K. Regulski

Multi-aspect Character of the Man-Computer Relationship in a Diagnostic-Advisory System

Chapter reviews the solutions used in diagnostic-advisory system, dedicated to the needs of the foundry industry. Multimedia techniques used in the system were selected to create a comprehensive capabilities of contact between user and computer system. The first part of the considerations apply to work in diagnostic mode, including identification of castings defects and determine the causes of their occurrence, the second part is a look at some of the features of the system implemented in a consultative mode, such as the integration of knowledge or technical and market expertise. Many illustrations was used to illustrate the various forms of contact with the user.

Data Exploration Approach Versus Sensitivity Analysis for Optimization of Metal Forming Processes

Product properties for innovative materials, e.g. dual phase steels, require precise control of production processes. Difficulties in optimization of process parameters correspond with large number of control variables, which should be considered in the technology design. Sensitivity analysis allows evaluating the importance of all process inputs on the final properties of material. Information on the most important inputs is crucial for further design of the process. Application of sensitivity analysis requires detailed knowledge of the process phenomena as well as the definition of the mathematical model of the thermomechanical process. Furthermore, some sensitivity analysis algorithms are of the high computational cost. Presented work concerns possibility of the application of data exploration approach in evaluation of the importance of process inputs as the alternative for sensitivity analysis. Use of data mining algorithms eliminates necessity of mathematical model development, it also does not require any apriori knowledge about the process. Authors presents the comparison of sensitivity analysis and data exploration approach in evaluating relationships between inputs and outputs of the hot rolling for dual phase steel strips. The presented approach and the perspectives of the practical application could lead to significant decrease of time necessary for the computations of process design. The theoretical considerations are supplemented with the results of both types of analysis.

Rough sets applied to the roughcast system for steel castings

Rough logic and rough sets theory are mainly devoted to analysis of incomplete, uncertain, and inconsistent data. An exploited in the article result of the theory is the so-called rough information system that gives a model for dealing with the situation in which some real objects are represented ambiguously via defined approximation (alternatives of values of the objects attributes). The proposed rough system opens a way to process such information and moreover is equipped with a powerful query language and possibility to classify real objects based on their stored rough characteristics. The implemented RoughCast system and, especially prepared for the case, knowledge base for steel casting defects form such the rough information system. They can be successfully applied in the process of knowledge integration concerning production of steel castings and, in consequence, as a tool in solving technological problems in operating foundries.

Practical Aspects of Knowledge Integration Using Attribute Tables Generated from Relational Databases

Until now, the use of attribute tables, which enable approximate reasoning in tasks such as knowledge integration, has been posing some difficulties resulting from the difficult process of constructing such tables. Using for this purpose the data comprised in relational databases should significantly speed up the process of creating the attribute arrays and enable getting involved in this process the individual users who are not knowledge engineers. This article illustrates how attribute tables can be generated from the relational databases, to enable the use of approximate reasoning in decision-making process. This solution allows transferring the burden of the knowledge integration task to the level of databases, thus providing convenient instrumentation and the possibility of using the knowledge sources already existing in the industry. Practical aspects of this solution have been studied on the background of the technological knowledge of metalcasting.

Process of Ontology Construction of Rolling Metal Sheets Industrial Process

The article presents assumptions and the process of construction of an ontology for the knowledge base that concerns industrial processes of metal sheets rolling including heat treatment operations. Creating of an ontology enables to build a knowledge base, which can be understood by both computers and engineers. Such a knowledge base can be used afterwards by intelligent computer techniques helping in solving of encountered problems during production process. The built ontology should be relevant to the nature of the rolling process – it has to take into account sequence of roll passes of the whole rolling process including all control parameters for each pass (e.g. the thickness before and after the pass, time of pass, temperature). Presented process of the construction of the ontology follows an ontology development cycle that should ensure relevance for industrial use of the ontology. The built ontology in the domain of industrial rolling should enable building knowledge base that concerns considered industrial process. One of possibilities is using of the elaborated ontology at construction of an advisory system that supports design of rolling process for a new product, which can be similar to some products made in the past. Other possibilities of utilization of the ontology can be seen in production scheduling or estimation of production costs.

Computer-Assisted Methods of the Design of New Materials in the Domain of Copper Alloy Manufacturing

The design of a new copper alloy to obtain material characterized by the expected mechanical properties requires experiments, which enable testing the influence of different processing techniques (e.g. heat treatment operations) on the investigated material. This work consumes both time and money, and hence is a real obstacle in situations, when the researcher has limited resources for preparing and testing only a couple of copper alloy samples. The process of design and testing of a new copper alloy can be speeded up by the use of computing methods, which can be helpful especially in the prime choice of material and its processing technique. The, investigated in this work, methodologies have been chosen from the domain of Artificial Intelligence allowing for a specific nature of the experimentally obtained data, which is usually incomplete in respect of the whole knowledge concerning the studied phenomena. Application of data mining techniques (the theory of rough sets and algorithms of rules or decision trees induction) enable constructing a knowledge base as a set of rules expressing the influence of different processing techniques on mechanical properties of the tested material. Case-based reasoning (CBR), as a methodology focused on the solution of problem together with sustained learning, enables us to build an advisory system giving advice on material design and learning on experimentally obtained results. The data mining techniques and CBR methodology complement each other – the data mining techniques allow generalization of knowledge related to the performed experiments, while CBR uses knowledge in the form of individual experimental items (cases).

Intelligent Advisory System for Support of Production Process Design in the Domain of Metal Forming

The domain of the presented work is the design of a computer advisory system which should offer support on general design of production cycle. The idea of functioning of the advisory system is related to the reuse of information gathered from previous processes of production design. The information on the design of entire production cycle is suggested to be split into fragments related to specific production phases in the whole manufacturing chain. The advisory system should provide the possibility of making use of diverse piece of information so as to obtain the full production cycle for a new product similar to others manufactured in the past. The idea of information processing is based on the data mining rules induction methods and is visualized with examples of fasteners manufacturing.

Application of Regression Trees in Optimization of Metal Forming Process

Application of sensitivity analysis in optimization of process parameters of production processes for innovative materials, e.g. dual phase steel, requires deterministic model of thermomechanical processes and large datasets that covers whole surface of results. Difficulties in optimization of process parameters correspond with large number of control variables, which should be considered in the technology design. Furthermore, conduction of such analysis takes the great computational cost. Presented work concerns possibility of application of regression trees, especially CART model, in preliminary analysis for sensitivity analysis. Use of data mining algorithms enables acquiring of preliminary, rough results: relationships among parameters of the hot rolling process of dual phase steel strips and rules of optimization of this process, it also does not require any apriori knowledge about thermomechanical processes.

Codification as Part of Knowledge Management in Research Projects in the Field of Metallurgy

Increasing requirements in the field of quality and management standards are the reason why knowledge management is regarded as an upcoming need for the metal processing industry. To fully benefit from the organisational achievements which are knowledge resources, and to meet the expectations of customers, one should think about functional, but also modern, computer system that allows the integration of heterogeneous sources of knowledge. The article describes practical aspects of the codification of metallurgical knowledge for the needs of a system of knowledge integration operating in industrial plants. The article propose successive steps to create objects of knowledge and requirements imposed onto the knowledge engineers. The presented methodology is consistent with the standards of knowledge management in the field of codification, and is based on the latest achievements of information science in the field of formal representation of knowledge.

Formalisms and Tools for Knowledge Integration Using Relational Databases

Until now, the use of attribute tables, which enable approximate reasoning in tasks such as knowledge integration, has been posing some difficulties resulting from the difficult process of constructing such tables. Using for this purpose the data comprised in relational databases should significantly speed up the process of creating the attribute arrays and enable getting involved in this process the individual users who are not knowledge engineers. This article illustrates how attribute tables can be generated from the relational databases, to enable the use of approximate reasoning in decision-making process. This solution allows transferring the burden of the knowledge integration task to the level of databases, thus providing convenient instrumentation and the possibility of using the knowledge sources already existing in the industry. Practical aspects of this solution have been studied on the background of the technological knowledge of metalcasting.