**1. Introduction**

Nowadays, industrial information provides effective knowledge of existing resources through databases and repositories, which provide details on the hosted equipment, including information on their capacity, performance, start/stop dates, turbine and generators models, etc. All of these properties and information are stored in digital repositories, digital files, and business websites. To collect, contribute, and share the knowledge about the resources installed in the industrial area, online databases named digital industry repository (DIR) is used. Therefore, the way in which information and knowledge stored in digital repositories is retrieved is of vital importance. DIRs provide centralized hosting and access to content, establish permissions, and

© 2016 The Author(s). Licensee InTech. This chapter is distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. © 2017 The Author(s). Licensee InTech. This chapter is distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

controls for access to content, the ability to share digital objects or files, to protect the intellectual, and integrity property rights of content owners and creators, etc.

So far, traditional search engines treat the information as an ordinary database that manages the content inefficiently. Current search engines retrieve the information by comparing the contents of the database with searched patterns. The generated result is a list of data that contain this patter. Although search engines are becoming more effectively, information overload hinders search and accurate knowledge retrieval. Consequently, it is necessary to develop new semantic and intelligent models that contribute new possibilities. The presented work offers a new approach to the information retrieval based on semantics and intelligent models. For this, the case-based reasoning (CBR) technique is applied contributing to the goal of improving knowledge recovery in the industrial field.

A significant number of researchers have already investigated the application of intelligence and semantic techniques, but just a few from the point of view of full integrated of both technologies an industrial environment. There are researchers and related field works that include ontology retrieval methods such as [1] present a system that uses an ontology query model to analyze the usefulness of ontologies in effectively performing document searches and proposes an algorithm to refine ontologies for information retrieval tasks with preliminary positive results. In this paper [2], real-time image capture was achieved by using digital camera technology and image processing technology. By extracting the glue line curve from image, thinning glue curve by morphological method, and extracting the frame information, the closure and quality of the glue curve can be detected. Results of test show that the effect is satisfactory and the method is effective. The major contribution of [3] is a novel semantic query expansion technique that combines association rules with ontologies and Natural Language Processing techniques, which utilizes the explicit semantics as well as other linguistic properties of unstructured text corpus. It makes use of contextual properties of important terms discovered by association rules, and ontology entries are added to the query by disambiguating word senses.

Semantic Web utilizes concepts, taxonomic relations, and nontaxonomic relations in a given domain ontology to capture knowledge efficiently. For example, [4] describes one component of a knowledge management platform with a multiagent search module (MASH), which employs domain ontology to search for Web pages that contain relevant information to each concept in the domain of interest. The search is then constrained to a specific domain to avoid as much as possible the analysis of irrelevant information. Ref. [5] expounds the function of each layer and analyses the implementation of this system from the knowledge organization and expression and knowledge retrieval and proposes a framework of knowledge management system based on ontology. This management system establishes a sharable ontology that can be understood both by human and computer, which people can found more relations of different concepts through a better circumstance of knowledge retrieval interface. The work of [6] proposes an ontology-based user model, called user ontology, for providing personalized information service in the Semantic Web which utilizes concepts, taxonomic relations, and nontaxonomic relations in a given domain ontology to capture the users' interests. The research of [7] presents a semantics-based digital project which provides faceted search and represents a novel approach to Digital Libraries, integrating social Web and multimedia elements in a semantically annotated repository. In other investigation, Ref. [8] describes the architecture of the dynamic retrieval analysis and semantic metadata management system (DREAM) designed to automatically and intelligently index huge repositories of special effects video clips, based on their semantic content, using a network of scalable ontologies to enable intelligent retrieval. Ref. [9] presents an information search and retrieval framework based on the semantically annotated multifacet product family ontology. The major contribution of [10] is an innovative comprehensive semantic search model, which extends the classic information retrieval (IR) model, addresses the challenges of the massive and heterogeneous Web environment.

controls for access to content, the ability to share digital objects or files, to protect the intellec-

So far, traditional search engines treat the information as an ordinary database that manages the content inefficiently. Current search engines retrieve the information by comparing the contents of the database with searched patterns. The generated result is a list of data that contain this patter. Although search engines are becoming more effectively, information overload hinders search and accurate knowledge retrieval. Consequently, it is necessary to develop new semantic and intelligent models that contribute new possibilities. The presented work offers a new approach to the information retrieval based on semantics and intelligent models. For this, the case-based reasoning (CBR) technique is applied contributing to the goal of

A significant number of researchers have already investigated the application of intelligence and semantic techniques, but just a few from the point of view of full integrated of both technologies an industrial environment. There are researchers and related field works that include ontology retrieval methods such as [1] present a system that uses an ontology query model to analyze the usefulness of ontologies in effectively performing document searches and proposes an algorithm to refine ontologies for information retrieval tasks with preliminary positive results. In this paper [2], real-time image capture was achieved by using digital camera technology and image processing technology. By extracting the glue line curve from image, thinning glue curve by morphological method, and extracting the frame information, the closure and quality of the glue curve can be detected. Results of test show that the effect is satisfactory and the method is effective. The major contribution of [3] is a novel semantic query expansion technique that combines association rules with ontologies and Natural Language Processing techniques, which utilizes the explicit semantics as well as other linguistic properties of unstructured text corpus. It makes use of contextual properties of important terms discovered by association rules, and ontology entries are added to the query by disambiguat-

Semantic Web utilizes concepts, taxonomic relations, and nontaxonomic relations in a given domain ontology to capture knowledge efficiently. For example, [4] describes one component of a knowledge management platform with a multiagent search module (MASH), which employs domain ontology to search for Web pages that contain relevant information to each concept in the domain of interest. The search is then constrained to a specific domain to avoid as much as possible the analysis of irrelevant information. Ref. [5] expounds the function of each layer and analyses the implementation of this system from the knowledge organization and expression and knowledge retrieval and proposes a framework of knowledge management system based on ontology. This management system establishes a sharable ontology that can be understood both by human and computer, which people can found more relations of different concepts through a better circumstance of knowledge retrieval interface. The work of [6] proposes an ontology-based user model, called user ontology, for providing personalized information service in the Semantic Web which utilizes concepts, taxonomic relations, and nontaxonomic relations in a given domain ontology to capture the users' interests. The research of [7] presents a semantics-based digital project which provides faceted search and represents a novel

tual, and integrity property rights of content owners and creators, etc.

improving knowledge recovery in the industrial field.

122 Knowledge Management Strategies and Applications

ing word senses.

There are a lot of researchers on applying these new technologies into current information retrieval systems, but no research addresses artificial intelligence (AI) and semantic issues from the whole life cycle and architecture point of view [11]. This article analyses the search methods efficiency in a distributed data space such as industrial information repositories. The paper presents an intelligent proposal to optimize search engines in a specific industrial domain and to focus our discussion on the indexing and retrieval strategies of cases and provides the application technical aspects. This paper describes the current problems of semantic interoperability and proposes an intelligent method to address them. To do these, technologies based on metadata and intelligent techniques are used. The main proposal goal is the intelligent search management in decentralized industrial repositories, where no global information scheme exists. The most important novel introduced by this proposal is that contextual user profiles are built based on ontologies and metadata facilitating the ontological search using expert systems technologies. The objective has focused on creating technologically complex environments industrial domain and incorporates Semantic Web and AI technologies to enable precise location of industrial resources [12]. For this reason, we are improving representation by incorporating more metadata from within the information.

We propose a new paradigm to achieve efficient knowledge retrieval from digital repositories. This paper presents an intelligent search engine for industrial process, especially for resources repositories, and proposes an intelligent agent–based personalized model. One major research area is intelligent systems, with the general intention to replace human operators with intelligent agents. We have used CBR methodology to develop a prototype for supporting efficient retrieval knowledge from DIR.

In the following sections, we review the CBR framework and its features for implementing the reasoning process over ontologies. Section 2 presents a general overview about the industrial domain and technology infrastructure, analyzing its failures and discovering the needs that push us toward new intelligent paradigms. Section 3 analyses ontology requirements and proposes the design criteria to guide the development of ontologies for knowledge-sharing purposes. Then, we show the methodology followed to conduct this research, and we describe the semantic-based management system in DIRs environment. Next section concerns the design of a prototype system for semantic search framework, in order to verify that our proposed approach is an applicable solution. Moreover, the functional requirements of the engine and the knowledge base are described in detail. Finally, we present the results of our work on the adaptation of the framework, and we outline the future works.
