In this paper, a HGA fuzzy supervisory PI controller using hierarchical genetic algorithms is developed and implemented for controlling the top and bottom product quality of a nonlinear, multi-input multi-output binar...
详细信息
In this paper, a HGA fuzzy supervisory PI controller using hierarchical genetic algorithms is developed and implemented for controlling the top and bottom product quality of a nonlinear, multi-input multi-output binary distillation column when the disturbances enter the column in the form of the changes in feed flow rate. Two conventional PI controllers, one for the bottom product composition and another for the top product composition, are used together in a decentralized control scheme to per form dual composition control. Hierarchical genetic algorithms are used to derive the optimal number and shape of membership functions and fuzzy rules of a fuzzy supervisory system that adapts the parameters of the PI controllers. The real-time implementation results show the effectiveness of the proposed method
By means of agent oriented software engineering flexible, adaptive automation systems can be developed. An open question is, nevertheless, how could the specific requirements on automation systems, in particular relat...
详细信息
Common engineering approaches and modelling approaches from software engineering are brought together. For the domain of processautomation, i.e. product and plant automation, an implementation oriented approach for a...
详细信息
Until today humans using computers to control technical systems must learn how to use and interact with a system that only understands numerical input and produces numerical output. This requires a high level of abstr...
详细信息
Until today humans using computers to control technical systems must learn how to use and interact with a system that only understands numerical input and produces numerical output. This requires a high level of abstraction and causes a loss of necessary "feeling" how the real process works. With multimedia computing technology we are now able to reduce the level of abstraction again. By using all major human senses in combination, that are, auditory, visual, haptic and olfactory modalities, we are able to implement simple and intuitive control applications for technical equipment. This requires new strategies for the design of human computer interaction. The state of development and use of multimodal interactive user interfaces are presented. Aspects and issues of human engineering concerned with the different modalities are discussed and new paradigms of human computer interaction are introduced.
This work will present the state of development and use of multimodal interactive user interfaces. Advanced human-to-process communication uses virtual- and augmented-reality-Systems to achieve intuitive process contr...
详细信息
This work will present the state of development and use of multimodal interactive user interfaces. Advanced human-to-process communication uses virtual- and augmented-reality-Systems to achieve intuitive processcontrol again. Hypermedia learning systems, catalogs and simulators improve operator skills. All this leads to a new paradigm of human computer interaction. In order to achieve simple and intuitive control of any technical equipment, all abilities of human communication should be efficiently combined.
According to the multi-model approach a nonlinear dynamical process is approximated in different working points by local valid linear models. The global valid model output is calculated as the weighted sum of the sub-...
详细信息
This paper presents two soft-sensing models for predicting the product yields profile and the cracking degree of an ethylene pyrolysis furnace. The model based on single neural network with only one hidden layer train...
详细信息
ISBN:
(纸本)0780386531
This paper presents two soft-sensing models for predicting the product yields profile and the cracking degree of an ethylene pyrolysis furnace. The model based on single neural network with only one hidden layer trained by Levenberg-Marquardt algorithm with regularisation was first developed. It was found that the single neural network lack generalisation capability in that they can give undesirable performance when applied to unseen data. To improve the generalisation capability of the soft-sensing model, multi-model soft-sensors based on bootstrap aggregated neural networks with sequential training are used. In the sequential training of bootstrap aggregated networks, the first network is trained to minimise its prediction error whereas the rest of the networks are trained not only to minimise their prediction errors but also minimise the correlation among the trained networks. The overall output is obtained by combining all the individual networks. Application results show that the multi-model soft-sensors possess good generalisation capability in that they give good performance when applied to unseen data.
A prediction control algorithm is presented based on least squares support vector machines (LS-SVM) model for a class of complex systems with strong nonlinearity. The nonlinear off-line model of the controlled plant i...
详细信息
A prediction control algorithm is presented based on least squares support vector machines (LS-SVM) model for a class of complex systems with strong nonlinearity. The nonlinear off-line model of the controlled plant is built by LS-SVM with radial basis function (RBF) kernel. In the process of system running, the off-line model is linearized at each sampling instant, and the generalized prediction control (GPC) algorithm is employed to implement the prediction control for the controlled *** obtained algorithm is applied to a boiler temperature control system with complicated nonlinearity and large time *** results of the experiment verify the effectiveness and merit of the algorithm.
process model based methods to detect faults in a hydraulic linear servo axis by measurement of up to five variables are presented. The faults that are detected include gas enclosures in the hydraulic fluid, such as a...
详细信息
process model based methods to detect faults in a hydraulic linear servo axis by measurement of up to five variables are presented. The faults that are detected include gas enclosures in the hydraulic fluid, such as air, vapour and foam. The control edges and the valve spool are also monitored in order to detect faults such as erosion of the control edges and grooving of the valve spool. Furthermore, the leakage flow between the cylinder chambers and to the surroundings are monitored, which allows to detect damages of the sealing between the cylinder chambers and between the cylinder and the pushrod. The external mechanical load and the valve spool dynamics are also included in the fault detection and diagnosis approach.
By means of agent oriented software engineering, flexible, adaptive automation systems can be developed. An open question is, nevertheless, how could the specific requirements on automation systems, in particular rela...
详细信息
By means of agent oriented software engineering, flexible, adaptive automation systems can be developed. An open question is, nevertheless, how could the specific requirements on automation systems, in particular related to dependability and real-time features, be considered. In this paper an approach for the integration of such features in the development of flexible agent oriented automation systems is presented
暂无评论