Artificial Intelligence in Engineering最新文献

This paper demonstrates the use of multiple models in intelligent control systems where models are organised within a model space of three primitive modelling dimensions: precision, scope and generality. This approach generates a space of models to extend the operating range of control systems. Within this model space, the selection of the most appropriate model to use in a given situation is determined through a reasoning strategy consisting of a set of model switching rules. These are based on using the most efficient, but least general models first and then incrementally increasing the generality and scope until a satisfactory model is found. This methodology has culminated in a multi-model intelligent control system architecture that trades-off efficiency with generality, an approach apparent in human problem solving. The architecture allows learning of successful adaptations through model refinement and the subsequent direct use of refined models in similar situations in the future. Examples using models of a laboratory-scale process rig illustrates the adaptive reasoning and learning process of multi-model intelligent control systems.

The planning of intelligent robot behavior plays an important role in the development of flexible automated systems. The robot’s intelligence comprises its capability to act in unpredictable and chaotic situations, which requires not just a change but the creation of the robot’s working knowledge. Planning of intelligent robot behavior addresses three main issues: finding task solutions in unknown situations, learning from experience and recognizing the similarity of problem paradigms. This article outlines a planning system which integrates the reinforcement learning method and a neural network approach with the aim to ensure autonomous robot behavior in unpredictable working conditions.

The assumption is that the robot is a tabula rasa and has no knowledge of the work space structure. Initially, it has just basic strategic knowledge of searching for solutions, based on random attempts, and a built-in learning system. The reinforcement learning method is used here to evaluate robot behavior and to induce new, or improve the existing, knowledge. The acquired action (task) plan is stored as experience which can be used in solving similar future problems. To provide the recognition of problem similarities, the Adaptive Fuzzy Shadowed neural network is designed. This novel network concept with a fuzzy learning rule and shadowed hidden layer architecture enables the recognition of slightly translated or rotated patterns and does not forget already learned structures.

The intelligent planning system is simulated using object-oriented techniques and verified on planned and random examples, proving the main advantages of the proposed approach: autonomous learning, which is invariant with regard to the order of training samples, and single iteration learning progress.

The purpose of this paper is to present results that were obtained in fault diagnosis of glutamic acid fermentation process. The diagnosis algorithm is based on the extended Kalman filter (EKF) and neural network classifier. Inputs of the network are the process I/O data, such as pressure and temperature, parameters estimated by EKF, and state values calculated by dynamic equations, while outputs of the network are process fault situations. A batch glutamic acid fermentation process is studied as a test case, which is with 13 measurements, five estimated parameters, three calculated states, and 11 fault situations. The running test results show that the strategy appears to be better suited to diagnose faults of such an industrial process.

Many computer simulations, experimental testing and monitoring of physical systems produce vast amounts of quantitative data. These data have always been assimilated by trained and experienced personnel. Human beings use qualitative representations naturally for efficient decision making. An automated system which can provide such qualitative descriptions can be useful in various disciplines for decision support and training. In this paper we describe the structure of such a system that can handle natural language queries to produce descriptions from data generated from structural dynamics simulations.

We proprose a method for verifying hardware design with an induction-based theorem prover such as the Boyer–Moore Theorem Prover. As a case study, we apply the method to verification of the correctness of systolic array designs. In verifying circuits, we prove that an implementation satisfies a specification, in particular their functional equivalence. In proving the equivalence, induction is applied to the variables that denote time and position in the circuit. We discuss what lemmas should be used for appropriate application of induction. The lemmas we have found reflect the characteristics of the structure of the circuit. With these lemmas, the method provides a systematic way of verification for systolic arrays and eases the user's burden with respect to the hardware verification.

This paper presents the Intelligent Forecasters Construction Set (IFCS) which is a toolset for constructing forecasting applications. The toolset supports the intelligent techniques of fuzzy logic, artificial neural networks, knowledge-based and case-based reasoning. The developer can construct a forecasting application using rules, procedures and flow diagrams, which are organized into a hierarchy of workspaces. The modularity of the IFCS allows subsequent addition of other modules of intelligent techniques.

The IFCS was used for developing a water demand forecasting system based on real-world data obtained from the City of Regina's water distribution system and Environment Canada. A utility demand prediction system developed with the IFCS system is useful for optimizing operation costs of water plants. Some water plants need to pay a flat rate for electricity, which is set depending on peak kilowatt demand. Hence, if the peak kilowatt demand can be reduced, the operating costs of the plant can be lessened (Jamieson RA et al. American Water Works Association Journal 1993;85:48–55). An energy management system needs a good estimate of future customer demand in order to find the optimal pumping schedules that can minimize the peak kilowatt demand. Since the IFCS supports developing multiple predictor models, modeling of data can be expedited. The benefits of using multiple modules of artificial neural networks for demand prediction are presented. The results from this approach are compared with a linear regression and a case-based reasoning program. The performance comparisons among the forecasters will be discussed.

As a result of good modeling capabilities, neural networks have been used extensively for a number of chemical engineering applications such as sensor data analysis, fault detection and nonlinear process identification. However, only in recent years, with the upsurge in the research on nonlinear control, has its use in process control been widespread. This paper intend to provide an extensive review of the various applications utilizing neural networks for chemical process control, both in simulation and online implementation. We have categorized the review under three major control schemes; predictive control, inverse-model-based control, and adaptive control methods, respectively. In each of these categories, we summarize the major applications as well as the objectives and results of the work. The review reveals the tremendous prospect of using neural networks in process control. It also shows the multilayered neural network as the most popular network for such process control applications and also shows the lack of actual successful online applications at the present time.

The implantation of programs which gives a robot the ability to perform a non-repetitive task (task not completely defined called also unexpected), was hindered by a complex problem: the difficulty met by the classical method in programming (procedural) to formulate a task which the evolution model does not obey to an algorithmic pre-established design. As a part of that the aim of this paper is to propose an analysis approach which lies on a mechanism of factorisation of the complex task. The idea developed consists of subdividing the activity of programming into two steps. A descriptive step which allows the formulation of a complex task using a functional approach without integrating any element to the construction of an executing program and a constructive step which develops a program using the preceding formulation. This program expresses, more or less explicitly, the way of solving different problems posed by the execution of the task at the level of a robot. The aspect of time is introduced as a logical form in the last step for the sequencing of actions while executing a task.

In this paper, the well developed parsimonious set covering theory based abductive inference model for diagnostic problem solving is extended, in order to deal with degrees of cause-and-effect relationship between disorders and manifestations, and degrees of manifestations. A new fuzzy abductive inference model capable of handling these problems is developed, and a new criterion for describing the relative plausibility of different diagnosis hypotheses proposed. Based on this criterion, the diagnostic problem is then formulated as a 0–1 integer programming problem, and a tabu search (TS) approach is presented for solving the problem. Three sample studies are served for demonstrating the reasonableness of the developed fuzzy abductive inference model and the computational efficiency of the TS based method.

This article addresses a specific feature of the engineering design process, i.e. the assignment of priorities among the parameters that constrain the design process. These parameters are often fuzzy in nature and Chen's weighted fuzzy reasoning algorithm was adapted for reasoning with them. We present the modified version of Chen's algorithm, which is called the enhanced weighted fuzzy reasoning algorithm, and apply it to some sample rules developed for the domain of solvent selection for carbon dioxide removal processes. This article also suggests how the proposed algorithm improves upon previous efforts at automating the solvent selection for the carbon dioxide removal task.