The aerodynamic drag coefficient curve of spin-stabilized projectiles is very important to the fast generation of accurate firing tables. To identify it from Doppler tracking radar measured velocity data in flight tes...
详细信息
The aerodynamic drag coefficient curve of spin-stabilized projectiles is very important to the fast generation of accurate firing tables. To identify it from Doppler tracking radar measured velocity data in flight tests, an iterative learning concept (ILC) is applied. High-order ILC algorithms are proposed. Convergence conditions are given in a general problem setting. A 3-DOF point mass trajectory prediction model is proposed. The learning gains, which vary with respect to both time and iteration number, have been used for a faster convergence compared to the constant learning parameter choices. Furthermore, in this paper, a bi-linear ILC scheme is proposed to produce even faster learning convergence. The flight testing data reduction results of an actual firing practice demonstrate that the iterative learning method is very effective in curve identification. Copyright (C) 1997 Elsevier Science Ltd.
Standard backpropagation, as with many gradient based optimization methods converges slowly as neural networks training problems become larger and more complex. In this paper, we present a new algorithm, dynamic adapt...
详细信息
Standard backpropagation, as with many gradient based optimization methods converges slowly as neural networks training problems become larger and more complex. In this paper, we present a new algorithm, dynamic adaptation of the learning rate to accelerate steepest descent. The underlying idea is to partition the iteration number domain into n intervals and a suitable value for the learning rate is assigned for each respective iteration interval. We present a derivation of the new algorithm and test the algorithm on several classification problems. As compared to standard backpropagation, the convergence rate can be improved immensely with only a minimal increase in the complexity of each iteration.
A learning algorithm for single layer perceptrons is proposed First, a cone-like domain is derived such that all its elements can be recognized as a stored pattern in the perceptron network. The learning algorithm is ...
详细信息
A learning algorithm for single layer perceptrons is proposed First, a cone-like domain is derived such that all its elements can be recognized as a stored pattern in the perceptron network. The learning algorithm is obtained as a process that enlarges the cone-like domain. For autoassociative networks, it is shown that the cone-like domain becomes a domain of attraction for a stored pattern in the network. In this case, extended domains of attraction are also obtained by feeding the outputs of the network back to the input layer In computer simulations, character recognition ability of the autoassociative network is examined. (C) 1997 Elsevier Science Ltd. All rights reserved.
This paper proposes a concurrent learning algorithm for forward and inverse modeling. The algorithm is consisted of two phases. In the first phase, a feedback controller is used. The forward model is trained using the...
详细信息
This paper proposes a concurrent learning algorithm for forward and inverse modeling. The algorithm is consisted of two phases. In the first phase, a feedback controller is used. The forward model is trained using the output values of the controller as the input values to the system and the inverse model is trained by the feedback error learning. In the second phase, the forward model and the inverse model are trained at the same time. By the simulation experiments in a two-link manipulator, it is confirmed that our algorithm can converge faster than the ones already proposed.
This paper reports on the existing robot force control algorithms and their composition based on the review of 75 papers on this subject. The objective is to provide a pragmatic exposition with speciality on their dif...
详细信息
This paper reports on the existing robot force control algorithms and their composition based on the review of 75 papers on this subject. The objective is to provide a pragmatic exposition with speciality on their differences and different application conditions, and to give, a guide of the existing robot force control algorithms. The previous work can be categorized into discussion, design and/or application of fundamental force control techniques, stability analysis of the various control algorithms, and the advanced methods. Advanced methods combine the fundamental force control techniques with advanced control algorithms such as adaptive, robust and learning control strategies.
The semiparametric statistical model is used to formulate the problem of blind source separation. The method of estimating functions is applied to this problem, It is shown that an estimator of the mixing matrix or it...
详细信息
The semiparametric statistical model is used to formulate the problem of blind source separation. The method of estimating functions is applied to this problem, It is shown that an estimator of the mixing matrix or its learning version can be described in terms of an estimating function. The statistical efficiencies of these algorithms are studied. The main results are as follows. 1) The space consisting of all the estimating functions is derived. 2) The spare is decomposed into the orthogonal sum of the admissible part and redundant ancillary part. For any estimating function, one can find a better or equally good estimator in the admissible part. 3) The Fisher efficient (that is, asymptotically best) estimating functions are derived4) The stability of learning algorithms is studied.
This paper presents a systematic methodology to the design of a multivariable fuzzy logic controller (MFLC) for large-scale nonlinear systems. A new general method which is based on a performance index of sliding moti...
详细信息
This paper presents a systematic methodology to the design of a multivariable fuzzy logic controller (MFLC) for large-scale nonlinear systems. A new general method which is based on a performance index of sliding motion is used to generate a fuzzy control rule base. Reducible input variables obtained from sliding motion are adopted as input variable of the fuzzy controller and the output scale factors of the MFLC are tuned by the switching variable. Thus, the determination of the input/output scale factors becomes easier and the system performance is significantly improved. The simulation results of a Puma 560 system and a two-inverted pendulum system demonstrate that the attractive features of this proposed approach include a smaller residual error and robustness against nonlinear interactions.
This paper presents a kind of on-line self adjusting learning controller based on fuzzy neural network(FNN), and gives its on-line self adjusting learning algorithm. The simulation results show that the presented meth...
详细信息
ISBN:
(纸本)0780342534
This paper presents a kind of on-line self adjusting learning controller based on fuzzy neural network(FNN), and gives its on-line self adjusting learning algorithm. The simulation results show that the presented method is satisfactory.
暂无评论