New effective features, extracted from single trial EEG data measured on the human scalp capable of hand movement prediction are reported. The envelope and the instantaneous main frequency of the filtered (8–12'H...
详细信息
New effective features, extracted from single trial EEG data measured on the human scalp capable of hand movement prediction are reported. The envelope and the instantaneous main frequency of the filtered (8–12'Hz) EEG signal, calculated by the Hilbert-Transform, are used as features. The EEG responses of right- and left-hand movements are studied. A Learning Vector Quantizer (LVQ) was used to predict the sides of the hand movements. The classification accuracy was about 90 percent.
作者：
B.R. MeijerJ. StigterControl Laboratory
Department of Electrical Engineering Delft University of Technology P.O. Box 5031 NL 2600 GA Delft The Netherlands Knowledge Based System Group
Department of Technical Mathematics and Informatics Delft University of Technology Julianalaan 132 NL 2628 BC Delft The Netherlands
A flexible assembly cell is considered to be an essential building brick for flexible automation of small to medium sized order-based industries. In order to be able to respond adequately to market changes a productio...
详细信息
A flexible assembly cell is considered to be an essential building brick for flexible automation of small to medium sized order-based industries. In order to be able to respond adequately to market changes a production facility that can be reprogrammed or even reconfigured in a very short time is vital. Such a system will have to exhibit some form of intelligent behavior. By intelligent behavior we mean that this system should be able to learn from experience. The experience gained in making subsequent batches of products will be used to increase the efficiency of future batches. Unreliable strategies will be replaced by more reliable ones, actual time data will make it possible to choose a better plan. In this paper a reference model for planning, control and error management for a flexible assembly cell is presented and scheduling and a cost function for the selection of strategies for primitive operations are discussed.
作者：
B.R. MeijerJ. StigterControl Laboratory
Department of Electrical Engineering Delft University of Technology P.O. Box 5031 NL 2600 GA Delft The Netherlands Knowledge Based System Group
Department of Technical Mathematics and Informatics Delft University of Technology Julianalaan 132 NL 2628 BC Delft The Netherlands
A flexible assembly cell is considered to be an essential building brick for flexible automation of small to medium sized order-based industries. In order to be able to respond adequately to market changes a productio...
详细信息
A flexible assembly cell is considered to be an essential building brick for flexible automation of small to medium sized order-based industries. In order to be able to respond adequately to market changes a production facility that can be reprogrammed or even reconfigured in a very short time is vital. Such a system will have to exhibit some form of intelligent behavior. By intelligent behavior we mean that this system should be able to learn from experience. The experience gained in making subsequent batches of products will be used to increase the efficiency of future batches. Unreliable strategies will be replaced by more reliable ones, actual time data will make it possible to choose a better plan. In this paper a reference model for planning, control and error management for a flexible assembly cell is presented and scheduling and a cost function for the selection of strategies for primitive operations are discussed.
The application of a variable structure system (VSS) to the control of a switched reluctance motor (SRM) drive is presented. The operation of an SRM drive is reviewed, and a VSS-based scheme is formulated to control t...
详细信息
The application of a variable structure system (VSS) to the control of a switched reluctance motor (SRM) drive is presented. The operation of an SRM drive is reviewed, and a VSS-based scheme is formulated to control the drive speed. The scheme is then tested by simulation. The results show that the VSS control is effective in reducing the torque ripple of the motor, compensating for the nonlinear torque characteristics, and making the drive insensitive to parameter variations and disturbances.< >
The control characteristics of switched-reluctance motor (SRM) drives are analyzed for operation of the motor in the linear region of its magnetic characteristics. After reviewing the motor operation, we consider the ...
详细信息
The control characteristics of switched-reluctance motor (SRM) drives are analyzed for operation of the motor in the linear region of its magnetic characteristics. After reviewing the motor operation, we consider the current-fed and voltage-fed SRM drives. For both types of drives, the control variables and the related ranges are identified, the relationships between such variables and the average motor torque are calculated, and the torque capability is found. The basic schemes for the speed control of the SRM drives are also formulated.
A novel piecewise linear model of the magnetic characteristics of a switched-reluctance motor is formulated and the procedure to evaluate the model parameters is illustrated. On the basis of the model, the torque-posi...
详细信息
A novel piecewise linear model of the magnetic characteristics of a switched-reluctance motor is formulated and the procedure to evaluate the model parameters is illustrated. On the basis of the model, the torque-position and average torque equations of the motor are calculated and expressed in a normalized form. A significant figure related to the motor performance is then introduced and discussed. The merit of the model over the existing ones in providing accurate results without complicating the analysis is pointed out.
The paper describes the control characteristics of the switched-reluctance motor (SSM) drives, assuming a linear behavior of the magnetic circuit of the motor. After reviewing the principles of operation of a SRM, the...
详细信息
A new knowledge-based method for modeling based on a fuzzy reasoning method has been developed. The method has been based on some ideas about human brain function. A knowledge structure is built up with cells. Before ...
详细信息
A new knowledge-based method for modeling based on a fuzzy reasoning method has been developed. The method has been based on some ideas about human brain function. A knowledge structure is built up with cells. Before the model can be used, a learning phase is required. In this phase a number of time responses of a process are stored in the cells of the knowledge structure. After the learning phase, the system enters an application phase, in which the obtained knowledge is used. The knowledge structure has been organized according to two fundamentally different types of relations: relations in time and relations in value. These relations (connections between the cells) are built up in the learning phase. The values of the input and the output of a process, stored in the cells, and the relations in time preserve the process behavior. The relations in value reflect information about similar responses. They are used to search for the responses which are applied in the fuzzy model, The fuzzy model is based on a comparison of the responses in the knowledge structure with the actual response. For this comparison a fuzzy comparison set is used, which is enlarged if necessary, dependent on the amount of information which is found in the knowledge structure. In the comparison of the responses a factor of linearity is used, so that the responses with the same shape are compared, regardless of their amplitudes. The factor of linearity is bounded by a fuzzy linearity set. This fuzzy linearity set reflects to some extent the nonlinearity of the process. A response in the knowledge structure can be divided into two parts: the actual cell and the cells backwards in time, which are called the past of the response, and the cells forwards in time, which are called the future of the response. The fuzzy model compares the past of the actual response with the past of a number of responses in the knowledge structure. The responses which resemble the actual response are used in the calcula
An analysis of the control characteristics of a switched reluctance motor drive is performed taking into account the saturation of the magnetic circuit of the motor. The drive operation is described, the control varia...
详细信息
An analysis of the control characteristics of a switched reluctance motor drive is performed taking into account the saturation of the magnetic circuit of the motor. The drive operation is described, the control variables and the related ranges are identified, the relationships between the average torque and such variables are calculated, and the torque capability is found. Both the current-source supply and the voltage source supply of the motor are considered. Schemes for speed control are also presented.< >
The method described here is based on our concept of how a human being makes a model of a process. In this method two phases are distinguished: - the first phase, which is a learning phase in which a data base is buil...
详细信息
The method described here is based on our concept of how a human being makes a model of a process. In this method two phases are distinguished: - the first phase, which is a learning phase in which a data base is built up ol an input and a corresponding output. - the second phase, in which the knowledge incorporated in the data base is applied to calculate the outputs of the process corresponding to various inputs. The resulting method also provides an indication about the complexity of the non-linearity of the process and the reliability of the model. This method has been successfully applied to the modeling of different processes, both linear as well as non-linear.
暂无评论