Traditionally fed-batch biochemical process optimization and control uses complicated theoretical off-line optimizers, with no online model adaptation or re-optimization. This study demonstrates the applicability, eff...
详细信息
Traditionally fed-batch biochemical process optimization and control uses complicated theoretical off-line optimizers, with no online model adaptation or re-optimization. This study demonstrates the applicability, effectiveness, and economic potential of a simple phenomenological model for modeling, and an adaptive critic design, generalized dual heuristic programming, for online re-optimization and control of an aerobic fed-batch fermentor. The results are compared with those obtained using a heuristic random optimizer.
An unmanned aerial vehicle (UAV) is a remotely controlled plane with sensing devices that has the capability to fly over terrain in search of enemy activity. We investigate the use of a genetic algorithm to develop ru...
详细信息
An unmanned aerial vehicle (UAV) is a remotely controlled plane with sensing devices that has the capability to fly over terrain in search of enemy activity. We investigate the use of a genetic algorithm to develop rules that guide the UAV by modeling the amount of uncertainty the UAV faces in terms of probability distributions over grid cells representing terrain. We employ the SAMUEL evolutionary learning system to create a set of rules with which to guide the UAV. Results indicate this methodology is capable of creating robust yet consistent sets of rules.
Service Robotics today requires developing a variety of robotic payload systems all installable on a common mobile robotic base. Kiss-lab (Labor fur Kiinstli-che Intelligenz, Graphische Datenverarbeitung und Sys~ tems...
详细信息
The concept of temporally sensitive fuzzy neural networks is introduced based on combining the basic ideas of logic-based neurocomputing with the concept of temporally sensitive connections of neural networks. This ne...
详细信息
The concept of temporally sensitive fuzzy neural networks is introduced based on combining the basic ideas of logic-based neurocomputing with the concept of temporally sensitive connections of neural networks. This new class of neural networks helps address two main issues arising in time-dependent modeling environments. Firstly, these neural networks capture the underlying logical fabric of the problem and, secondly, they provide a useful insight into the temporal nature of the modeling environment. The authors show that the continuously changeable temporal environment gives rise to a logical transformation of the introduced model. This transformation is implemented by triggering from its original AND-like nature to an OR-like version, with this triggering regarded as a function of time. This paper discusses fuzzy decision-making in detail, particularly real estate problem solving.
A fuzzy neural relational model of software quality derived from the McCall hierarchical software quality measurement framework (HSQF), is introduced. The HSQF has three fundamental levels (factors/spl rarr/criteria/s...
详细信息
A fuzzy neural relational model of software quality derived from the McCall hierarchical software quality measurement framework (HSQF), is introduced. The HSQF has three fundamental levels (factors/spl rarr/criteria/spl rarr/metrics) which has a rather natural generalization in the context of fuzzy sets. Vectors of factors, criteria, and metrics are treated as fuzzy sets. On each level, fuzzy objects (fuzzy set and fuzzy relation) are introduced. A learning algorithm is proposed to calibrate the relations at the topmost levels of the software quality model. A learning scenario and detailed learning formulas are given. A brief illustration of the model is also given.
Application of adaptive critic designs for optimization of real-world processes require a model of the process under optimization or feedback from the real process. For optimization of mechanical manufacturing it is o...
详细信息
Application of adaptive critic designs for optimization of real-world processes require a model of the process under optimization or feedback from the real process. For optimization of mechanical manufacturing it is often too expensive and time consuming to use real equipment for the model. However, mathematical models adequately describing real manufacturing processes with realistic noise and interference assumptions may be too difficult to create. We propose to use micro machine tools and micro manipulators as the physical models of real mechanical engineering equipment. They allow us to reduce the cost of experiments and accelerate their speed. We have created prototypes of micro machine tools and work on their use for adaptive critic based optimal control. We describe possible use of adaptive critic designs for optimization of two typical problems of mechanical engineering: shaft cutting and gear fitting on an axle.
A force tracking nonlinear impedance control scheme using a neural network is introduced. Due to the nonlinear characteristics of the proposed control law, stability has been analyzed. The numerical bound of environme...
详细信息
A force tracking nonlinear impedance control scheme using a neural network is introduced. Due to the nonlinear characteristics of the proposed control law, stability has been analyzed. The numerical bound of environment position uncertainty for ensuring robot contact with the environment and to perform desired force tracking has been found. Intensive simulation studies with a three link rotary robot manipulator tracking the surface with a desired force are carried out to confirm the boundary solutions of the proposed scheme under no knowledge of environment surface position and environment stiffness.
A general approximation theorem is proved. It uniformly envelopes both the classical Stone theorem and approximation of functions of several variables by means of superpositions and linear combinations of functions of...
详细信息
A general approximation theorem is proved. It uniformly envelopes both the classical Stone theorem and approximation of functions of several variables by means of superpositions and linear combinations of functions of one variable. This theorem is interpreted as a statement on universal approximating possibilities ("approximating omnipotence") of arbitrary nonlinearity. For the neural networks, our result states that the function of neuron activation must be nonlinear, and nothing else.
暂无评论