Dentcho N. Batanov

Decision support system for multicriteria machine selection for flexible manufacturing systems

Abstract This paper proposes an approach to the design and development of an intelligent Decision Support System (DSS) that is intended to help the selection process of alternative machines for Flexible Manufacturing Systems (FMS). The process consists of a series of steps starting with an analysis of the information and culminating in a conclusion —a selection from several available alternatives and verification of the selected alternative to solve the problem. In real decision situations, more than one criterion is present, and the problem becomes multicriteria decision making. The approach presented combines the Analytic Hierarchy Process (AHP) technique for multicriteria decision making with the rule-based technique for creating Expert Systems (ES). Such an approach allows the past experience, expressed as heuristics in ES, to be used. Moreover, this approach determines the architecture of the computer-based environment necessary for the decision support software system to be created. It includes the AHP software package (Expert Choice), Dbase III + DBMS, Expert System shell (EXSYS) and Turbo Pascal compiler (for the external procedural programs). As a result, a prototype decision support system for a fixed domain, namely a CNC turning center that is required to process a family of rotational parts, is developed. It helps the user to find the most “satisfactory” machine on the basis of several objective as well as subjective attributes.

Development of industrial information systems on the web using business components

Web technologies, as tools, are most popular and widely used today not only in the everyday life but in industry as well. Examples of such technologies are the browsers, search engines, related communication protocols and their implementations, mechanisms for creating dynamic and active Web sites, security mechanisms, etc. These technologies lead to requirements for substantial changes in the methodologies for development and deployment of all systems and subsystems, which constitute any business process. Changes and/or new decisions are necessary to make possible the modern Web-based technological tools to be used effectively for Web-based business processes. A methodology for developing business software components as basic building elements of industrial information systems, implemented and deployed in Web-based computing environment is proposed and discussed in this paper. The methodology is based on the idea of creating a unified framework for representing business activities as a basis for business process modeling. Respective models, methods and techniques ensure the business objects and components to applied to currently most accepted three-tier Web application architecture using XML document as distributed object. For illustrative purposes only the proposed methodology is applied step by step, with respective comments, to developing a part of inventory subsystem of industrial information system as a case study.

Fuzzy-C-Mean determines the principle component pairs to estimate the degree of emotion from facial expressions

Although many systems exist for automatic classification of faces according to their emotional expression, these systems do not explicitly estimate the strength of given expressions. This paper describes and empirically evaluates an algorithm capable of estimating the degree to which a face expresses a given emotion. The system first aligns and normalizes an input face image, then applies a filter bank of Gabor wavelets and reduces the datas dimensionality via principal components analysis. Finally, an unsupervised Fuzzy-C-Mean clustering algorithm is employed recursively on the same set of data to find the best pair of principle components from the amount of alignment of the cluster centers on a straight line. The cluster memberships are then mapped to degrees of a facial expression (i.e. less Happy, moderately happy, and very happy). In a test on 54 previously unseen happy faces., we find an orderly mapping of faces to clusters as the subjects face moves from a neutral to very happy emotional display. Similar results are observed on 78 previously unseen surprised faces.

An object-oriented expert system for fault diagnosis in the ethylene distillation process

Abstract This paper presents a unified object-oriented methodology (methods, techniques, and tools) for building relatively complex knowledge-based software systems for diagnosis of industrial equipment. A Fault Diagnosis Expert System ( fdes ) is developed as a prototype for locating the root causes of a set of abnormalities in the ethylene distillation process. The underlaying domain-related features of the methodology are the problem-solving method, diagnostic knowledge representation, and control strategy. The problem-solving method is based on diagnostic knowledge and an appropriate problem-solving structure. Diagnostic knowledge is derived from shallow knowledge and deep knowledge about the problem domain. The hierarchical problem-solving structure is created on the base of functional and structural considerations. This structure leads to the structured knowledge base. A two-level knowledge base is constructed for fdes . The system structure is built entirely using an object-oriented representation scheme. All the necessary declarative and procedural knowledge is embedded in objects. In addition, the production rules, which are bearers of heuristic knowledge, are combined with that scheme thanks to the unified programming environment used. The reasoning is based on a hypothesis-test strategy. A control strategy, in which the diagnostic direction is decided at top level, is adopted. The basic part of fdes is implemented using the object-oriented version of clips (C Language Integrated Production System). fdes has a friendly user interface written in C. Two case studies are briefly discussed as examples validating the system.

Recognizing Thai handwritten characters and words for human-computer interaction

Normally, people use a keyboard to interact with a computer. This type of interaction has two main problems; typing speed and typing error. This paper proposes a non-keyboard computer interaction by using a write-pen or mouse to write Thai handwritten characters and words, using a feature-based, fuzzy logic and object-oriented approach (FBFLOOA) to recognize on-line handwritten Thai characters and words. The feature-based concept is used to extract handwritten character features, the fuzzy logic set is used to identify uncertain handwritten character shapes and the object-oriented approach is used to analyse, design and implement a handwritten character and word recognition program.Two phases of Thai handwritten character and word recognition are proposed. The first phase uses only the FBFLOOA to recognize a handwritten character and the second phase uses FBFLOOA combined with a Thai dictionary file to seek a correct answer for a rejected recognition character. The first phase experimental results show a recognition accuracy of 89.24%, 9.20% misrecognition and 1.56% rejection. The second phase precision results are 97.82%, 0.62% misrecognition and 1.56% rejection. Both phases have an average recognition speed of 6.72s per character. The FBFLOOA-executed program size is 189 KB and the Thai dictionary file is 853 KB, which makes FBFLOOA available for notebooks, mobile phones, calculators and pocket computers.

Using simulation to evaluate the batching approach to part type selection in flexible manufacturing systems

The selection of part types for simultaneous processing in a Flexible Manufacturing System (FMS) is one of the most responsible phases of the short‐time production planning. The batching approach to part type selection is more popular in practice but this leads to the requirement for a preliminary evaluation of the results obtained. Using simulation is a convenient, no‐risk and cheapest way to do this, which is shown and discussed in the paper. The objective of batching approach is to maximize the number of part types in a batch taking into account constraints on tool magazine capacity and tool type availability. Two alternative ways of assigning weights in the objective function of the part type selection model are explored to direct the search to a different set of part types. A procedure to determine the mix ratios of the selected part types is used so as to balance the aggregate machine workloads. The model aggregations have been accounted for in a simulation experiment conducted to evaluate the performance of the batching approach and to investigate the sensitivity of total makespan and machine utilizations.

Data and knowledge integration through the feature-based approach

Abstract One promising and convenient approach towards the integration of data and knowledge is the so called feature-based approach. Most existing definitions of the term ‘feature’ represent an attempt at generalization. However, as a rule, they depend on the application in one or another subsystem of computer integrated manufacturing systems. Probably, the reason for this is that more attention has been paid to the feature as a data-based entity. The approach, presented in this paper, can be generalized as follows: • the part (product) features are bearers of knowledge about that part (product); • there are two general kinds of knowledge: connected with data and connected with existing and/or necessary relations among these data, leading to a part (product) description; • two general types of features can be defined which correspond to those kinds of knowledge: fact-features and rule-features. Some requirements and practical recommendations for creating a feature-based application software are given. Declarative production programming languages are proposed as a most convenient tool for creating such software. In addition, those of them in which the forward chaining inference strategy is accepted are recommended. The contents of facts- and rule-bases is discussed. It is shown that the set of rules is defined as a consequence of the necessary operations, which ensure the interface with the user and external systems, parametrization of available facts and different types of their processing. As a confirmation of the ideas presented in this paper, the main components of an intelligent system for feature-based modeling in computer-aided design and computer-aided manufacturing are briefly shown.

Self-testing and self-learning fuzzy expert system for technological process control

The application of expert systems in technological processes control is usually limited. One problem is how to respond to changes in the environment surrounding system. A way to overcome the above shortcoming is to use fuzzy logic for representation of the inexact information. Still more the fuzzy system could be responsible for the changes in the environment if it is self-learning by automatic fuzzy rules generation. Another problem is how to balance the conflicting situations concerning facts and rules. The certainty factor formalism in classical expert systems is rather subjective assessment to overcome this. In the present work a self-testing method is proposed, based on fuzzy certainty factor. The system is designed to find the contradictory facts and incompleteness of the fuzzy rule-base. A self-learning and self-testing fuzzy expert system is presented, where the control actions of a complex technological process could be automatically generated. The system can operate in two modes, expert and fuzzy ones, that corresponds to implicit and explicit use of human knowledge during the control process. The fuzzy rule base can be automatically tested for completeness and correctness using production rules. A fuzzy module allows automatically fuzzy rule generation and fuzzy inference that allows permanent model testing for completeness. The production system is a mechanism for creating an expert module that trains the fuzzy system artificially with new learning sequences, like as states and control actions.

KBS and macro-level systems: support of energy demand forecasting

Abstract Applications of expert systems have been flourishing in the field of strategic planning. For the energy sector, a number of expert systems have been developed for carrying out various tasks such as system design, diagnosis and trouble shooting, demand forecast and planning. A review of existing expert systems in the energy sector in general and in energy planning in particular, shows that they have mostly concentrated on the most pressing problems involving load forecast, investment planning, transmission and distribution network design, operation control, etc., in the power sector, while very few have been implemented for supporting energy planning processes. This paper presents an expert system developed for supporting the evaluation of selected variables of the medee-s , a powerful energy demand forecast model. The system was developed using the vp -Expert knowledge-based shell.

CUSTOMIZING COMPONENT-BASED SOFTWARE USING COMPONENT COORDINATION MODEL: A USE-CONTEXT DRIVEN APPROACH TOWARD ROLE-BASED MODEL

In this paper, we introduce a component coordination model (CCM) that is embedded into the applications during software architecture design. The CCM is driven by the use-context model, which directly reflects the role-based model that abstracts system behaviors as a computational organization comprising various role relationships. It then focuses on exposing the design of software components to be separated from their execution contexts. These separate concerns — computation, coordination, and policies imposed on a given use-context — form the principal concept of our approach. Finally, a case study using the proposed model has been demonstrated in order to provide the feasibility of the introduced approach.