Showing papers in "Engineering Applications of Artificial Intelligence in 1995"

TL;DR: A backpropagation-based neural network was trained to identify the presence of the appropriate primitives in a trend of noisy process data and a process grammar which can utilize both contextual and non-contextual information to perform error correction and explanation generation has been developed.

TL;DR: The results of the computational experiments show that simulated annealing is a suitable approach for solving this very difficult combinatorial optimization problem, in the sense that it provides feasible and low-cost solutions within reasonable CPU times.

TL;DR: A neural-network-based computational scheme to generate optimized robotic assembly sequences for an assembly product using both a neural network with functional link nets, and an expert system is presented.

TL;DR: This paper presents a procedure for utilizing genetic algorithms in an LMS approach to curve fitting by combining the search capabilities of a genetic algorithm with the curve fitting capabilities of the LMS method.

TL;DR: A feature-extraction algorithm, a frequency analyzer, was developed, and the features are formulated as the inputs of an artificial neural network using backpropagation, in order to speed up the training speed.

TL;DR: It is found that much smaller errors are obtained as compared to backpropagation nets with the same degrees of freedom, the mapping depends only slightly upon the actual values of the hidden weights, provided the net has sufficient neurons, and the speed of computation is incomparably much faster than with back Propagation.

TL;DR: A simulated-annealing-based optimization algorithm for power-system optimization problems that possesses the ability to determine the global optimum solution to the problem of the economic dispatch of electric power.

TL;DR: Two new computing models, namely a fuzzy expert system and a hybrid neural network-fuzzy expert system for time series forecasting of electric load, are presented and the results for a typical winter day are given to confirm the effectiveness of these models.

TL;DR: How function approximation techniques can be used to solve nonlinear estimation and system identification problems is explained and a new technique for function approximation via fuzzy systems called “modified learning from examples” is outlined.

TL;DR: A new tool-life criterion depending on a pattern-recognition technique is proposed and the experimental results show that this criterion is applicable to tool condition monitoring in a wide range of cutting conditions.

TL;DR: Examination of the suitability of the generalized data rule in training artificial neural networks (ANN) for damage identification in structures finds some heuristics are proposed for the design of neural networks for damage Identification in structures.

TL;DR: In this article, an internal model control (IMC) scheme using a fuzzy neural network for process modeling is proposed, which is most useful in an environment where first-principles-based descriptions are difficult to obtain, but partial knowledge about the process is known and input-output data is available.

TL;DR: This paper shows how to utilize GAs to perform on-line adaptive state estimation for nonlinear systems and constructs a genetic adaptive observer (GAO) where a GA evolves the gains in a state observer in real time so that the state estimation error is driven to zero.

TL;DR: This hybrid approach shows significantly better performance than the “black box” method, and almost as good a performance as a nonlinear IMC based on an exact mathematical model.

TL;DR: A real-time navigation and obstacle avoidance method based on grids on the THMR-2 mobile root that permits the detection of unknown obstacles and the avoidance of collisions, based on information received from ultrasonic sensors, while autonomously steering the mobile root towards the given target by a smooth and continuous motion.

TL;DR: A generic hierarchical architecture for expert control systems is presented which integrates a real-time control mechanism and on-line supervision with multiple knowledge resources and can provide good performance with guaranteed stability.

TL;DR: A genetic algorithm (GA) designed to search for significant input and output combinations to a software control system and is intended that such a tool should be used to support the human tester by focusing their attention on areas of concern which they can investigate further.

TL;DR: This deliberately provocative paper poses the question as to whether it is professionally acceptable to use AI-based control systems in real-time automation and suggests possible ways in which it may be resolved.

TL;DR: This method treats the HO's behaviour as a dynamic process in itself, transformed from the dynamics of the unknown process to be controlled, and has been successfully applied to control a nonlinear level-control process using computer simulation.

TL;DR: This paper will give a review of preprocessing methods used in linear and nonlinear models, and how a combination of the techniques used to solve the individual problems can be combined to solve this composite problem.

TL;DR: A Continuous Fuzzy Petri Net (CFPN) tool which integrates the three technologies of fuzzy control, Petri nets and real-time expert systems is presented and is currently being used by ESSO Canada.

TL;DR: A camera-based bar-code recognition system using backpropagation neural networks is proposed to use a camera instead of a laser reader so that in-store automation can be achieved.

TL;DR: An alternative approach is described which more closely models the engineer's expertise, based on traditional classifications of shape elements which have evolved over many years in casting design, which is naturally object-oriented.

TL;DR: A knowledge-based framework by which a CAD model of the part to be oriented and fed is analysed for its significant orienting feature(s), and a suitable match of orienting devices is determined.

TL;DR: An intelligent design environment (Meta-COOP) for conceptual process design is presented, based on object-oriented programming (OOP) techniques and coded in C ++ , which provides such distinct features as the integration of various knowledge-representation and inference methods, and deals with multimedia information.

TL;DR: The paper describes a system named DRS-Sched, a knowledge-based scheduler aimed at solving an important aspect of the whole DRS scheduling problem, and the basic algorithm and heuristics used in the current release of the system.

TL;DR: A brief overview of expert control systems is presented and the impact of expert-system techniques on control engineering is discussed, with an emphasis on distinctions between conventional expert systems, traditional advanced control systems and expertcontrol systems.

TL;DR: The expert system, developed using the general-purpose application expert-system shell SUPER, is shown to be efficient in all the cases, even with signals obtained in very noisy environments.

TL;DR: A rule-based expert system to aid an operator in the fault diagnosis of the electronics of forge press equipment, developed in Turbo PROLOG on an IBM PC to help the operator fix faults up to replaceable module level.

TL;DR: The simplified qualitative model can reduce the computational load in qualitative simulation and retain the qualitative description of the system, in order to simplify the structural properties of the multistage separation processes.