The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
A new control scheme based on neural network and traditional PID controller is proposed to improve the performance of precision stage in SPMs. The mathematical model is set up by analyzing the principle of the piezoelectric actuator. Mechanical parameters are identified online by a neural estimator. The traditional PID controller is replaced by a neural network PID controller. Weights in the network...
Vibration suction method (VSM) is a novel suction strategy for wall climbing robot. Regular vibration can improve the suction cup's adsorption capacity. Through the study of the first vibration suction robotic foot (VSRF I) the applicability of VSM was verified while the suction capability, safety, and wall adaptability of it was not well enough. Based on these, a new vibration suction robotic foot...
Large variations of the control variable add to plant wear and tear. In view of this fact, this paper provides a plant-friendly PID controller design method by minimizing the weighted sum of the integral of squared time-weighted error and the integral of squared time-weighted derivative of the control variable with respect to a step set-point change. The robustness of the system is guaranteed by a...
For ship steering systems with the nonlinear uncertain parameters, a concise nonlinear adaptive robust control (CNARC) derived from the backstepping design method is constructed with the close-loop gain shaping algorithm (CGSA) via aid of the adaptive strategy in this paper. To overcome the high conservative of the nonlinear robust control scheme, which makes no use of the feedback information of...
In this paper, we investigate a novel adaptive design approach for nonlinear systems as an exploration of the new challenging topic on dealing with both parametric and nonparametric internal uncertainties in adaptive control of discrete-time nonlinear systems. The existence of both two kinds of uncertainties makes it very difficult or even impossible to apply the traditional recursive identification...
Approximate dynamic programming method is a combination of neural networks, reinforcement learning, as well as the idea of dynamic programming. It is an online control method which bases on actual data rather than a precise mathematical model of the system. This method is suitable for the optimal control of nonlinear systems, and can avoid the problem of dimension disaster. It can effectively solve...
As a higher layer protocol based on CAN (Controller Area Network), SAE J1939 has specified SP (Suspect Parameter) and PG (Parameter Group) which respectively represent signal exchanged between ECUs (Electronic Control Units) and message containing a set of SPs. There is temporal characteristic constraint, such as period and deadline, between SP and PG in SAE J1939-based passenger car information integrated...
Based on in-vehicle network technology and ECU (electronic control unit), passenger car information integrated control system implements correlative real-time control of passenger car functions. ECU is the core of system function implementation. Currently, passenger car ECU is designed according to special function requirement. Passenger car model has diversity because of the difference of market...
The probabilistic roadmap method (PRM) has been successfully implemented in the motion planning field. But, when the sampled points are being connected to each other, collision check is an inevitable step, which is the most time-consuming operation of this method. A new method is proposed, in which the collision check operation is not necessary, and speed up the path planning operation. Based on the...
The background of this paper is about water quality monitoring and pollution source positioning as the main function of telemetry for large-scale drainage basins. The paper introduces wireless sensor network technology, designs and proposes an overall architecture of a hydrologic telemetry and pollution tracking and positioning system based on the public mobile communications network, and chooses...
This paper aims to establish a dynamic vessel fleet planning model in uncertain circumstance, which offers the shipping companies the appropriate development strategy. Based on the characteristics of the shipping market, we consider the market volatility faced by the shipping companies on the strategies of the fleet planning. Firstly, we establish a forecast model to predict the future shipping demand...
Oscillating motion of ship makes a great impact on the safety of ocean shipping of LNG tank, so a simulation system is built to study the ship oscillation under different conditions. We construct several groups of simulation environment and an algorithm based on direction spectrum to describe ocean wave spectrum according to seakeeping theory, ship oscillation simulation system based on this algorithm...
Based on the model-following adaptive neural network control theory, a gust load alleviation controller for civil airplanes by direct force control is proposed. For Dryden power spectral density function, the rational spectral theory is used to set up the linear state-space model of the vertical gust. The effects of gust to aircraft are considered to develop the synthesized system model of aircraft...
Electrocardiogram (ECG) signal has been widely used in cardiac pathology to detect heart disease. In this paper, wavelet neural network (WNN) is studied for ECG signal modeling and noise reduction. WNN combines the multi-resolution nature of wavelets and the adaptive learning ability of artificial neural networks, and is trained by a hybrid algorithm that includes the adaptive diversity learning particle...
Nature inspires many interesting ideas of solving our day to day problems. In this paper, we take inspiration from the chemotaxis behaviour of the bacterium and create a novel algorithm. Simulated results show the feasibility of using a bacterial inspired algorithm in finding a pollution source and then generating a visual 3D representation of the pollutant. We believe that by providing a visual 3D...
By using function one direction S-rough sets, this paper presents concepts of f-separation law, F-separation law, f-separation law dependence and F-separation law dependence. Based on these concepts above, this paper proposes the separation-dependence theorem of f-separation law, the separation-dependence theorem of F-separation law, the separation-dependence theorem, and the criteria of law separation...
Security and economical operation of the traction transformer is a significant guarantee for electric railway with growing apace. Based on analysis of the economical operation principle with an instance, three kinds of power losses due to transformer and the outlay are discussed. Meanwhile, this paper puts forward an economical operation monitoring system for traction transformers, which links to...
Vehicle scheduling optimization of hazardous materials is one of effective means to prevent accidents and reduce the loss of lives and property. This paper studies the vehicle scheduling problem of Hazardous materials based on the transportation risks which vary with time, taking into account the cost constraints and allowing for waiting at the nodes of the network, that is, our problem is a risk-based...
This paper is concerned with the dynamic pricing problems of a duopoly case in electronic retail markets. Combined with the concept of performance potential, the simulated annealing Q-learning (SA-Q) and the win-or-learn-fast policy hill climbing algorithm (WoLF-PHC) are used to solve the learning problems of multi-agent systems with either average- or discounted-reward criteria, under the case that...
It is a research trend to incorporate neural network with genetic algorithm for solving technical and practical problems. As a single genetic algorithm has slow convergent speed and it is easily falling into local optimum, this paper presents a genetic and simulated annealing hybrid algorithm, which searches the neighborhood using chaos variables. And this paper trains a neural network using the single...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.