Ian Jenkinson

Inference and learning methodology of belief-rule-based expert system for pipeline leak detection

Belief rule based expert systems are an extension of traditional rule based systems and are capable of representing more complicated causal relationships using different types of information with uncertainties. This paper describes how the belief rule based expert systems can be trained and used for pipeline leak detection. Pipeline operations under different conditions are modelled by a belief rule base using expert knowledge, which is then trained and fine tuned using pipeline operating data, and validated by testing data. All training and testing data are collected and scaled from a real pipeline. The study demonstrates that the belief rule based system is flexible, can be adapted to represent complicated expert systems, and is a valid novel approach for pipeline leak detection.

The use of Bayesian network modelling for maintenance planning in a manufacturing industry

This paper has been written in order to apply Bayesian network modelling to a maintenance and inspection department. The primary aim of this paper is to establish and model the various parameters responsible for the failure rate of a system, using Bayesian network modelling, in order to apply it to a delay-time analysis study. The use of Bayesian network modelling allows certain influencing events to be considered which can affect parameters relating to the failure rate of a system. Bayesian network modelling also allows these influencing events to change and update depending on the influencing data available at any given time, thus changing the failure rate or probability of failure. A methodology has been developed and applied to a case study in order to demonstrate the process involved.

An Offshore Risk Analysis Method Using Fuzzy Bayesian Network

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.

Application of genetic programming to the calibration of industrial robots

Robot calibration is a widely studied area for which a variety of solutions have been generated. Most of the methods proposed address the calibration problem by establishing a model structure followed by indirect, often ill-conditioned numeric parameter identification. This paper introduces a new inverse static kinematic calibration technique based on genetic programming, which is used to establish and identify model structure and parameters. The technique has the potential to identify the true calibration model avoiding the problems of conventional methods. The fundamentals of this approach are described and experimental results provided.

Methodology of using delay-time analysis for a manufacturing industry

This paper has been written to give a methodology of applying delay-time analysis to a maintenance and inspection department. The aim is to reduce downtime of plant items and/or reducing maintenance and inspection costs, taking into account the possible environmental impact of a failure in terms of cost, both to the company and the environment. The paper also attempts to give a subjective measure of the consequences of such a failure in terms of cost to the environment, in monetary value to the company and the damaging effect to the company image.

Suitability of the Upper Airway Models Obtained from MRI Studies in Simulating Drug Lung Deposition from Inhalers

No HeadingPurpose.In this study, the suitability of the upper airway models, obtained by applying a magnetic resonance imaging method, in simulating in vivo aerosol deposition data is determined.Methods.Depositions of salbutamol sulfate from two nebulizers in two models, one with constriction at the oropharynx (the constricted cast) and another model without that constriction (the wide cast), were determined.Results.For the Sidestream and Ventstream nebulizer, 76 ± 3% (mean ± standard deviation) and 81 ± 2% of the emitted dose deposited in the constricted cast, whereas 51 ± 2% and 49 ± 3% of the emitted dose deposited in the wide cast, respectively. These values were in good agreement with in vivo data. Mostly, increasing nebulizer charge volume (by normal saline) from 2.5 ml to 5 ml increased significantly the lung dose. However, the lung doses from the Sidestream and Ventstream nebulizer with 2.5 ml charge volume via the wide cast were (1.37 ± 0.06 and 1.38 ± 0.05 mg) significantly larger than those for the constricted cast with 5 ml charge volume (0.87 ± 0.15 and 0.86 ± 0.21 mg, respectively) (p = 0.005).Conclusions.The upper airway models closely simulated the in vivo deposition data. Optimizing the upper airway posture during inhalation via the nebulizers would be more efficient in increasing drug lung delivery than diluting their contents.

Modelling dwelling fire development and occupancy escape using Bayesian network

Abstract The concept of probabilistic modelling under uncertainty within the context of fire and rescue through the application of the Bayesian network (BN) technique is presented in this paper. BNs are capable of dealing with uncertainty in data, a common issue within fire incidents, and can be adapted to represent various fire scenarios. A BN model has been built to study fire development within generic dwellings up to an advanced fire situation. The model is presented in two parts: part I deals with “initial fire development” and part II “occupant response and further fire development”. Likelihoods are assessed for states of human reaction, fire growth, and occupant survival. Case studies demonstrate how the model functions and provide evidence that it could be used for safety assessment, planning and accident investigation. Discussion is undertaken on how the model could be further developed to investigate specific areas of interest affecting dwelling fire outcomes.

MRI image-based FE modelling of the pelvis system and bladder filling

In this study, high-resolution magnetic resonance imaging was performed in the transaxial, coronal and sagittal planes to provide comprehensive structural details of the bladder and surrounding systems. Detailed finite-element (FE) models that were specific to each participant were developed by rendering the images, and the process of bladder filling was simulated. The overall model of bladder deformation was compared with repeated images of the filled bladder that were obtained using computed tomography to validate the FE models. The relationship between the changes in the key dimensions of the bladder and the increase in bladder volume during the filling process was also investigated. The numerical results showed that the bladder dimensions increased linearly with its volume during the filling process and the predicted coefficients are comparable to some of the published clinical results.

A seafarer’s reliability assessment incorporating subjective judgements

More than 80% of international cargo moves through seaports, making a contribution to the world economy. As a result, the performance of seafarers plays a major role in the safety of international trade and the maritime environment. This paper presents a novel approach to monitoring the performance of seafarers in terms of their conditional reliability. Unlike a traditional reliability analysis of a seafarer, this approach contains a dynamic model capable of coping with continually changing conditions that affect a seafarer’s performance. The proposed methodology enables and facilitates decision makers to assess the performance of a seafarer before his or her designation to any activities and during his or her seafaring period. To evaluate a seafarer’s reliability, a generic model is constructed and a combination of different techniques such as fuzzy logic, a fuzzy rule base, an analytical hierarchy process, evidential reasoning, a mapping process and expected utility is used. Furthermore, by changing the conditions that affect the reliability of an ideal seafarer and through calculating a value for this reliability, a benchmark is constructed. A seafarer’s reliability depends upon many variables and their dependencies; alteration of a criterion value will ultimately alter a seafarer’s reliability. In order to correct any deviation on time, a seafarer’s reliability has to be measured appropriately and regularly.

An offshore safety assessment framework using fuzzy reasoning and evidential synthesis approaches

The operation of tandem loading/offloading is associated with a high level of uncertainty because it usually operates in a dynamic environment in which both technical, and human and organisational, malfunctions may cause possible accidents. There is a lack of approaches for dealing with uncertainty and vagueness in expert judgements in assessment of safety of the operations. This paper proposes a framework for modelling the safety of offshore and marine engineering systems using fuzzy reasoning and evidential synthesis approaches. The proposed method is capable of dealing with uncertainties, including ignorance and vagueness, which traditional methods or frameworks for multiple criteria decision analysis, such as expected utility theory, cannot handle. A case study of the collision risk between a floating production, storage and offloading unit (FPSO) and a shuttle tanker due to technical failure during a tandem offloading operation is used to illustrate the application of the proposed model.