This paper presents a novel approach devoted to the design of feed forward hybrid neural models. Graph genetic programming techniques are used to provide a flexible construction of partially interconnected neural stru...
详细信息
ISBN:
(纸本)9781424474325;9781424474332
This paper presents a novel approach devoted to the design of feed forward hybrid neural models. Graph genetic programming techniques are used to provide a flexible construction of partially interconnected neural structures with heterogeneous layers built as combinations of local and global neurons. By exploiting the inner modularity and the parallelism of the neural architectures, the approach suggests the encryption of the potential mathematical models as directed acyclic graphs and defines a minimally sufficient set of functions which guarantees that any combination of primitives encodes a valid neural model. The exploration capabilities of the algorithm are heightened by means of customized crossovers and mutations, which act both at the structural and the parametric level of the encrypted individuals, for producing offspring compliant with the neural networks' formalism. As the parameters of the models become the parameters of the primitive functions, the genetic operators are extended to manage the inner configuration of the functional nodes in the involved hierarchical individuals. The applicability of the proposed design algorithm is discussed on the identification of an industrial nonlinear plant.
The spreading of brushless DC (BLDC) motors has imposed the need for efficient and low cost motor control drives. In this paper, a low cost digital controller is presented. For experimental testing, the controller is ...
详细信息
The spreading of brushless DC (BLDC) motors has imposed the need for efficient and low cost motor control drives. In this paper, a low cost digital controller is presented. For experimental testing, the controller is implemented inside a field programmable gate array (FPGA) device. The developed design is validated in a modular fashion by logic simulation and experimental results are provided. The main contribution is the presented controller design methodology for FPGA implementation.
This contribution reveals some problems concerning the use of holonic manufacturing systems. These regard both the design and implementation phases and they can be discovered since the system analysis. A new Petri net...
详细信息
This contribution reveals some problems concerning the use of holonic manufacturing systems. These regard both the design and implementation phases and they can be discovered since the system analysis. A new Petri net based model is proposed for the holonic system organized according to the Contract Net Protocol coordination scheme. Certain weaknesses are discovered both at the model and implementation levels and some solutions are sketched. These are illustrated with a case from an experimental manufacturing environment that could exemplify the problems regarding the resource sharing and holons' coordination.
Reducing fuel consumption, lowering emissions and improving driveability represent the main interests nowadays in automotive research centres from both academic and industry fields. The purpose is to develop more comp...
详细信息
Reducing fuel consumption, lowering emissions and improving driveability represent the main interests nowadays in automotive research centres from both academic and industry fields. The purpose is to develop more complex and accurate models for the automotive drivetrain in order to design and to apply different control strategies. In this paper, starting from the relations that describe the dynamical behaviour for each subsystem of an automotive powertrain, a nonlinear state-space model for a drivetrain with backlash was developed. The model was then implemented in Matlab/Simulink and a PID cascade controller was proposed in order to maintain a desired wheel speed trajectory.
The paper suggests a customized elite based genetic programming technique for the identification of complex nonlinear systems. The models generated by the proposed method are nonlinear, linear in parameters, as the un...
详细信息
The paper suggests a customized elite based genetic programming technique for the identification of complex nonlinear systems. The models generated by the proposed method are nonlinear, linear in parameters, as the universal approximation capacities of such a mathematical formalism have been rigorously proven. To better exploit the models' parameter wise linearity, the authors propose a memetic approach that combines the stochastic structural transitions caused by enhanced genetic operators, with a deterministic parameter computation routine based on QR decomposition. This symbiosis assures a quasi simultaneous model structure and parameters selection and heightened search space exploration capabilities. To better fit the requirements of systems identification, the problem is formulated as a multiobjective optimization one, employing accuracy and parsimony assessment criteria. Two elitist evolutionary procedures have been implemented to obtain a solution, each featuring original contributions: the first one employs a dynamic clustering mechanism aimed at encouraging specific solutions of interest for the problem at hand, whilst the second is oriented towards maintaining population diversity by means of similarity analysis. The practical efficiency of the described methods is demonstrated relative to a multivariable test system with delayed inputs and a complex industrial plant.
Automotive engineers are continuously exploring various transmission technologies to increase vehicle performance, fuel economy and safety. The most common control devices inside the transmission are hydraulic actuate...
详细信息
Automotive engineers are continuously exploring various transmission technologies to increase vehicle performance, fuel economy and safety. The most common control devices inside the transmission are hydraulic actuated clutches. In this paper a state-space model for a wet clutch actuated by an electro-hydraulic valve used by Volkswagen for automatic transmission is presented. The developed model was implemented in Matlab-Simulink and was validated against the data obtained from a test bench provided by Continental Automotive Romania. The simulations are very similar to the experimental data proving that the modeling approach is suitable to this kind of clutch actuated by an electro-hydraulic pressure reducing valve.
A key component of the automotive industry is represented by clutch control technology, a central element in gear shifting, playing an important role in assuring improved safety, drivability, comfort and fuel economy....
详细信息
A key component of the automotive industry is represented by clutch control technology, a central element in gear shifting, playing an important role in assuring improved safety, drivability, comfort and fuel economy. Yet, in modern vehicles, control signals and sensors measurements are exchanged by control system components using a network based type of communication. In this paper a new Networked Predictive control Strategy is proposed in order to decrease the influence of the variable time delay induced in the NCS on the control performance of the electro-hydraulic actuated wet clutch. The performances of the proposed method are demonstrated by simulation results and corresponding comparisons prove the significance of this method.
Some points regarding the design and implementation of holonic manufacturing systems are presented. As the holonic approach supposes a distributed architecture regarding both planning and execution, certain methods an...
详细信息
This paper proposes a way of implementing a deadbeat controller in FPGA. The focus is on the FPGA implementation of the digital controller. The emphasis is on the software tools for design and simulation of FPGA based...
详细信息
The paper proposes a new method for sensorial integration within manufacturing systems. The control scheme is a holonic one, namely a PROSA reference architecture is considered. Some principles regarding the way the c...
详细信息
暂无评论