A paper deals with application of stochastic methods for dynamic neural network training. The considered network is composed of dynamic neurons, which contain inner feedbacks. This network can be used as a part of a f...
详细信息
A paper deals with application of stochastic methods for dynamic neural network training. The considered network is composed of dynamic neurons, which contain inner feedbacks. This network can be used as a part of a fault diagnosis system to generate residuals. Up-to-date training algorithms, based on the classical back propagation, suffer from entrapment in local minima of an error function. Two stochastic algorithms are tested as training algorithms to overcome these difficulties. Efficiency of the proposed learning methods is checked using data recorded at Lublin Sugar Factory, Poland.
This paper addresses the problem of implementing predictive controllers for supervisory level control systems. In this configuration the manipulated variables calculated by the Predictive controller are used as comman...
详细信息
This paper addresses the problem of implementing predictive controllers for supervisory level control systems. In this configuration the manipulated variables calculated by the Predictive controller are used as command signals for the Distributed control Systems, which provide references to the operator-tuned local PID controllers that act on the physical system. This structure introduces the problem of loosing of performance if the inner-loop controllers are re-tuned. The paper discusses the solution to this problem based on the use of a two-degrees-of-freedom structure in the inner loop, that separates open and closed-loop properties. Both design guidelines and robustness issues are discussed.
The complexity of technical systems that need to be designed and researched is gradually increasing. In order to be competitive and to satisfy the demands of the market, thorough analyses and early risk assessment of ...
详细信息
The complexity of technical systems that need to be designed and researched is gradually increasing. In order to be competitive and to satisfy the demands of the market, thorough analyses and early risk assessment of the systems are required. System investigation might involve some changes that might entail the redesigning or even redeveloping of some parts of the system. Modifications are usually expensive, time consuming and risky. Consequently, there is a need for methods that examine the possible effects of the modifications before investing in the alteration of the system. There are four methods that are used to study the behavior of a system: simulation, emulation, real-time control and prototyping. In this paper we discuss an approach for a distributed architecture that supports these four testing methods and the interaction between them.
Substantial progress has been made recently towards designing, building and test-flying remotely piloted Micro Air Vehicles (MAVs) and small UAVs. We seek to complement this progress in overcoming the aerodynamic obst...
详细信息
Substantial progress has been made recently towards designing, building and test-flying remotely piloted Micro Air Vehicles (MAVs) and small UAVs. We seek to complement this progress in overcoming the aerodynamic obstacles to flight at very small scales with a vision-guided flight stability and autonomy system, based on a robust horizon detection algorithm. In this paper, we first motivate the use of computer vision for MAV autonomy, arguing that given current sensor technology, vision may be the only practical approach to the problem. We then describe our statistical vision-based horizon detection algorithm, which has been demonstrated at 30 Hz with over 99.9% correct horizon identification. Next, we develop robust schemes for the detection of extreme MAV attitudes, where no horizon is visible, and for the detection of horizon estimation errors, due to external factors such as video transmission noise. Finally, we discuss our feedback controller for self-stabilized flight, and report results on vision-based autonomous flights of duration exceeding ten minutes.
We present a method for recognizing the existence of outer frames in binary trademark images and segmenting a trademark that contains an outer frame into the frame and its inner figure, even if both touch. This focuse...
详细信息
It is concluded from the results of testing the frequency characteristics of the sub micron precision machine tool servo control system, that the existence of several oscillating modalities is the main factor that aff...
详细信息
It is concluded from the results of testing the frequency characteristics of the sub micron precision machine tool servo control system, that the existence of several oscillating modalities is the main factor that affects the performance of the control system. To compensate for this effect,several concave filters are utilized in the system to improve the control accuracy. The feasibility of compensating for several oscillating modalities with a single concave filter is also studied. By applying a modified Butterworth concave filter to the practical system, the maximum stable state output error remains under ±10 nm in the closed loop positioning system.
This paper shows design & implementation of adaptive neural networks controller for DC Motor Speed control System. DC Motor is actuated by Pulse Width Modulation (PWM)-based H-Bridge actuator. By using certain lea...
详细信息
This paper shows design & implementation of adaptive neural networks controller for DC Motor Speed control System. DC Motor is actuated by Pulse Width Modulation (PWM)-based H-Bridge actuator. By using certain learning methods to the networks, changing plant's parameter can be estimated and used to produce appropriate control action. The experiment shows that the controller conforms the adaptive control scheme, although there are flaws which related to feedback resolution. The most interesting result is that the implementation circuit is based on very simple 8-bit microcontroller system.
The Internet explosion impels the extensive demands for distributed multimedia presentations (DMPs), which provide multiple users with QoS-controlled multimedia services under multicast communications, such as media d...
详细信息
The formation of a convoy of cars (platoon) by linking these electronically (soft platooning) or mechanically (hard platooning) are two of the most researched methods in highway transportation systems, particularly th...
详细信息
The formation of a convoy of cars (platoon) by linking these electronically (soft platooning) or mechanically (hard platooning) are two of the most researched methods in highway transportation systems, particularly the first one that is the base of the Automated Highway Systems. This paper focuses on the advantages and disadvantages of both systems and introduces the main technical problems of them. The need for new traffic rules is examined in the case of truck train travels on a multi-lane highway. The kingpin sliding technique is also proposed to face the off-tracking phenomenon of multi-articulated vehicles. Some conclusions from the comparison of the two systems are also given
The motion of a multi-body autonomous robot as well as of a train-like multi-articulated transportation vehicle is characterized by the deviation of the path of each intermediate vehicle from that of the leading one (...
详细信息
The motion of a multi-body autonomous robot as well as of a train-like multi-articulated transportation vehicle is characterized by the deviation of the path of each intermediate vehicle from that of the leading one (off-tracking). This paper proposes an intelligent controller for the elimination of the off-tracking phenomenon, in both robotic and transportation multi- articulated vehicles. By using a sliding kingpin technique that allows articulated semi-trailers to follow closely the tractor's path, and taking into consideration the heuristic knowledge that stems from the driving practice and the tests' experience, a fuzzy rule-based controller has been developed to determine the sliding distance and the sliding rate of the kingpin mechanism. Simulation results for various cases, without and with the sliding kingpin system showed that off-tracking elimination is achieved to a significant degree through the use of intelligent controller.
暂无评论