Showing papers by "Dong-Ling Xu published in 2009"

An Offshore Risk Analysis Method Using Fuzzy Bayesian Network

Abstract: The operation of an offshore installation is associated with a high level of uncertainty because it usually operates in a dynamic environment in which technical and human and organizational malfunctions may cause possible accidents. This paper proposes a fuzzy Bayesian network (FBN) approach to model causal relationships among risk factors, which may cause possible accidents in offshore operations. The FBN model explicitly represents cause-and-effect assumptions between offshore engineering system variables that may be obscured under other modeling approaches like fuzzy reasoning and Monte Carlo risk analysis. The flexibility of the method allows for multiple forms of information to be used to quantify model relationships, including formally assessed expert opinions when quantitative data are lacking in early design stages with a high level of innovation or when only qualitative or vague statements can be made. The model is also a modular representation of uncertain knowledge due to randomness and vagueness. This makes the risk and safety analysis of offshore engineering systems more functional and easier in many assessment contexts. A case study of the collision risk between a floating production, storage and offloading unit and the authorized vessels due to human errors during operation is used to illustrate the application of the proposed model.

Online updating belief rule based system for pipeline leak detection under expert intervention

Abstract: A belief rule base inference methodology using the evidential reasoning approach (RIMER) has been developed recently, where a new belief rule base (BRB) is proposed to extend traditional IF-THEN rules and can capture more complicated causal relationships using different types of information with uncertainties, but these models are trained off-line and it is very expensive to train and re-train them. As such, recursive algorithms have been developed to update the BRB systems online and their calculation speed is very high, which is very important, particularly for the systems that have a high level of real-time requirement. The optimization models and recursive algorithms have been used for pipeline leak detection. However, because the proposed algorithms are both locally optimal and there may exist some noise in the real engineering systems, the trained or updated BRB may violate some certain running patterns that the pipeline leak should follow. These patterns can be determined by human experts according to some basic physical principles and the historical information. Therefore, this paper describes under expert intervention, how the recursive algorithm update the BRB system so that the updated BRB cannot only be used for pipeline leak detection but also satisfy the given patterns. Pipeline operations under different conditions are modeled by a BRB using expert knowledge, which is then updated and fine tuned using the proposed recursive algorithm and pipeline operating data, and validated by testing data. All training and testing data are collected from a real pipeline. The study demonstrates that under expert intervention, the BRB expert system is flexible, can be automatically tuned to represent complicated expert systems, and may be applied widely in engineering. It is also demonstrated that compared with other methods such as fuzzy neural networks (FNNs), the RIMER has a special characteristic of allowing direct intervention of human experts in deciding the internal structure and the parameters of a BRB expert system.

Consumer preference prediction by using a hybrid evidential reasoning and belief rule-based methodology

Abstract: Consumer preference prediction is a key factor to the success of new product development. This paper presents a hybrid evidential reasoning (ER) and belief rule-based (BRB) methodology for consumer preference prediction and a novel application to orange juices. The orange juices are distinguished by their values of sensory attributes, which are grouped for simplicity into different categories such as appearance, aroma, texture, flavour, and aftertaste. The ER approach is used to aggregate consumer preferences for category attributes into an overall preference, and the BRB methodology is used to model the casual relationships between category attributes and their sensory attributes. The casual relationships between the overall preference and the sensory attributes of orange juices are trained and tested using real data and memorized for prediction or new product design. A case study involving 16 orange juices is conducted using the proposed hybrid ER and BRB methodology to demonstrate its novel applications. The results show that the hybrid ER and BRB methodology can fit and predict consumer preferences with high accuracy.

Applying a belief rule-base inference methodology to a guideline-based clinical decision support system

Abstract: A critical issue in the clinical decision support system (CDSS) research area is how to represent and reason with both uncertain medical domain knowledge and clinical symptoms to arrive at accurate conclusions. Although a number of methods and tools have been developed in the past two decades for modelling clinical guidelines, few of those modelling methods have capabilities of handling the uncertainties that exist in almost every stage of a clinical decision-making process. This paper describes how to apply a recently developed generic rule-base inference methodology using the evidential reasoning approach (RIMER) to model clinical guidelines and the clinical inference process in a CDSS. In RIMER, a rule base is designed with belief degrees embedded in all possible consequents of a rule. Such a rule base is capable of capturing vagueness, incompleteness and non-linear causal relationships, while traditional IF–THEN rules can be represented as a special case. Inference in such a rule base is implemented using the evidential reasoning approach which has the capability of handling different types and degrees of uncertainty in both medical domain knowledge and clinical symptoms. A case study demonstrates that employing RIMER in developing a guideline-based CDSS is a valid novel approach.

Assessment of nuclear waste repository options using the ER approach

Abstract: Two technically feasible nuclear waste repository options have been identified in Belgium. To select one for implementation, a study was carried out to compare the public perception and acceptance of the two options. In this paper, it is described how the study and selection process can be supported, and how the diversity and uncertainty in public opinions can be rationally modeled and analyzed by applying the Evidential Reasoning (ER) approach. The ER approach is a recent advancement for multi-criteria decision analysis (MCDA). By using belief decision matrices to model MCDA problems, both qualitative and quantitative information with various types of uncertainties can be taken into account in decision-making processes in a unified and logical format. Following an illustration of the ER approach and an outline of the selection problem, it is described how the ER approach can be used to model the problem, aggregate information, and facilitate sensitivity analysis. Some suggestions are made for future assessment studies.

Application of multiple criteria decision analysis in impact assessment of carbon labelling

Abstract: In this paper, it is described how multiple criteria decision analysis (MCDA) methods, in particular the Evidential Reasoning (ER) approach, is applied to help Tesco, the largest UK retailer, to prioritise product groups for its carbon labelling program. The main objectives of the program are to maximise the positive impact of the program to the environment in terms of carbon footprint reduction, while not to introduce unintentionally non-carbon related risks such as resource depletion, pollution and ethical risks. The application is focused on comparing both the positive and negative impacts of labelling different product groups so that the ones with the relatively higher positive impacts are recommended for early participation in the program. The main challenges of the application are uncertainties in data and judgements, such as lack of data, inaccuracy of data estimates and weights of different criteria. It is demonstrated with examples how those challenges can be dealt with by applying the ER approach for MCDA.

Project Risk Modelling and Assessment in New Product Development

Abstract: New Product Development (NPD) is a crucial process to maintain the competitiveness of a company in an ever changing market. In the process of developing new products of a high level of innovation, there are various types of risks, which should be properly identified, systematically analyzed, modeled, evaluated and effectively controlled. In this paper, the Bayesian Network (BN) method will be investigated to assess risks involved in NPD processes. A systematic method is examined to generate probabilities in BNs. Both the probability generation method and the BN model are demonstrated by a case study about the design of electronic products for a multinational flashlight manufacturing company.