In this paper, a Supervised Adaptive Learning-based Fuzzy Controller (ALFC) with Neural Network Identification and Convex Parameterization is designed to identify and control the unmanned vehicle in an autonomous park...
详细信息
ISBN:
(纸本)9781467386838
In this paper, a Supervised Adaptive Learning-based Fuzzy Controller (ALFC) with Neural Network Identification and Convex Parameterization is designed to identify and control the unmanned vehicle in an autonomous parking system. The objective is to achieve robust learning and control while maintaining a low implementation cost. The proposed algorithm design incorporates the following learning and control theorems - non-linear system identification using neural network, fuzzy logic, supervised adaptive learning as well as multiple model based convex parameterization. To demonstrate the algorithm in a more straight forward manner, we are using a real nonlinear unmanned autonomous driving system as an example to apply the algorithm and showing the superior performance of controller. In the autonomous driving system, the proposed method can be used for both estimating and further controlling a desired vehicle speed and steering wheel turning. With a supervised adaptive learning-based method, robustness can be also assured under various operating environments regardless of unpredictable disturbances. The convex parameterization further improves the speed of convergence of the adaptive learning process for the Fuzzy controller by using the multiple models concept. Last but not least, comparative experiments have also demonstrated that systems equipped with the new algorithm are able to achieve faster and smoother convergence.
Only one harmony vector is obtained in each iteration in the classical harmony search algorithm, which affects its search ability. In view of this, we propose an improved harmony search algorithm in this paper. In our...
详细信息
ISBN:
(纸本)9781784660529
Only one harmony vector is obtained in each iteration in the classical harmony search algorithm, which affects its search ability. In view of this, we propose an improved harmony search algorithm in this paper. In our approach, an equivalent number of harmony vectors with a population size are obtained in each iteration, and the newly generated harmony vectors are put into the harmony memory array. Then, all harmony vectors are sorted according to fitness from high to low, and the first half individuals are removed into the next generation of populations. Experimental results show that the proposed approach is obviously superior to the classical one under both the same number of iterations and the same running time, which reveals our approach can effectively extract the characteristics of excellent individuals in the population and obtain satisfactory optimization results.
Grating digital geophone is designed based on grating measurement technique benefiting averaging-error effect and wide dynamic range to improve weak signal detected *** paper introduced the principle of grating digita...
详细信息
Grating digital geophone is designed based on grating measurement technique benefiting averaging-error effect and wide dynamic range to improve weak signal detected *** paper introduced the principle of grating digital geophone and its post signal processing *** signal acquisition circuit use Atmega 32 chip as core part and display the waveform on the Labwindows through the RS232 data *** transform is adopted this paper to filter the grating digital geophone' output signal since the signal is unstable. This data processing method is compared with the FIR filter that widespread use in current *** result indicates that the wavelet algorithm has more advantages and the SNR of seismic signal improve obviously.
Predicting gas outburst in coalmine extraction face accurately is an effective method to prevent gas outburst *** there are the features of suddenness,unevenness,uncertainty and dynamic in gas outburst,the existing pr...
详细信息
Predicting gas outburst in coalmine extraction face accurately is an effective method to prevent gas outburst *** there are the features of suddenness,unevenness,uncertainty and dynamic in gas outburst,the existing prevention method should be improved in accuracy and *** in the paper the predicted model of gas outburst is built combining fuzzy neural network and Dempster-Shafer(D-S) evidence theory,and the model specifically introduces the overall structure design of gas outburst predicted model,the selection of gas outburst evaluation indicators,the design of fuzzy neural network unit and the design of D-S evidence theory *** eight key factors including the thickness of coal layer,the geological structure types of coal and the gas pressure of coal layer are selected as the evaluation indicators of gas outburst,and the preliminary judgment of gas outburst state in local point of mining working face,is made by fuzzy neural network,and then global judgment of gas outburst state in mining working face is made based on D-S evidence *** simulated result shows that this method can make accurate judgments of gas outburst state grade,and regarding with the judgments of the three kinds of gas outburst state,the accuracy error is less than 0.0048% and the uncertainty value approximates to 0.
Under the background of mobile Internet era, the application requirements of indoor positioning technology is increasingly urgent,and accurate positioning information has become an important prerequis
Under the background of mobile Internet era, the application requirements of indoor positioning technology is increasingly urgent,and accurate positioning information has become an important prerequis
This paper proposed a solution based on quantum-behaved particle swarm optimization(QPSO) to solve the optimization problem of oil-water well measure *** first,it proposed a new quantum-behaved particle swarm optimiza...
详细信息
This paper proposed a solution based on quantum-behaved particle swarm optimization(QPSO) to solve the optimization problem of oil-water well measure *** first,it proposed a new quantum-behaved particle swarm optimization algorithm based on the square potential well from quantum *** according to the construction situation,it took the 0-1 coding of oil-water *** the objective functions and constrains satisfying combination of various measures,it set up fitness function *** the optimization process,it introduced mutation strategy to increase the diversity of *** experimental results show that it obtains satisfactory optimization results with this *** it reveals that quantum intelligent optimization algorithm has broad application prospect in oilfield development projects.
The diverse world of machine learning applications has given rise to a plethora of algorithms and optimization methods, finely tuned to the specific regression or classification task at hand. We reduce the complexity ...
详细信息
ISBN:
(纸本)9781510838819
The diverse world of machine learning applications has given rise to a plethora of algorithms and optimization methods, finely tuned to the specific regression or classification task at hand. We reduce the complexity of algorithm design for machine learning by reductions: we develop reductions that take a method developed for one setting and apply it to the entire spectrum of smoothness and strong-convexity in applications. Furthermore, unlike existing results, our new reductions are optimal and more practical. We show how these new reductions give rise to new and faster running times on training linear classifiers for various families of loss functions, and conclude with experiments showing their successes also in practice.
We present a study on minimizing non-renewable energy for the Internet. The classification of renewable and nonrenewable energy brings in several challenges. First, it is necessary to understand how the routing system...
详细信息
ISBN:
(纸本)9781467399548
We present a study on minimizing non-renewable energy for the Internet. The classification of renewable and nonrenewable energy brings in several challenges. First, it is necessary to understand how the routing system can distinguish the two types of energy in the power supply. Second, the routing problem changes due to renewable energy;and so do the algorithm designs and analysis. We first clarify the model of how routers can distinguish renewable and non-renewable energy supporting their power supply. This cannot be determined by the routing system alone, and involves modeling the energy generation and supply of the grid. We then present the router power consumption model, which has a fixed startup power and a dynamic traffic-dependent power. We formulate a minimum non-renewable energy routing problem, and two special cases representing either the startup power dominates or the traffic-dependent power dominates. We analyze the complexity of these problems, develop optimal and sub-optimal algorithms, and jointly consider QoS requirements such as path stretch. We evaluate our algorithms using real data from both National and European centers. As compared to the algorithms minimizing the total energy, our algorithms can reduce the non-renewable energy consumption for more than 20% under realistic assumptions.
This work presents an algorithm for designing the optimal robust saturated output feedback controller for the two-link planar robot with a spring between two links by the Attractive Ellipsoid Method serving for class ...
详细信息
ISBN:
(纸本)9781467357159
This work presents an algorithm for designing the optimal robust saturated output feedback controller for the two-link planar robot with a spring between two links by the Attractive Ellipsoid Method serving for class of uncertain "quasi-Lipschitz" dynamics. The Attractive Ellipsoid Method (AEM) application permits to describe the class of nonlinear feedbacks containing a saturation operator that guarantees a boundedness of all possible trajectories around the origin. Here we consider more general types of nonlinear bounded feedbacks which can be corrected (adjusted) on-line during a control process. The optimization of feedback within this class of controllers is associated with the selection of the feedback parameters which provide the trajectory converges within an ellipsoid of a "minimal size".
Programming language and algorithm design are core courses in computer *** are the foundation of software ***,in the experiment teaching of courses there are still many *** paper first analyzes those problems,then som...
详细信息
Programming language and algorithm design are core courses in computer *** are the foundation of software ***,in the experiment teaching of courses there are still many *** paper first analyzes those problems,then some advantages are discussed when ACM contest mode is brought in those courses;and last an online judge system is introduced in detail,including system design,implementation and *** results of the system prove that reform experiment teaching can effectively improve the students’ programming ability and study interest.
暂无评论