Vijay Shah

Bio: Vijay Shah is an academic researcher from Saint Petersburg State University. The author has contributed to research in topics: Fuzzy control system & Intelligent decision support system. The author has an hindex of 1, co-authored 1 publications receiving 12 citations.

Hybrid intelligent systems: Tools for decision making in intelligent manufacturing

Abstract: Many intelligent computing techniques have been developed over the last decade. Some of these include neural networks, fuzzy systems, genetic algorithms, rule-based expert systems, inductive expert systems, and the wide array techniques lumped under the heading of artificial intelligence. The application of these intelligent computing techniques to support planning and control in manufacturing can be done at three levels: organization, coordination, and execution. Because of the different nature of the problems at each level, different types of solutions may be required. Until recently, problem solvers have typically used single-technique-based tools to build these solutions, e.g., an expert system based solution, a neural network based solution, or a linear programming solution. Simple problems that fit the assumptions of a single-technique-based solution may be easily solved by such an approach. However, most real world manufacturing problems are not simple. They may neither fit the assumptions of a single technique nor be effectively solved by the strengths and capabilities of a single technique. One approach to deal with these complex real world problems is to integrate the use of two or more techniques in order to combine their different strengths and overcome each other’s weaknesses to generate hybrid solutions.

A Hybrid Intelligent Systems Approach for Die Design in Sheet Metal Forming

Abstract: Die design is heavily experience based and the die design process is an iterative procedure of trial and error in order to obtain a final die design for the successful manufacture of stampings. Most automotive industries use internal guidelines and past experience for die design. Even though powerful computer-aided design systems are being used in automotive industry, the lack of adequate analysis tools at the initial die geometry design stage hinders the die manufacturing process, and also necessitates lead times of the order of 5-30 weeks [1]. At the concept design stage, and during the initial die development process, the variations in geometry and process conditions are so large that it is prohibitively expensive to use 3D finite element analysis. The complexity of die design heuristic knowledge hinders the development and application of knowledge-based systems. Hybrid intelligent systems are computer programs in which at least one of the constituent models simulates intelligent behaviour [2]. These models could be knowledge-based systems, artificial neural networks, fuzzy logic systems, etc. In this approach both artificial neural networks, knowledge-based systems and finite-element analysis (FEA) for modelling the design process are used. A simulation-based design approach [3] for the die design process is followed. Artificial neural networks (ANNs) are preliminary design tools which indicate the formability of the component geometry, for the selected process and material conditions, The ANN module is trained from FEA results for a generic set of component geometries, process conditions, and material properties. The final die design validation is carried out by FEA. The intelligent framework incorporates rules for material selection, process parameter selection and their modification. Component geometry is a critical parameter which affects the manufacturability of the given part. Hence, an intelligent geometry handling module, which automatically modifies and optimises the geometry of the designed die, is implemented in the present system. Knowledge-based blackboard architecture is used for the integration of various analysis models such as CAD, FEA, and ANN, as an intelligent framework for die design [4]. The hybrid intelligent system provides an integrated decision support environment for simulation and analysis of the forming process, both during the initial die design phase and during the die tryout phase. The hybrid intelligent systems approach supports the capability for automatic evaluation of prospective die design for manufacturability, and performs automatic modification of design inputs. Applications of the hybrid intelligent system for die design are described together with a comparison with shop floor data.

The design and validation of a hybrid information system for the auditor's going concern decision

Abstract: Decision making in a semistructured environment often involves the use of quantitative, structured analysis along with the qualitative judgment of an expert. Decision support systems and expert systems are often developed to assist in this judgment process. The hybrid information system described in this paper combines a statistical model with a rule-based expert system in order to integrate the quantitative and qualitative aspects of decision making. The GC Advisor hybrid system is designed for use by auditors to assess the ability of the client firm to continue as a going concern. The guidelines for expert system validation given in previous literature are then applied to the validation of GC Advisor.

Decision‐making capabilities of a hybrid system applied to the auditor's going‐concern assessment

Abstract: The purpose of this study is to evaluate a hybrid system as a decision support model to assist with the auditor's going-concern assessment. The going-concern assessment is often an unstructured decision that involves the use of both qualitative and quantitative information. An expert system that predicts the going-concern decision has been developed in consultation with partners at three of the Big Five accounting firms. This system is combined with a statistical model that predicts bankruptcy, as a component of the auditor's decision, to form a hybrid system. The hybrid system, because it combines the use of quantitative and qualitative information, has the potential for better prediction accuracy than either the expert system or statistical model predicting separately. In addition, testing of the system provides some insight into the characteristics of firms that experience problems, but do not necessarily receive a going-concern modification. Further investigation into those firms that have problems could reveal factors that may be incorporated into decision support systems for auditors, in order to improve accuracy and reliability of these decision tools. © 2001 John Wiley & Sons, Ltd.

An empirical study of design and testing of hybrid evolutionary–neural approach for classification

Abstract: We propose a hybrid evolutionary–neural approach for binary classification that incorporates a special training data over-fitting minimizing selection procedure for improving the prediction accuracy on holdout sample. Our approach integrates parallel global search capability of genetic algorithms (GAs) and local gradient-descent search of the back-propagation algorithm. Using a set of simulated and real life data sets, we illustrate that the proposed hybrid approach fares well, both in training and holdout samples, when compared to the traditional back-propagation artificial neural network (ANN) and a genetic algorithm-based artificial neural network (GA-ANN).

Neural networks in supply chain management

Abstract: Neural networks, an emerging technique in artificial intelligence, has a strong appeal for a wide range of applications. Seldom has the concept been related directly to supply chain management, it has however been applied in a number of areas which constitute the core elements of supply chains. This paper gives a general introduction to neural networks and explains the ways in which it can contribute to supply chain management.