A Knowledge Management Framework for Remote Maintenance

—Plant maintenance is a critical role in the success of manufacturing enterprises. The concept of remote maintenance (or e-maintenance) n the industry refers to the integration of the information and communication technologies to service for plant maintenance remotely. Remote maintenance is characteristic of knowledge intensive and collaborative. To improve the efficiency of knowledge management and so as to improve the quality of remote maintenance work, a knowledge management framework was proposed. In the model, maintenance business ontology provides a common understanding for maintenance business to share information for knowledge management, and knowledge integration network describes the relationships among role knowledge, task knowledge and equipment knowledge, to achieve the integration of maintenance business and knowledge resources. At last, the paper illustrated the application of the proposed model. Results of this study can improve the level of knowledge management for remote maintenance.


INTRODUCTION
Remote maintenance (or e-maintenance) is the totality of all maintenance, repair, overhaul and operation in the stage of use and maintain equipment remotely. It is a critical role in the success of manufacturing enterprises, and also is the core of the manufacturing services support technology [1]. Remote maintenance integrates maintenance theory in the information technology, communication, and enterprise management method to service for plant maintenance [2].
Remote maintenance is characteristic of knowledge intensive [3]. Each of Maintenance tasks requires employing of various knowledge and experience. Member of remote maintenance alliance has the willing to share knowledge, so as to cooperate with other members and finish the remote maintenance work. The key to successful remote maintenance is full understanding and effective sharing of knowledge throughout the remote maintenance cycle. Consequently, knowledge management approach capable of supporting the accumulation knowledge and experience in a distributed environment is one of the important guarantees to the successful execution of remote maintenance.
The research of knowledge management for remote maintenance has been emphasized in manufacturing industries, and many researches provide theories and methods for knowledge sharing of remote maintenance [4][5][6][7][8][9]. However, in addition to the effective sharing, knowledge also requires effective integration model to rapidly respond to the demand of maintenance work [10]. Few studies have focused on this issue.
According to the characteristics of business-driven and distributed cooperation, this paper proposes knowledge management framework for remote maintenance. In the framework, maintenance business ontology provides a common understanding for maintenance business to share information for knowledge management, and knowledge integration network describes the relationships among role knowledge, task knowledge and equipment knowledge, to achieve the integration of maintenance business and knowledge resources. The model can support the overall view of knowledge resources in remote maintenance, and to achieve the effective organization and application of maintenance knowledge.

II. REMOTE MAINTENANCE PROCESS
CHARACTERIZATIONS Remote maintenance concept model is shown as in Figure1. Remote maintenance is an approach to integrating resources from different enterprises to overcome the problem in plant maintenance and the tools/systems can be quickly and easily reconfigured by adding, adapting, adjusting and deleting individual tools/systems as needed. These tools/systems run on various platforms, which may be located in dispersed locations. Remote maintenance has the following characterizations: Alliance Organization: organization structure of remote maintenance is maintenance alliance. Maintenance alliance is a virtual organization in which different enterprise share the processes, activities and resources of maintenance to provide a value-add maintenance services.
Business-centered: Participants in a remote maintenance process works together on a business with a commonly agreed time frame and have a common goal and well-defined responsibilities. Maintenance business is a process that consists of series of activities. An activity also can be further divided into lower level activities. This forms the hierarchical structure of processes.
Remote and On-line working: In addition to the necessary on-site operation, maintenance works are carried out by network remotely.
Distributed and cooperativeness: maintenance resources may be located in dispersed locations, and maintenance worker who take chare of the maintenance task may come from difficult enterprise. Individual activities performed together with other activities to achieve higher-level goals through communication and coordination.  Knowledge Node Graph (AKNG. The KOG is made up of knowledge objects and their relations which defined by maintenance alliance. The EKNG is the mapping of the MBO and is made up of knowledge nodes and their relations within a collaborative enterprise. Each Alliance Knowledge Node (AKN) is the mapping of the concept in the MBO and links with one or more Enterprise Knowledge Nodes. Each Enterprise Knowledge Node (EKN) is the mapping of the concept in the MBO and links with one or more Knowledge Objects (KO). By using the knowledge integration mechanism, distributed EKNGs are integrated into the AKNG established by the dominant enterprise, hereby creating a global knowledge network with address connected physical knowledge. Thus, collaborating enterprises can share their own knowledge with other knowledge workers in collaborating enterprises to increase knowledge value.

IV. ESTABLISHMENT OF KNOWLEDGE MANAGEMENT FRAMEWORK
A. Establishment of MBO Ontology [11] is an explicit, shared and formal description of important concepts and their relationships. The purpose of ontology ies to define knowledge concepts within a specific domain using an interoperable format both humans and machines can understand, thereby realizing knowledge sharing and reuse. With the appropriate use of ontology, it is easy to realize semantic information exchange in knowledge management. Enterprise ontology is a collection of terms and definitions relevant to an enterprise to ensure that all parties involved have a shared understanding of the relevant aspects of an enterprise [12]. Enterprise ontology plays a crucial role in enterprise's knowledge management [13]. To establish a process-oriented knowledge supply model, enterprise ontology is also adopted to enable the e-maintenance federation to share commonsense concepts used in knowledge supply.
MBO can be expressed as: MBO = (C, R). Where C is ontology concept set, and R is ontology relation set.
Top level concepts and relations of MBO are shown as in   Where Background is knowledge background, which has the basic information of the knowledge; Content is knowledge content, which describes the content of knowledge; Application knowledge application, which describes the applicable scope of the knowledge.
Background describes the background information of knowledge object. Background is represented as follows: Background = (Owner, Author, CreationDate, Modify-Date). Where, Owner is owner of knowledge object; Author is author of knowledge object; CreationDate is the date when knowledge object is created; ModifyDate is the date when knowledge object is modified.
Content describes function of knowledge content. Content is represented as follows: Content= (Category, Level, Version, Keywords, Abstract, Evaluation, Location).
Category is classification of knowledge function, and is defined by maintenance alliance. Level reflects different structures and storage forms of knowledge. Level classifies knowledge into five knowledge levels of "Description", "Rule", "Procedure" and "Case". Version is the version of knowledge object. Abstract is abstract description of knowledge object. Keywords is a collection of words, which descript the function of knowledge object. Evaluation is evaluation value of knowledge quality. Location is the location of knowledge object.
Application is expressed as: Application = (MRS, MTS, MES). MRS is the role set, which describes the suitable roles of knowledge. 3. Knowledge link graph includes G AEKN and G NO . G AEKN is the link sets between alliance knowledge nodes and enterprise knowledge nodes. G AEKN is defined as: G AEKN ={ael ij , 1 i n , 1 j m }, ael ij is the link between one alliance knowledge node and one enterprise knowledge node. ael ij =(akn i , ekn j ), akn i is alliance knowledge node and ekn j is enterprise knowledge node.
G NO is the link sets between enterprise knowledge nodes and knowledge object nodes. G NO is defined as: G NO ={nol ij , 1 i n , 1 j m }, nol ij is the link between one enterprise knowledge node and one knowledge object node. nol ij = (ekn i , kon j ), ekn i is enterprise knowledge node and kon j is knowledge object node.
KON is defined as: KON= (KONID, EID, KOL) KONID is the unique ID number of knowledge object node which enterprise assign; EID is ID number of enterprise; KOL is location of knowledge object which link with knowledge object.
Based above define, the data structure of the model is shown as in Figure 4.

V. APPLICATION
Based the knowledge management framework for remote maintenance, a knowledge management system had been developed ( Figure 5).
Functions of system are as follows: 1. The Ontology Management supports the construction and maintenance of MBO. The system uses Protégé to develop the MBO and Jena [14] to enable creation, modifying, maintenance of ontology. Figure 6 is Protégé development interface of MBO.    Figure 7 is Knowledge object register interface.
3. The Knowledge Network Management supports creation, deletion and integration of knowledge nodes. Knowledge node search interface is shown as in Figure 8 4. The Knowledge Application Management takes business process as the core and integrates knowledge resources in order to adapt to the maintenance business operation. Its development is based process-oriented knowledge supply model [3] which the author had been developed.
5. The Knowledge Security Management takes business process as the core to protect the knowledge. Its develop-ment is based business-process-context-based knowledge access control model [15] which the author had been developed.

VI. CONCLUSION
Knowledge is one of core e-maintenance resources and critical support element of maintenance process. The knowledge management framework is proposed to achieve the integration of maintenance business and knowledge resources. From the application, it is known that the model can support the navigation knowledge, supply activities, and improve the efficiency of knowledge management.