This paper presents the use of Artificial Neural Networks to diagnose degraded behaviours in Wire Electrical Discharge Machining (WEDM). The detection in advance of the degradation of the cutting process is crucial si...
详细信息
This paper presents the use of Artificial Neural Networks to diagnose degraded behaviours in Wire Electrical Discharge Machining (WEDM). The detection in advance of the degradation of the cutting process is crucial since this can lead to the breakage of the cutting tool (the wire), reducing the process productivity and the required accuracy. Concerning this, previous investigations have identified different types of degraded behaviors in two commonly used workpiece thicknesses (50 and 100 mm). This goal was achieved by monitoring different functions of the characteristic variables of the discharges. However, the thresholds achieved by these functions depended on the workpiece thickness. Consequently, the main objective of this work is to detect the process degradation in different workpiece thicknesses using one unique empirical model Since Neural network techniques are appropriate for stochastic and nonlinear nature processes, its use is investigated here to cope with different workpiece thicknesses. The results of this work show a satisfactory performance of the presented approach.
This contribution aims at unifying two recent trends in applied particle filtering (PF). The first trend is the major impact in simultaneous localization and mapping (SLAM) applications, utilizing the FastSLAM algorit...
详细信息
This contribution aims at unifying two recent trends in applied particle filtering (PF). The first trend is the major impact in simultaneous localization and mapping (SLAM) applications, utilizing the FastSLAM algorithm. The second one is the implications of the marginalized particle filter (MPF) or the Rao-Blackwellized particle filter (RBPF) in positioning and tracking applications. Using the standard FastSLAM algorithm, only low-dimensional vehicle models are computationally feasible. In this work, an algorithm is introduced which merges FastSLAM and MPF, and the result is an algorithm for SLAM applications, where state vectors of higher dimensions can be used. Results using experimental data from a UAV (helicopter) are presented. The algorithm fuses measurements from on-board inertial sensors (accelerometer and gyro) and vision in order to solve the SLAM problem, i.e., enable navigation over a long period of time.
Many papers have demonstrated that interpolation methods can often enlarge feasible regions significantly while also reducing computational complexity in MPC algorithms (Bacic et al, 2003;Rossiter et al, 2004). Howeve...
详细信息
To improve the robustness of high-precision servo systems, quantitative feedback theory (QFT) which aims to achieve a desired robust design over a specified region of plant uncertainty is proposed. The robust design...
详细信息
To improve the robustness of high-precision servo systems, quantitative feedback theory (QFT) which aims to achieve a desired robust design over a specified region of plant uncertainty is proposed. The robust design problem can be solved using QFT but it fails to guarantee a high precision tracking. This problem is solved by a robust digital QFT control scheme based on zero phase error (ZPE) feed forward compensation. This scheme consists of two parts: a QFT controller in the closed-loop system and a ZPE feed-forward compensator. Digital QFT controller is designed to overcome the uncertainties in the system. Digital ZPE feed forward controller is used to improve the tracking precision. Simulation and real-time examples for flight simulator servo system indicate that this control scheme can guarantee both high robust performance and high position tracking precision.
This paper presents an investigation into the development of a noise cancellation system using genetic algorithms (GAs). A multi-input multi-output (MIMO) control structure and associated control algorithm are develop...
详细信息
ISBN:
(纸本)9781605603858
This paper presents an investigation into the development of a noise cancellation system using genetic algorithms (GAs). A multi-input multi-output (MIMO) control structure and associated control algorithm are developed on the basis of optimum cancellation of noise at a set of observation points. The algorithm is realised using GA and its performance assessed in the cancellation of noise in a free-field medium. The global search technique of GA is used to select the system component configuration for enhanced performance of an active noise control (ANC) system. In this investigation, randomly selected parameters are optimized for different, arbitrarily chosen locations for system components by applying the working mechanism of GA. The percentage of reinforcement that occurs in the medium is adopted as the objective function value. The MIMO GA-ANC algorithm is implemented and simulation results are presented to asses the performance of the system, with single frequency noise. The results are presented for analysis using a graphical user interface, to allow the user asses the system design in an interactive manner.
In this paper are presented some new concepts of control applied in Power systems. Are given the architectures and methodologies based on the agents theory. The complexity of Power systems is included into a new parad...
详细信息
ISBN:
(纸本)9783902661388
In this paper are presented some new concepts of control applied in Power systems. Are given the architectures and methodologies based on the agents theory. The complexity of Power systems is included into a new paradigm - Complex Adaptive systems - and the modelling and control of Power systems based on intelligent agents are considered. Some concepts on hierarchical and heterarchical architectures which include different intelligent techniques are also presented in this paper.
In the high speed range, vector control of rotor flux orientation of an induction machine implements good performance. However, the performance in low speed rang deteriorates because of the inaccurate estimation of ro...
详细信息
In this paper are presented some new concepts of control applied in Power systems. Are given the architectures and methodologies based on the agents theory. The complexity of Power systems is included into a new parad...
详细信息
In this paper are presented some new concepts of control applied in Power systems. Are given the architectures and methodologies based on the agents theory. The complexity of Power systems is included into a new paradigm – Complex Adaptive systems – and the modelling and control of Power systems based on intelligent agents are considered. Some concepts on hierarchical and heterarchical architectures which include different intelligent techniques are also presented in this paper.
This paper addresses the optimization of safety instrumented systems design based on a RAMS+C approach using a multi-objective genetic algorithm. The design includes optimization of safety and reliability measures aga...
详细信息
Agent-based models are widely used for the simulation of systems from several domains (biology, economics, meteorology, etc). In biology agent-based models are very useful for predicting the social behaviour of system...
详细信息
暂无评论