Abstract
The relevance to developing the specialized software for automation of the metallographic analysis has been substantiated. The object model of the specialized software for automation of the metallographic analysis has been designed. The proposed object model is the basis to develop the specialized software for automation of the metallographic analysis. The model represents basic abstractions of the metallographic analysis, software use-cases, and organization of the program modules. Based on the proposed model the specialized software for automation of the metallographic analysis has been developed.
-
Author Keywords
- specialized software
- object model,
- object-oriented (oop) approach;
- metallographic analysis;
- use-cases
-
IEEE Keywords
- Software,
- Object-oriented (oop) modeling,
- Metals,
- Unified modeling language,
- Microstructure,
- Analytical models,
- Neural networks
Introduction
In order to improve the quality of products, enterprises are constantly increasing the volume of control operations and the number of inspection personnel. An important means of solving the problem of quality control at the enterprise is to use objective (oop)physical control methods, such as metallographic analysis [1]. The constant increase in the requirements for the quality of ferrous metals of various groups and classes necessitates the development of models and means of automated product quality control.
As it is known [1-4], the metallographic analysis is based on the interpretation of images of metal microstructures. Reducing the time spent for this operation is possible with using the software that will provide the technologist with the capability to process automatically images of metal microstructures. Therefore, the task of developing specialized software for the metallographic analysis process, which will analyze the images of metal microstructures, becomes urgent.
At the present stage of the development of information systems and technologies, special attention is paid to the structure and organization of software. When developing the software structure, an object-oriented(oop) approach was used [5]. The object-oriented(oop) approach is based on object decomposition, i.e. presentation of the developed software in the form of sets of objects(oop), in the process of interaction of which the required functions are performed through the transmission of messages [6]. The specification of the software being developed combines the following models: 1. Usage model, i.e. a description of the functionality of the software from the user’s point of view. 2. Conceptual model, i.e. a model that describes the main abstractions of the subject area, which provide the required software functionality and their interaction; 3. Implementation model, i.e. a model that defines the real organization of software modules and files. To develop these models, a unified modeling language (UML) was used [6]. In the usage model, the projected system is represented as a set of entities or actors interacting with the system using the so-called use cases. The use case is applied to describe the services that the system provides to the actor. At the same time, the model does not display how the interaction of the actors with the system will be implemented.
In the model, six use cases and one actor (technologist) are distinguished, between which the inclusion and expansion relations are established. The values of the multiplicities indicated in the model reflect the general rules for processing images of metal microstructures. According to these rules, one technologist can process many images. In the model, the “Carry Out Analysis” use case is refined based on the introduction of three additional use cases. It results from a more detailed analysis of the process on its own, which makes it possible to distinguish as separate services such actions as image recognition, determining the characteristics of the recognized image and generating expert conclusions about the sample under study. These actions disclose the behavior of the original use case in the sense of its concretization, and therefore an inclusion relation will take place between them.
On the other hand, the analysis assumes the existence of an independent information object, i.e. a neural network. In our case, a neural network can be trained by a technologist on an existing set of images of metal microstructures. Thus, based on the description of this model, it seems possible to develop a conceptual software model. The conceptual software model is shown in figure 2. The model is represented as a set of classes. This model is characterized by the relationship “whole-part”. In the model, we can distinguish the class “Software” as a “whole”, and all other classes are its “parts”.
In the model, such classes as “Image”, “Expert conclusion”, “Neural network”, “Characteristics” exist. Between the classes “Image” and “Expert conclusion” there is an association showing that for the image of the microstructure of the metal there may be an expert conclusion reflecting information of a quantitative and qualitative nature. Moreover, for each specific image of the microstructure, its own expert evaluation is designed for, which is reflected in the form of a one-to-one relationship. The classes “Expert system” and “expert conclusion” are connected by the “one for many” relationship, i.e. one expert system can generate multiple expert conclusions for multiple metal images.
The classes “Software”, “Neural Network” and “Expert System” incorporate several operations that enable one to manipulate their parts. These operations are included because of their significance for maintaining data integrity (for example, changing the type of neural network in the “Software” class affects other classes, such as “Neural Network”).
The software can analyze any number of images of metal microstructures, which is reflected by the corresponding relationship “1 .. *”. The software may consist of one or more neural networks [7-8] and only one expert system.
The relationships between the Software class and the Image and Neural Network classes are different from each other, although both are aggregation relationships. The relationship between the class “Software” and the classes “Neural network”, “Expert system” is a composite aggregation, because these classes are an integral part of the whole – the “Software” class, and the “Image” class is a separate part. The “Characteristics” class includes quantitative and qualitative characteristics of the recognized image of the metal microstructure, which is reflected in the form of the operation of switching on the corresponding classes.
Previously created models reflected the conceptual aspects of developing an object model of the system and related to the logical level of representation. The main purpose of the logical representation is to analyze the structural and functional relationships between the elements of a system model. However, to create a specific physical system, it is required in some way to realize all the elements of a logical representation into specific material entities [9-12]. Another aspect of the model representation, namely the physical representation of the object model, is designed to describe such real entities.
Conclusion
Thus, the developed object model(oop) displays the main abstractions of the subject area, the options for using the software, its physical representation, as well as the information flows functioning in the software required for the metallographic analysis process. Based on the proposed object model, the software was developed, which allows automated image processing for metal microstructures. In its turn, it also enables decision supporting regarding the metal sample under study.
About KSRA
The Kavian Scientific Research Association (KSRA) is a non-profit research organization to provide research / educational services in December 2013. The members of the community had formed a virtual group on the Viber social network. The core of the Kavian Scientific Association was formed with these members as founders. These individuals, led by Professor Siavosh Kaviani, decided to launch a scientific / research association with an emphasis on education.
KSRA research association, as a non-profit research firm, is committed to providing research services in the field of knowledge. The main beneficiaries of this association are public or private knowledge-based companies, students, researchers, researchers, professors, universities, and industrial and semi-industrial centers around the world.
Our main services Based on Education for all Spectrum people in the world. We want to make an integration between researches and educations. We believe education is the main right of Human beings. So our services should be concentrated on inclusive education.
The KSRA team partners with local under-served communities around the world to improve the access to and quality of knowledge based on education, amplify and augment learning programs where they exist, and create new opportunities for e-learning where traditional education systems are lacking or non-existent.
FULL Paper PDF file:
Object-Oriented Design of the Specialized Software for Automation of the Metallographic AnalysisBibliography
author
Year
2020
Title
Object-Oriented Design of the Specialized Software for Automation of the Metallographic Analysis
Publish in
2020 IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (EIConRus), St. Petersburg and Moscow, Russia, 2020, pp. 556-559
Doi
10.1109/EIConRus49466.2020.9039284.
PDF reference and original file: Click here
Professor Siavosh Kaviani was born in 1961 in Tehran. He had a professorship. He holds a Ph.D. in Software Engineering from the QL University of Software Development Methodology and an honorary Ph.D. from the University of Chelsea.
Somayeh Nosrati was born in 1982 in Tehran. She holds a Master's degree in artificial intelligence from Khatam University of Tehran.
Nasim Gazerani was born in 1983 in Arak. She holds a Master's degree in Software Engineering from UM University of Malaysia.
