A fuzzy-based decision support model for engineering asset condition monitoring - A case study of examination of water pipelines



Publication Details

Lau, H. C W. and Dwight, R. (2011). A fuzzy-based decision support model for engineering asset condition monitoring - A case study of examination of water pipelines. Expert systems with applications, 38 (10), 13342-13350.


Engineering asset management (EAM) is a multi-disciplinary activity that aims to tackle the issues of asset capability, life, safety, maintenance and reliability, taking into account economical and managerial factors. Condition monitoring is an important aspect of EAM as it is able to identify potential failure symptoms and suggest remedial actions prior to any operational interruptions. In general, conditions of assets can be investigated through various tests and then decision has to be made if the asset should be repaired or replaced or further in-depth test is needed. In the current practice, the decision to be made is normally based on human judgement and field experience which are subject to personal view and bias. As such, a more scientific and reliable decision support model is needed to help companies make the right decision which may be vital to ensure that daily operations will not be disrupted. In this paper, a decision support model characterized by its inclusion of fuzzy logic technology to achieve rule inference is proposed. This fuzzy-based decision support (FDS) model adopts the fuzzy reasoning approach to suggest the optimal action that needs to be taken to deal with the problem of asset conditions. This approach provides a relatively independent result based on available numerical (crisp) data. One of the main benefits of using FDS model is that its knowledge base accumulates experience through a learning process and becomes “smarter” over time. To demonstrate the feasibility of this approach, a case study related to the condition monitoring of water pipelines in an electro-plating plant based in China has been conducted. Results indicate that this model provides expertise advice and pre-warning signals, if any, of engineering asset conditions based on input crisp data of examined asset status, thereby enhancing the effectiveness of EAM.

Please refer to publisher version or contact your library.



Link to publisher version (DOI)