Applying Semantic Technology in Nuclear

Semantic technologies are not specific to a particular application area or knowledge domain. The distinguishing feature of semantic technologies rather consists in building applications on the basis of Knowledge Organization Systems and/or taking advantage of Linked (Open) Data Sources as described in the section of "Knowledge Organization Systems and Semantic Technologies". In consequence, nuclear organizations will deploy semantic technologies in many business areas and for many purposes, just as non-nuclear organizations do.

The applications mentioned in the following are those which are either of particular importance for organizations operating in the nuclear field, or have specifically nuclear purposes. As the application of semantic technologies in the nuclear fields is in its early stages, exploration of many other paths beyond the ones indicated in the following is fully underway, and more developments are to be expected.

Establishing common vocabularies, taxonomies and thesauri

Efforts to establish a common language within the nuclear community have been undertaken on international, national and organizational levels. However, these independently developed KOS’s usually contain formal definitions of many terms in the different glossaries which contain overlaps, and which are not always consistent. As these technical terms are used in licensing documents, contracts, specifications, design documents etc., problems may arise when interpreting an applying these terms. Semantic technologies offer solutions to the problem of managing KOS’s in a consistent way, and support many additional features.

Text analysis and term extraction

The application of advanced text analysis methods is indicated whenever large bodies of documents have to be searched for important information. An example in the nuclear field is the extensive documentation of events. Extracting important terms and combining them by means of a KOS improves the retrieval of documents (“semantic search”). Recent developments in machine-supported analysis of very large document and data repositories (“Big Data”) rely on such techniques. A further application area concerns the development of extensive and detailed KOS’s by analysing a body of documents, particularly helpful with specialized document Corpora which are closely related to a specific, well defined subject, such as analysis of a given class of accidents.

Integration of heterogeneous knowledge sources

The nuclear domain is a particularly well documented domain, the reason therefore being that organizations operate in a complex, strongly regulated environment. Every step in the lifecycle of a nuclear installation has to be properly documented for purposes of maintaining records on design, the history of the design basis, further developments within phases of the life-cycle, and fulfilling regulatory requirements. For the purpose of documentation, a multitude of content management systems and other document repositories is used, resulting in a variety of non-interoperable data silos. However, many of the documents and data residing in one repository are related to information in other repositories. Semantic technologies play a prominent role in integrating heterogeneous sources, or making them interoperable.

Knowledge bases and knowledge portals

Knowledge Organization Systems provide powerful means of modelling knowledge domains. In particular, Linked Data allow enriching a base KOS with other sources which are increasingly published by many organizations on the web. Publicly available sources such as Wikipedia and restricted, topical data sources may contribute significantly to enhance established concepts, leading to rich knowledge bases which lend itself to knowledge discovery as described in previous chapters. Such knowledge bases provide an excellent backbone for constructing knowledge portals, enabling improved search by automatically categorizing documents, translating the taxonomical hierarchy into site pages, and linking pages to internal and external information sources.

Plant information models (PIM)

In a nuclear power plant, multiple information systems and databases from different vendors and for different purposes are used. Most of these systems are not integrated with each other and cannot share plant data throughout their life cycle. This results in redundancies in capturing, handling, transferring, maintaining and preserving plant’s data. Interoperability problems can stem from the fragmented nature of the industry, paper based business practices, a lack of standardization, and inconsistent technology adoption among stakeholders. Recent exponential growth in computer, network, and wireless capabilities, coupled with more powerful software applications, has made it possible to apply information technologies in all phases of a facility life cycle, creating the potential for streamlining historically fragmented operations. The focal point for consolidating all these diverse data management tasks consists in a power plant information model (PIM) that is comprehensive, detailed, and able to be integrated and interoperable with plant design, operations, and maintenance processes, as well as databases, document systems, and records systems of organizations that own and operate them. Semantic technologies provide the glue to link all this information and documents.

Competency Networks

The potential of semantic technologies lies foremost in the ability of linking disparate information. Thereby, new insight might be gained into systems which interoperate in complex ways. One example of this is found in competency networks, where different factors are involved: industries looking for qualified staff, advertising their positions by job descriptions; competencies required for given tasks; taxonomies describing required skills and knowledge; training centres and academic institutions providing education and training to achieve those skills and knowledge. An integration of these aspects may answer questions on existing gaps between job requirements and education, forecast future needs for qualified staff, and direct education resources in particular directions.

For more information please contact the Scientific Secretary M. Gladyshev at: NKM-Contact