Using HLT for acquiring, retrieving and publishing knowledge in AKT:position paper

AKT is a major research project applying a variety of technologies to knowledge management. Knowledge is a dynamic, ubiquitous resource, which is to be found equally in an expert's head, under terabytes of data, or explicitly stated in manuals. AKT will extend knowledge management technologies to exploit the potential of the semantic web, covering the use of knowledge over its entire lifecycle, from acquisition to maintenance and deletion. In this paper we discuss how HLT will be used in AKT and how the use of HLT will affect different areas of KM, such as knowledge acquisition, retrieval and publishing.

Background and foreground knowledge in dynamic ontology construction

Ontologies have become a key component in the Semantic Web and Knowledge management. One accepted goal is to construct ontologies from a domain specific set of texts. An ontology reflects the background knowledge used in writing and reading a text. However, a text is an act of knowledge maintenance, in that it re-enforces the background assumptions, alters links and associations in the ontology, and adds new concepts. This means that background knowledge is rarely expressed in a machine interpretable manner. When it is, it is usually in the conceptual boundaries of the domain, e.g. in textbooks or when ideas are borrowed into other domains. We argue that a partial solution to this lies in searching external resources such as specialized glossaries and the internet. We show that a random selection of concept pairs from the Gene Ontology do not occur in a relevant corpus of texts from the journal Nature. In contrast, a significant proportion can be found on the internet. Thus, we conclude that sources external to the domain corpus are necessary for the automatic construction of ontologies.

Modelling and improving maintenance decisions:Having foresight with simulation and artificial intelligence

Machine breakdowns are one of the main sources of disruption and throughput fluctuation in highly automated production facilities. One element in reducing this disruption is ensuring that the maintenance team responds correctly to machine failures. It is, however, difficult to determine the current practice employed by the maintenance team, let alone suggest improvements to it. 'Knowledge based improvement' is a methodology that aims to address this issue, by (a) eliciting knowledge on current practice, (b) evaluating that practice and (c) looking for improvements. The methodology, based on visual interactive simulation and artificial intelligence methods, and its application to a Ford engine assembly facility are described. Copyright © 2002 Society of Automotive Engineers, Inc.

Using a simulation model for knowledge elicitation and knowledge management

The work reported in this paper is part of a project simulating maintenance operations in an automotive engine production facility. The decisions made by the people in charge of these operations form a crucial element of this simulation. Eliciting this knowledge is problematic. One approach is to use the simulation model as part of the knowledge elicitation process. This paper reports on the experience so far with using a simulation model to support knowledge management in this way. Issues are discussed regarding the data available, the use of the model, and the elicitation process itself. © 2004 Elsevier B.V. All rights reserved.

Knowledge based improvement:simulation and artificial intelligence for identifying and improving human decision-making in an operations systems

The performance of most operations systems is significantly affected by the interaction of human decision-makers. A methodology, based on the use of visual interactive simulation (VIS) and artificial intelligence (AI), is described that aims to identify and improve human decision-making in operations systems. The methodology, known as 'knowledge-based improvement' (KBI), elicits knowledge from a decision-maker via a VIS and then uses AI methods to represent decision-making. By linking the VIS and AI representation, it is possible to predict the performance of the operations system under different decision-making strategies and to search for improved strategies. The KBI methodology is applied to the decision-making surrounding unplanned maintenance operations at a Ford Motor Company engine assembly plant.

Mapping causal knowledge: how people consider their environment during meetings

Causal mapping can help managers to think through the causal influence between issues, enabling them to base a decision on a more structured consideration. Even in regular meetings, learning and the integration of knowledge from diverse stakeholders can benefit from causal mapping. Four causal mapping meetings with management teams are analysed to assess how managers thought causally about their environment when strategy-making. We found that although managers can use other views to expand their environmental knowledge, some prefer to use familiar information rather than less familiar information. Despite this preference, many managers thought systemically about a raft of related issues. We discuss our findings in the context of regular meetings and offer improvements to the facilitation of group causal mapping.

An advanced real-time predictive maintenance framework for large scale machine systems

This thesis introduces and develops a novel real-time predictive maintenance system to estimate the machine system parameters using the motion current signature. Recently, motion current signature analysis has been addressed as an alternative to the use of sensors for monitoring internal faults of a motor. A maintenance system based upon the analysis of motion current signature avoids the need for the implementation and maintenance of expensive motion sensing technology. By developing nonlinear dynamical analysis for motion current signature, the research described in this thesis implements a novel real-time predictive maintenance system for current and future manufacturing machine systems. A crucial concept underpinning this project is that the motion current signature contains infor­mation relating to the machine system parameters and that this information can be extracted using nonlinear mapping techniques, such as neural networks. Towards this end, a proof of con­cept procedure is performed, which substantiates this concept. A simulation model, TuneLearn, is developed to simulate the large amount of training data required by the neural network ap­proach. Statistical validation and verification of the model is performed to ascertain confidence in the simulated motion current signature. Validation experiment concludes that, although, the simulation model generates a good macro-dynamical mapping of the motion current signature, it fails to accurately map the micro-dynamical structure due to the lack of knowledge regarding performance of higher order and nonlinear factors, such as backlash and compliance. Failure of the simulation model to determine the micro-dynamical structure suggests the pres­ence of nonlinearity in the motion current signature. This motivated us to perform surrogate data testing for nonlinearity in the motion current signature. Results confirm the presence of nonlinearity in the motion current signature, thereby, motivating the use of nonlinear tech­niques for further analysis. Outcomes of the experiment show that nonlinear noise reduction combined with the linear reverse algorithm offers precise machine system parameter estimation using the motion current signature for the implementation of the real-time predictive maintenance system. Finally, a linear reverse algorithm, BJEST, is developed and applied to the motion current signature to estimate the machine system parameters.

Knowledge, capabilities and manufacturing innovation: a US-Europe comparison

In this paper we report a comparative analysis of the factors which contribute to the innovation performance of manufacturing firms in the US state of Georgia, and three European regions, the UK regions of Wales and the West Midlands, and the Spanish region of Catalonia. We consider the factors which shape firms’ ability to generate new products and processes and undertake various forms of organisational and structural change. We are particularly concerned with how firms collect the knowledge on which they base their innovation and their effectiveness in translating that knowledge into new innovations. Three main empirical conclusions result. First, US firms have more widespread links to external knowledge sources than those in Europe and notably the universities make a greater contribution to innovation in the US than in Europe. Second, UK firms prove more effective at capturing synergies between their innovation activities than US and Catalan firms. Third, firms’ operating environment proves more conducive to innovation in the US than in either the UK regions or Catalonia. Our results suggest the potential for mutual learning. For the UK there are lessons in terms of the way in which the universities in Georgia are supporting innovation. For firms in Georgia and in Catalonia the potential lessons are more strategic or organisational and relate to how they can better capture potential synergies between their innovation activities.

Knowledge elicitation and knowledge representation in a large domain with multiple experts

This paper describes the knowledge elicitation and knowledge representation aspects of a system being developed to help with the design and maintenance of relational data bases. The size algorithmic components. In addition, the domain contains multiple experts, but any given expert's knowledge of this large domain is only partial. The paper discusses the methods and techniques used for knowledge elicitation, which was based on a "broad and shallow" approach at first, moving to a "narrow and deep" one later, and describes the models used for knowledge representation, which were based on a layered "generic and variants" approach. © 1995.

Knowledge elicitation supported by simulation

The work reported in this paper is part of a project simulating maintenance operations in an automotive engine production facility. The decisions made by the people in charge of these operations form a crucial element of this simulation. Eliciting this knowledge is problematic. One approach is to use the simulation model as part of the knowledge elicitation process. This paper reports on the experience so far with using a simulation model to support knowledge management in this way. Issues are discussed regarding the data available, the use of the model, and the elicitation process itself.

Explaining process and performance in the co-production of knowledge:a comparative analysis of collaborative research projects

Despite considerable and growing interest in the subject of academic researchers and practising managers jointly generating knowledge (which we term ‘co-production’), our searches of management literature revealed few articles based on primary data or multiple cases. Given the increasing commitment to co-production by academics, managers and those funding research, it seems important to strengthen the evidence base about practice and performance in co-production. Literature on collaborative research was reviewed to develop a framework to structure the analysis of this data and relate findings to the limited body of prior research on collaborative research practice and performance. This paper presents empirical data from four completed, large scale co-production projects. Despite major differences between the cases, we find that the key success factors and the indicators of performances are remarkably similar. We demonstrate many, complex influences between factors, between outcomes, and between factors and outcomes, and discuss the features that are distinctive to co-production. Our empirical findings are broadly consonant with prior literature, but go further in trying to understand success factors’ consequences for performance. A second contribution of this paper is the development of a conceptually and methodologically rigorous process for investigating collaborative research, linking process and performance. The paper closes with discussion of the study’s limitations and opportunities for further research.

Fatigue crack propagation in nickel-base superalloys:effects of microstructure, load ratio, and temperature

The current state of knowledge and understanding of the long fatigue crack propagation behavior of nickel-base superalloys are reviewed, with particular emphasis on turbine disk materials. The data are presented in the form of crack growth rate versus stress intensity factor range curves, and the effects of such variables as microstructure, load ratio, and temperature in the near-threshold and Paris regimes of the curves, are discussed.

Knowledge-based Robot Control

The paper is related with the problem of developing autonomous intelligent robots for complex environments. In details it outlines a knowledge-based robot control architecture that combines several techniques in order to supply an ability to adapt and act autonomously in complex environments. The described architecture has been implemented as a robotic system that demonstrates its operation in dynamic environment. Although the robotic system demonstrates a certain level of autonomy, the experiments show that there are situation, in which the developed base architecture should be complemented with additional modules. The last few chapters of the paper describe the experimentation results and the current state of further research towards the developed architecture.

Applications of Nonclassical Logic Methods for Purposes of Knowledge Discovery and Data Mining

* The work is partially supported by Grant no. NIP917 of the Ministry of Science and Education – Republic of Bulgaria.

Ontology-Based Model of Representation of Knowledge about Language Mappings

The paper presents a short review of some systems for program transformations performed on the basis of the internal intermediate representations of these programs. Many systems try to support several languages of representation of the source texts of programs and solve the task of their translation into the internal representation. This task is still a challenge as it is effort-consuming. To reduce the effort, different systems of translator construction, ready compilers with ready grammars of outside designers are used. Though this approach saves the effort, it has its drawbacks and constraints. The paper presents the general idea of using the mapping approach to solve the task within the framework of program transformations and overcome the disadvantages of the existing systems. The paper demonstrates a fragment of the ontology model of high-level languages mappings onto the single representation and gives the example of how the description of (a fragment) a particular mapping is represented in accordance with the ontology model.