Yoshiyuki Takaoka

Identification of ontologies to reuse knowledge for substation fault recovery support system

Abstract A methodology to identify task/domain ontologies is proposed in this paper. According to the methodology, task/domain ontologies that are indispensable for building a reusable knowledge base are identified. The expertise model of the methodology has two kinds of ontologies at different abstraction levels. The first one is based on a vocabulary applicable in common to the entire target field. This vocabulary is used as a communication basis between domain experts and knowledge engineers. The first layer of an expertise model is described in this vocabulary and is built in collaboration with them. The second one is based on a generic vocabulary. By defining the common vocabulary in terms of the generic vocabulary, a reusable task model that is an expertise model at the second layer can be built. We evaluate the effectiveness of this methodology by applying it into substation restoration problems.

A planning support document based system for transformer reparation task using ontology

Engineers have to refer to various technical information to perform their job. Technical information have been accumulated in an electronic form as documents which contain texts, pictures and movies in enterprises. However, it needs expert knowledge to make use of these technical information. In this paper, we describe an ontology-centric framework, called intelligent corporate base (ICoB) which organizes a technical information into documents, assists a comprehension of documents and helps share information. We explain a prototype system for planning on repair work of transformers. Furthermore, we describe development and use of ontology for technical information sharing.

Generation of operation sequences for accident restoration of primary substations based on a re-usable knowledge base

Abstract Although considerable advances have been made in the automation of power systems, it is still a fact that restoration operations after accidents in primary substations have to depend on experts because restoration operations are complicated. It is useful to make them automatic by using knowledge base technology. As there are many kinds of primary substations, and they have different configurations, operation rationale, etc., it is necessary to build expert systems (ES) suitable for every kind of primary substation. In this paper we propose an approach to generating operation sequences for accident restoration in primary substations based on a re-usable knowledge base that is composed of object models, and on general rules. The re-usability of the knowledge base is verified by applying it to ten cases of accidents, in two different kinds of substation.

CHARM pad: ontology-based tool for learning systematic knowledge about nursing

Japan is no exception among developed countries facing healthcare system problems due to aging and low birthrate as the number of patient increases and health care worker numbers shrink. The introduction of high tech medicine has increased the amount of knowledge to be learned by novice nurses. Although vast amounts of implicit knowledge have accumulated among nursing practitioners, this knowledge needs to be communicated when hospitals train younger generations of nurses. In this paper, the authors have proposed an activity model called CHARM (the Convincing Human Action Rationalized Model) and CHARM Pad, tablet PC with browsing software for CHARM models. CHARM explicates multidimensional purpose-oriented procedure relations often existing as implicit knowledge. For this reason, CHARM supports the training and education of novice nurses. We developed CHARM models according to nursing guidelines of hospitals and applied them to training of the nurses in two hospitals. CHARM and CHARM Pad are being evaluated at these hospitals and positive responses are coming from nurses.

Construction of a reusable knowledge base—Generating operation sequences for the accident restoration of primary substations based on the reusable knowledge base

The expert systems (ES) in the past have mostly been constructed to solve particular problems, and it is difficult to share or reuse the obtained knowledge. This has been a serious drawback in efficiently constructing an ES. Since practical application of ES is in progress, and the practical usefulness is recognized widely in society at present, it is very significant to work for sharing reuse of knowledge. The authors considered the accident restoration assist of the primary substations, and attempted to construct a reusable knowledge base. In this paper, first, the conventional ES to assist the accident restoration of the primary substations is analyzed, and it is pointed out that the knowledge is restricted to particular substations and, consequently, cannot directly be reused. Then the methodology for constructing the reusable knowledge base is discussed. Based on the presented methodology, the constructing procedure for the reusable knowledge base for the accident restoration of the primary substations is discussed in detail. The knowledge of the expert in problem-solving is analyzed and is divided into the following three classes: 1) the object model; 2) the general rules; and 3) the knowledge specific to the particular primary substations. Finally, the procedure-generation system for the accident restoration of the primary substations is described. Through the test using the case data of 10 accidents in 2 primary substations, it is verified that the same operation sequence can be generated as the one by the expert.