memory neurons based on the RBF network. Due to the current output value of the network is related to the past input value in the network, the network will be able to ide...
详细信息
ISBN:
(纸本)9781467397148
A recursive network is proposed by introducing memory neurons based on the RBF network. Due to the current output value of the network is related to the past input value in the network, the network will be able to identify the dynamics of the system without the need of explicitly feedback of input and output in the past. Thus, the network is able to identify a system has an unknown order or an unknown delay. Training algorithm and the theoretical rationality are provided in this paper. The validity of the method is verified by simulation of dynamic system identification, and it is of great significance in the field of adaptive control.
In this paper, an "Adaptive Receding Horizon Controller (ARHC)" is exemplified in the suboptimal control of a Furuta pendulum. A dynamic model of strongly overestimated inertia and friction parameters is use...
详细信息
ISBN:
(纸本)9781665444996
In this paper, an "Adaptive Receding Horizon Controller (ARHC)" is exemplified in the suboptimal control of a Furuta pendulum. A dynamic model of strongly overestimated inertia and friction parameters is used in an RHC controller to track the nominal trajectory under cost terms penalizing the control forces. The so obtained "optimized" trajectory is tracked by an adaptive controller that uses a realistic approximate dynamic model of the controlled system. Since the approximate and the actual model contain considerably smaller inertia and friction parameters than that used for optimization the cautiously optimized trajectory can be precisely tracked by the actual system without suffering from heavy force burdens. The adaptivity is guaranteed by a "Fixed Point Iteration"-based approach that in this manner easily can be combined with the mathematical framework of optimal controllers. Instead of using Lagrange multipliers, the optimization happens through explicitly applying the dynamic model in forward Euler integration. The operation of the method is exemplified via numerical simulations.
Predicting the solution of complex systems is a significant challenge. Complexity is caused mainly by uncertainty and nonlinearity. The nonlinear nature of many complex systems leaves uncertainty irreducible in many c...
详细信息
ISBN:
(纸本)9783319984438;9783319984421
Predicting the solution of complex systems is a significant challenge. Complexity is caused mainly by uncertainty and nonlinearity. The nonlinear nature of many complex systems leaves uncertainty irreducible in many cases. In this work, a novel iterative strategy based on the feedback neural network is recommended to obtain the approximated solutions of the fully fuzzy nonlinear system (FFNS). In order to obtain the estimated solutions, a gradient descent algorithm is suggested for training the feedback neural network. An example is laid down in order to demonstrate the high accuracy of this suggested technique.
In recent years machine learning technologies have been applied to ranking, and a new research branch named "learning to rank" has emerged. Three types of learning-to-rank methods - pointwise, pairwise and l...
详细信息
ISBN:
(纸本)9781424496365
In recent years machine learning technologies have been applied to ranking, and a new research branch named "learning to rank" has emerged. Three types of learning-to-rank methods - pointwise, pairwise and listwise approaches - have been proposed. This paper is concerned with listwise approach. Currently structural support vector machine(SVM) and linear neural network have been utilized in listwise approach, but these methods only consider the content relevance of an object with respect to queries, they all ignore the relationships between objects. In this paper we study how to use relationships between objects to improve the performance of a ranking model. A novel ranking function is proposed, which combines the content relevance of documents with respect to queries and relation information between documents. Two types of loss functions are constructed as the targets for optimization. Then we utilize neural network and gradient descent algorithm as model and training algorithm to build ranking model. In the experiments, we compare the proposed methods with two conventional listwise approaches. Experimental results on OHSUMED dataset show that the proposed methods outperform the conventional methods.
In this paper, we propose two kinds of orthogonalization gradient linear discriminant analysis (OGLDA) algorithms to improve the performance of traditional gradient LDA (GLDA) for undersampled problems in face recogni...
详细信息
ISBN:
(纸本)9781424435296
In this paper, we propose two kinds of orthogonalization gradient linear discriminant analysis (OGLDA) algorithms to improve the performance of traditional gradient LDA (GLDA) for undersampled problems in face recognition tasks. In the OGLDA1, the orthogonalization procedure is performed on the discriminant vectors to reduce the redundancy among the discriminant features obtained by GLDA. Thus, all obtained discriminative features can equally contribute to classification performance, which significantly improves the performance of GLDA algorithm for face recognition. In the OGLDA2, the discriminant vectors are resolved one by one in each iterative procedure which overcomes the drawbacks of high computational cost and numerical instability existing in the OGLDA1 algorithm. Since the orthogonalization procedure is applied in the proposed OGLDA methods, the computational stability is improved greatly. The effectiveness of the proposed methods is verified in the experiments on the standard face image databases.
In this work we propose an adaptive PID control law to deal with a class of single input single output (SISO) uncertain nonlinear systems. In fact, a fuzzy system is used for approximating the PID control gains. The f...
详细信息
ISBN:
(纸本)9781538606865
In this work we propose an adaptive PID control law to deal with a class of single input single output (SISO) uncertain nonlinear systems. In fact, a fuzzy system is used for approximating the PID control gains. The fuzzy system parameters are adjusted online using a robust adaptation law based on the gradient method and augmented by the so-called "e-modification" term, in order to minimize the error between the fuzzy PID controller and the unknown ideal controller. The stability of the closed-loop system is proven analytically using the Lyapunov approach. A simulation example is presented to illustrate the performance of the proposed scheme.
Wavelet Neural Networks (WNN) are computational tools used now a day for control and estimation purposes. This paper describes a wavelet neural network based control system designed for Permanent Magnet Brushless DC (...
详细信息
ISBN:
(纸本)9781538682524
Wavelet Neural Networks (WNN) are computational tools used now a day for control and estimation purposes. This paper describes a wavelet neural network based control system designed for Permanent Magnet Brushless DC (PMBLDC) Motor drive. The WNN controller is trained online through gradient descent algorithm for controlling the motor output in different operating conditions. A software is developed in C++ and was used to test the performance of the drive system. The results show that drive control system works effectively after comparison of the results with those obtained using PI controller based system.
暂无评论