Artificial neural networks (ANNs) are actively utilized by researchers due to their extensive capability during the training process of the networks. The intricate training stages of many ANNs provide a powerful mechanism in solving various optimization or classification tasks. The integration of an ANN with a robust training algorithm is the supreme model to outperform the existing framework. Therefore, this work presented the inclusion of three satisfiability Boolean logic in the Hopfield neural network (HNN) with a sturdy evolutionary algorithm inspired by the Imperialist Competitive Algorithm (ICA). In general, ICA stands out from other metaheuristics as it is inspired by the policy of extending the power and rule of a government/country beyond its own borders. Existing models that incorporate standalone HNN are projected as non-versatile frameworks as it fundamentally employs random search in its training stage. The main purpose of this work was to conduct a comprehensive comparison of the proposed model by using two real data sets with an elementary HNN with exhaustive search (ES) versus a HNN with a standard evolutionary algorithm, namely- the genetic algorithm (GA). The performance evaluation of the proposed model was analyzed by computing plausible errors, such as root mean square error (RMSE), mean absolute error (MAE), global minima ratio (Rm), computational time (CT) and accuracy (Q). The computational simulations were carried out by operating the different numbers of neurons in order to validate the efficiency of the proposed model in the training stage. Based on the simulations,
the proposed model was found to execute the best performance in terms of attaining small
errors and efficient computational time compared to other existing models.
Analyzing commodity prices contributes greatly to traders, economists and analysts in
ascertaining the most feasible investment strategies. Limited knowledge about the price
trend of the commodities indeed will affect the economy because commodities like palm
oil and gold contribute a huge source of income to Malaysia. Therefore, it is important to
know the optimal price trend of the commodities before making any investments. Hence,
this paper presents a logic mining technique to study the price trend of palm oil with other
commodities. This technique employs 2-Satisfiability based Reverse Analysis Method
(2-SATRA) consolidated with 2-Satisfiability logic in Discrete Hopfield Neural Network
(DHNN2-SAT). All attributes in the data set are represented as a neuron in DHNN which
will be programmed based on a 2-SAT logical rule. By utilizing 2-SATRA in DHNN2-SAT,
the induced logic is generated from the commodity price data set that explains the trend
of commodities price. Following that, the performance evaluation metric; error analysis
and accuracy will be calculated based on the induced logic. In this case, the experimental
result has shown that the best-induced logic identifies which trend will lead to an increase
in the palm oil price with the highest accuracy rate.
This paper focuses on the construction of two-point and three-point implicit block
methods for solving general second order Initial Value Problems. The proposed methods
are formulated using Hermite Interpolating Polynomial. The block methods approximate
the numerical solutions at more than one point at a time directly without reducing the
equation into the first order system of ordinary differential equations. In the derivation of
the method, the higher derivative of the problem is incorporated into the formula to enhance
the efficiency of the proposed methods. The order and zero- stability of the methods are
also presented. Numerical result
In this paper work, three-dimensional terrain models were reconstructed from twodimensional contour lines. Firstly, spatial curves were generated from contour lines using
parameterized cubic B-spline curve interpolation. Then surfaces were constructed by using
B-spline ruled surface. In the reconstruction process, some issues such as keyholes and
branching may arise. Therefore, we propose a method that handles the branching object to
construct a bilinear patch by following the proposed data point’s extraction algorithm. We
also solved keyholes issues by retaining the same knot vector condition on B-spline ruled
surface. Results are also demonstrated for models with branching and without branching.
Working at heights has always been a concern for the process industry and construction industry. According to recent statistics, falls from heights are the leading cause for at least a third of all construction accidents, based on the accident reports from Malaysia, United States of America (USA) and Great Britain. Therefore, the aim of this research is to investigate the contributing factors for fatal accidents due to falls from heights based on published official data by government agencies such as Department of Occupational Safety and Health (DOSH) in Malaysia and Occupational Safety and Health and Administration (OSHA) in the USA. Thorough risk analysis of accidents due to falls from heights is needed as a step to improve the safety of workers and reduce the number of fatalities. The methodology used was developed through an in-depth literature review from relevant publications that discussed falls from heights investigations ranging from individual characters to management commitment and site conditions. The data is available and accessible to the public via OSHA and DOSH and can be obtained by browsing their websites. The data were analysed based on the relevant understanding of the description mentioned in the accident reports and its relationship with the contributing factors. Eventually, from the analysis, the factors which affect more the numbers of fatal accidents due to falls from heights were obtained. In this study, 105 fatal accidents due to falls from heights from Malaysia data and 101 fatal accidents from USA data were selected through a precise selecting process and analysed to determine which factor was the highest contributor to increasing the number of fatal workplace accidents due to falls from heights. Results indicate that a lack of effective management is the highest contributor to falls from height fatal accidents.
The information on the combustion properties of local timber is crucial in Malaysia as the archival material related to this subject matter is found to be very limited in scope and incomplete. The heat release rate (HRR) is the most precious variable of combustion properties as it provides the key to understand and quantify the hazard in fires. Thus, this work is to verify the reliability of the HRR obtained from cone calorimeter tests conducted upon six Malaysian wood species: Shorea laevis, Vatica rassak, Koompassia malaccensis, Heritiera, Shorea parvifolia and Cratoxylum arborescens. The single factor one-way analysis of variance (ANOVA) was used to investigate statistically significant differences between the means of the HRR dataset of each species during the combustion tests at three different heat fluxes. Later, the confidence interval estimation was occupied to determine the range around the HRR dataset, where the means of the data was likely to be found. The intraclass correlation coefficient (ICC) test was also implemented to assess the reliability of the heat release rate data obtained from the cone calorimeter test. From the surveillance, the P-values of all the six species were higher than α = 0.05, insinuating that the difference between the means of the dataset was not statistically significant. The confidence interval values consisting of the upper bound and lower bound limits indicate that the certainty that these ranges contain the true mean of the heat release rate dataset is 95%. Finally, the fact that heat release data received from the cone calorimeter test were highly reliable to statistically calculate the variation in measurements taken by a single instrument under the same condition confirmed by the ICC’s values of 0.82 to 0.99 that reflect good to excellent correlations.
The development and application of advanced materials i.e. nanomaterials are important for the technology revolution and economic progress of the country. However, the potential health risk arising from nanomaterials become a major concern. Given the fact that both particulate and molecular identity of nanomaterials is responsible for the biological effects, the effects of nanomaterial exposure cannot be predicted based on the current understanding of their bulk properties. The lack of nanomaterials data for safety assessment become a major challenge to implement safe work practice at nanomaterials related industries. To resolve the aforementioned problem, a conceptual framework for hazard assessment of nanomaterials is presented in this study. Bayesian Network (BN) is used to support hazard assessment according to the guideline issued by the Department of Occupational Safety and Health (DOSH) Malaysia. The understanding of the hazard is crucial to encourage the development of an action plan to ensure the safety aspect while processing and handling nanomaterials.
In natural gas processing, carbon dioxide is one of the major streams contaminate from the gas reservoir and must be removed, as it reduces the energy content of sales gas. In order to remove huge amounts of carbon dioxide (CO2), gas hydrate is used to capture CO2. However, the high formation of hydrate will inhibit clogs in gas pipelines. Hence, this research presents literature on hydrate formation, prediction of methane-carbon dioxide (CH4-CO2) gas mixture, by using simulation packages of Aspen Hysys 7.2, K-factor, VMG SIM Ver. 6 and BR & E ProMax 2.0. Peng-Robinson model was used in all simulation packages. Simulation results obtained were then compared with experimental data from previous literature sources. The simulation results showed that the higher the concentration of CO2 in CH4-CO2 gas mixture, the lower the pressure required for CO2 hydrate to form throughout the predicted temperature range from -20°C to 20°C.
In household products, specific chemical ingredients are used to satisfy the desired target properties as required by the consumers. However, some of these ingredients may result in safety risks and adverse health effects. Early consideration of safety and health aspects during product design is vital to minimize the impact on consumers. Safety and health aspects have not been strongly emphasized before in many product design methodologies. Therefore, a systematic methodology is proposed to assess the safety and health effects of the potential ingredients, before they are used in the product formulation. The chemical ingredient candidate may be a novel ingredient or a typical ingredient used in formulated product design. In this work, a computer-aided molecular design (CAMD) technique was used to design the novel ingredient candidates with the integration of safety and health aspects. Then, the safety and health performance of the ingredient candidates were assessed by inherent safety and health sub-indexes. Each safety or health parameter was assigned with a score, based on the degree of the potential hazards. A higher score was given to the ingredients with higher safety risk or more severe health effect, and vice versa. The result of the safety and health assessment based on the score allocation had contributed to the selection of chemical ingredient. This new approach ensures that the selected ingredient possesses desirable properties as well as low safety and health effects. A case study on surfactant design is presented to illustrate the incorporation of safety and health aspects into product design methodologies.
Composite repairs have been increasingly applied for maintenance and rehabilitation of piping, pipelines and vessels in the oil and gas industry, thus there is a growing need to monitor their in-service integrity, repair lifetime extension and prevent loss of containment of the product. There are many challenges of inspecting composite repairs including accessibility, inhomogeneous and anisotropic structure of composites, probability of detection, lack of adequate standards and diversity of composite materials amongst others. The current practice for inspection and monitoring of composites repair on oil and gas piping and pipelines is usually conducted based on International Standards Organisation (ISO) 24817 whereby visual inspection is generally performed to observe any irregularities on the surface like discolouration, cracks, chalking and blistering. This will usually be followed through with a coin tap test and Barcol hardness testing. Upon any findings of anomalies, further investigation is then performed using advance non-destructive testing (NDT) inspection technique to determine the integrity of the wrap, depending on the type and severity of defects. ISO 24817 has stated the general techniques that can be used to inspect the composites overwrap repairs including Ultrasound Technique, Radiography and Acoustic Emission. However, Petroliam Nasional Berhad (PETRONAS) has performed a series of assessments on various inspection techniques to seek suitable inspection methods for the composite wrap system, composites/substrate interface and/ or substrate. A total of 10 NDT techniques had been evaluated thus far including Laser Shearography, X-Ray, Microwave technique, Dynamic Response Spectroscopy (DRS), Acoustic Emission (AE), Computed Radiography (CRT), Pulse Eddy Current, Metal Magnetic Memory (MMM). This research summarises an overview of the effectiveness of the evaluated techniques and findings of the evaluation.
The potential of a major accident may significantly increase when change is unprepared especially in a temporary and emergency change. An unplanned change may lead to the emergence of new hazards which eventually lead towards severe impact on human, property, environment and business reputation. Management of Change (MOC) with integrated risk analysis is an important Process Safety Management (PSM) elements involving planning and controlling risks and hazards that come with the proposed change. However, lacking systematic technique for easy adoption of this element has delayed its application in plant. Corresponding to these weaknesses, an integrated MOC management system focusing on the temporary and emergency change is presented in this study. Results of this study comprise MOC process framework and MOC management system (MOCMS) which act as a guidance and documentation inventory tool. Implementation of this technique and system at the selected plant as a case study is examined and discussed. The system is beneficial to industries to manage underlying risks in a temporary and emergency change which ease the tracking of MOC case inventory to improve risk controls in changes.
Leaks and breakdowns of pipelines can lead to catastrophic failures and cause economical losses worldwide. Currently, condition monitoring has become a challenging process because of various reasons such as fluctuating external conditions, natural hazards. Pipelines are installed in severe conditions and are subjected to degradation mainly due to corrosion and metal loss. This study attempted to classify different types of metal loss faults using historical inspection data of oil and gas fields. For this purpose, Support Vector Machines (SVM) were employed to classify and predict various types of metal loss faults which were affecting the life condition of a crude oil pipeline. The historical inspection data was acquired from a crude oil pipeline located in Sudan. Different types of SVM models were trained and quadratic SVM type was selected for the present study due to its high prediction accuracy. The performance evaluation of the proposed SVM model was done using the confusion matrix. The developed SVM model provides promising results with a prediction accuracy of 93.0%. As a result, the fault detection rate (FDR) for all faults is found to be 90.4%, while the misclassification rate (MR) is 9.6%. The prediction of metal loss fault type may help in condition assessment and maintenance schedule to take prior actions for the better life of pipeline which reduces the degradation rate of a pipeline.
Vapor cloud explosion is one of the major threats to Floating, Production, Storage and Offloading (FPSO) facilities due to its congested and confined nature. Reduction in explosion overpressure can be achieved by improving the ventilation in FPSO. During early design stage of FPSO, designers consider providing grated process decks to improve the ventilation. However, there is limited research on the comparison of the explosion overpressure between the grated deck and the traditional plated deck. In this study, Vapor Cloud Explosion perspective of plated versus grated process deck in typical FPSO was evaluated by utilizing Det Norske Veritas’s (DNV) SAFETI OFFSHORE modelling tool. Representative leak scenarios were selected based on frequency analysis of major accident hazards associated with typical FPSO facility. This study revealed that the overpressure exceedance frequency in plated process deck was higher than the grated process deck for the selected scenario. This serves as quantitative guidance for designers to select an inherently safer type of decks in FPSOs from explosion perspective during the preliminary design stage. However, a detailed Computational Fluid Dynamics (CFD) study is recommended to get an insight of dangers associated with the presence of plated and grated process decks in FPSO, by considering all the parameters and conditions applicable.
Pressure relief system is a system to prevent overpressure inside protected equipment that exceeds its maximum allowable working pressure (MAWP) to disposal treatment. Relief system is designed on two different plant case studies, which are dimethyl-ether and ethylbenzene plants by using conventional design procedure. Nevertheless, the conventional design steps are not considering cost optimization of plant installed with relief system. Thus, the design pressure of protected equipment, piping diameter, and disposal treatment is set to be manipulated variables to determine the cost minimization. Pressure drops of inlet piping and backpressure are as constraint variables due to standard requirements. The standards state that inlet piping pressure drops should be below 3% of set pressure and outlet piping pressure drop to set pressure percentage based on range to determined types of the relief valve to be used. From that, optimum plant design with consideration of pressure relief system’s installation can be achieved by calculating the total cost of plant designed with relief system when set pressures are changed. As a result, dimethyl-ether plant shows a minimum point of the total cost at 170% of set pressure increment, which is lower than its original design. On the other hand, ethylbenzene plant gives optimum point at original design as the total cost is higher at set pressure increment.
Maintenance acts as a significant role in smoothening the operations in power plants. Risk and failure are some of the common problems in power plant leading to unexpected outages such as boiler shutdown or tube leakage. The rectification of these problems requires ceasing operations of the boiler which leads to a loss in the revenue annually. Therefore, this work was focused on prioritizing the maintenance activities and optimize the operational duration and cost by implementing risk-based maintenance (RBM) and particle swarm optimization (PSO). Previous literature implores that, RBM is commonly used in oil and gas industries to predict the risk or failure of the equipment. In this work, the RBM method was adopted accordingly to the power plant industries. The methodology is segregated into two main phases. First, the ranking and prioritization maintenance activities were performed using RBM. Then, the optimization of the operational duration and cost were simulated by PSO approached in MATLAB. The main outcome of this research is to act as a reference in adopting the best approaches to improve the power plant performance.
The continuous depletion of global oil reserves with the propensity for light distillates
propels the oil and gas industry to explore heavier fractions of crude oils with significant
amount of paraffin waxes. However, the precipitation and deposition of waxes during the
transportation of these waxy crude oils in the pipelines contribute to several issues, such as
the flowability reduction, excessive pumping cost, and wax gel formation, that adversely
affect the supposedly steady offshore oil production. As a result, substantial resources are
expended to resolve these flow assurance problems. The wax inhibitors and pour point
depressants are developed and modified to meet the wax remediation criteria. Essentially,
the wax crystals are formed through the nucleation, growth, and agglomeration processes,
while the deposition of these waxes occurs via molecular diffusion and shear dispersion.
The wax inhibitors are able to control the growth of wax crystals through nucleation, cocrystallization,
adsorption, and dispersion interactions. This paper particularly assessed
the following compounds: (1) polymeric wax inhibitors, (2) nano-hybrid pour point
depressants, (3) organic solvents, and
(4) surfactants. Given the significance of
these compounds in the deposition and
precipitation of waxes, it is imperative to
comprehensively explore the types and
nature of these compounds and their recent
applications as well as to critically assess
their strengths and drawbacks, which were
addressed in this paper. Furthermore, the
challenges of using these compounds and the factors that govern their efficiencies were also discussed. Accordingly, the carbon
length and the molecular weight of both paraffin waxes and wax inhibitors are among the
most influential factors.
Support vector machine (SVM) is one of the most popular algorithms in machine learning
and data mining. However, its reduced efficiency is usually observed for imbalanced
datasets. To improve the performance of SVM for binary imbalanced datasets, a new scheme
based on oversampling and the hybrid algorithm were introduced. Besides the use of a
single kernel function, SVM was applied with multiple kernel learning (MKL). A weighted
linear combination was defined based on the linear kernel function, radial basis function
(RBF kernel), and sigmoid kernel function for MKL. By generating the synthetic samples
in the minority class, searching the best choices of the SVM parameters and identifying
the weights of MKL by minimizing the objective function, the improved performance of
SVM was observed. To prove the strength of the proposed scheme, an experimental study,
including noisy borderline and real imbalanced datasets was conducted. SVM was applied
with linear kernel function, RBF kernel, sigmoid kernel function and MKL on all datasets.
The performance of SVM with all kernel functions was evaluated by using sensitivity,
G Mean, and F measure. A significantly improved performance of SVM with MKL was
observed by applying the proposed scheme.
Anaerobic composting is a promising method to fully transform food wastes into useful
materials such as biofertilizer and biogas. In this study, the optimum proportions of food
wastes containing vegetable, fruit and meat wastes with dry leaves or cow manure for
composting were determined using the simplex centroid design and response optimizer.
The effectiveness of the pilot-scale composting process was evaluated based on the targeted
compost quality of C/N ratio at 21, pH value at 8 and electrical conductivity of 1 dS/m.
Food wastes composting formulation with dry leaves suggested high percentage of dry
leaves, 86.9% with low food wastes composition of 13.1% constituted by vegetable waste
(1.1%), fruit waste (4.9%) and meat waste (7.1%). With cow manure formulation, only
6% of cow manure was recommended with
another 94.0% of food wastes contributed
by a fair mix of vegetable waste (23.2%),
fruit waste (34.3%) and meat waste (36.5%).
The developed regression models were
experimentally validated with predicted
responses obtained in acceptable ranges for
C/N ratio (21.2 - 21.8), pH (7.92 - 7.99) and
electrical conductivity (0.97 - 1.03 dS/m).
Titanium (Ti) and Ti-based alloys presence the most widely applied as advanced biomaterials
in biomedical implant applications. Moreover, these alloys are known to be the most
valuable metallic materials including spinal cord surgical treatment. It becomes an interest
due to its advantages compared to others, including its bio compatibility and corrosion
resistant. However, an issue arises when it comes for permanent implant application as
the alloy has a possible toxic effect produced from chemical reaction between body fluid
environments with alloys chemical compositions. It also relies on the performance of
neighbouring bone tissue to integrate with the implant surface. Abnormalities usually
happen when surrounding tissue shows poor responses and rejection of implants that would
leads to body inflammation. These cause an increase in foreign body reaction leading to
severe body tissue response and thus, loosening of the implant. Corrosion effects and
biocompatibility behaviour of implantation usage also become one of the reasons of
implant damage. Here, this paper reviews the importance of using Ti and Ti-based alloys
in biomedical implantation, especially in orthopaedic spinal cord injury. It also reviews the
basic aspects of corrosion effects that lead to implant mechanical damage, poor response
of body rejection and biocompatibility behaviour of implantation usage.
In this study, the effects of addition of ammonium and aluminium-based hardeners into
urea formaldehyde resin (UF) on the physico-mechanical properties and formaldehyde
emission of the rubberwood particleboard were investigated. Four types of hardeners,
namely ammonium chloride (AC), ammonium sulphate (AS), aluminium chloride (AlC)
and aluminium sulphate (AlS), were added into UF resin. The acidity, gelation time,
viscosity and free formaldehyde content of the UF/hardener mixtures were determined.
Particleboard made with the UF/hardener mixtures were tested for physico-mechanical
properties and formaldehyde emission. The pH values of the resin after addition of
aluminium-based hardeners were higher and resulted in higher viscosity and shorter
gelation time. Consequently, despite lower formaldehyde emission was recorded, the
physico-mechanical properties of the resulted particleboard were inferior compared to
that of ammonium-based hardeners. The best quality particleboard in terms of mechanical,
physical and formaldehyde emission were obtained from the particleboard made with AS,
followed by AC.