Proposed Hybrid Methodology Research Articles

Predicting ship machinery system condition through analytical reliability tools and artificial neural networks

Inadequate ship machinery maintenance can increase equipment failure posing a threat to the environment, affecting performance, having a great impact in terms of business losses by reducing ship availability, increasing downtime and moreover increasing the potential of major accidents occurring and endangering lives on-board. This paper aims to provide a systematic approach for identifying critical ship machinery systems/components and to analyse their physical parameters. Critical ship main engine systems/components are used as input in a dynamic time series neural network, in order to monitor and predict future values of physical parameters related to ship critical systems. The critical main engine systems/components and their relevant parameters to be monitored are identified though the combination of Fault Tree Analysis (FTA) and Failure Mode and Effects Analysis (FMEA). A case study of a Panamax size container ship is presented in which Artificial Neural Networks (ANN) are used to predict the upcoming values of all main engine cylinders exhaust gas temperatures. The forecasted results were validated through comparison with actual observations recorded on board the ship. The proposed hybrid methodology successfully presents a systematic approach for initially identifying critical systems/components through reliability modelling and tools and subsequently monitoring their physical parameters through neural networks.

Fischer-Trospch synthesis using iron-based catalyst in a microchannel reactor: Hybrid lump kinetic with ANNs/RSM

A hybrid methodology of using lump kinetic and of AANs (Artificial Neuron Networks)/RSM (Response Surface Methodology) was investigated for modeling Fischer-Tropsch (FT) synthesis in a microchannel reactor using iron-based catalyst in this work. This robust and cost-effective methodology was reliable to extensively analyze the effect of operating conditions including TOS (time on stream), partial pressures of different gases in reaction system (H2, CO, CO2 and H2O) on CO disappearance rate. With experimental data as training data set using ANNs and Box-Behnken design as design of experiment, the setup model was able to present good results in nonlinear noisy processes with significant changes of operational parameters in experimental design plan. The proposed hybrid methodology was able to provide comprehensive information such as reaction mechanism, the multiple combined effects on the studied response, and significance of process parameters during FT synthesis using iron-based catalyst in microchannel reactor.

Trace element soil contamination at a former shooting range in Athens, Greece

This study was focused on the determination of lead, zinc and nickel in a former shooting range in Athens, Greece. In order to propose a hybrid methodology, two analytical techniques were complimented, namely inductively coupled plasma mass spectrometry (ICP-MS) and X-ray fluorescence (XRF). Analysis by ICP-MS was carried out over a minimum of locations following international sampling guidelines whereas analysis by XRF was carried out using a portable device and over a denser sampling design. After analyzing certified reference materials, the reliability of both techniques was Pb>Zn>Ni. Linear correlation analysis between techniques suggests that at least some degree of homogenization must be carried out in the field to achieve reliable results with XRF. Characterization maps were built using data from both techniques. A comparison of areas of concern led to the conclusion that the proposed hybrid methodology allows a highly efficient delineation of the contamination and that additional improvement in the characterization can be reached by correcting the XRF data by calibration against ICP-MS measurements.

Fisher kernels match deep models

Deep models have recently shown improved performance on numerous benchmark tasks in computer vision and machine learning. The availability of huge amount of digital data, possibility of massively parallel computations on graphics processing units and the development of advance optimisation techniques have pushed the limits of the deep learning framework by superseding the performance of state-of-the-art research, in specific the kernel methods . This research proposes a novel connection between the two paradigms of research and shows empirical evidence to emphasise that the knowledge learnt from one domain could be supplemented with the significant properties of the other domain to achieve the best of both the worlds. The proposed hybrid methodology illustrates the advantages of deep architectures for kernel methods by showing significant improvement in the classification performance on benchmark tasks with kernel methods. It is shown empirically that the results achieved are either better or competitive to the leading benchmarks from support vector machines and deep models.

Optimization of processing parameters of AISI 316L laser welding influenced by external magnetic field combining RBFNN and GA

The external static magnetic field has significant influence on the microstructure and mechanical properties of weld bead during 316L stainless steel laser welding. The quality of a weld joint of laser welding supported by external magnetic field (LWSMF) is significantly influenced by the processing parameters. Hence, how to choose appropriate processing parameters for a good-quality weld joint of LWSMF is significantly important. This paper develops a hybrid methodology by combining radial basis function neural network (RBFNN) and genetic algorithm (GA) to address this issue. Firstly, the bead appearance, which is the external manifestation of the weld geometrical imperfection and weld quality, is quantitatively described and selected as the indices to judge the weld quality of LWSMF. Then the physical experiments are conducted, where laser power (LP), laser welding speed (WS), and the flux density of magnetic field (MFD) are taken into consideration as the input process parameters. Secondly, the RBFNN model, as its excellent global prediction performance, is adopted to establish the relationships between the inputs and outputs. Thirdly, based on the constructed RBFNN model, the effects of different input parameters on the bead appearance are analyzed and the global process parameter space exploration is performed by using GA. At last, the verification experiments are conducted to verify the effectiveness of the calculated optimal process parameters. Results demonstrate that the spatter defects decrease and the grains are refined under the influence of external magnetic after optimization. On the whole, the proposed hybrid methodology shows great promise for improving the effectiveness and stability of LWSMF.

Measuring logistics performance of OECD countries via fuzzy linear regression

In logistics, performance measurement has been considered as a key competency to acquire world class performance. In light of this, we presented a robust methodology to establish an analysis framework for measuring logistics performance. The proposed hybrid methodology is a combination of criteria importance through intercritera correlation (CRITIC), simple additive weighting (SAW), and Peters' fuzzy regression methods. To the best of our knowledge, country-based logistics performance is seldom studied in the literature. Therefore, we measured the logistics performance of Organization for Economic Cooperation and Development (OECD) countries using the devised model based on the data of Logistics Performance Index 2014 provided by the World Bank. The introduced methodology, which is suitable to model imprecise relationships among system parameters, appears to be a practical alternative approach for the assessment of logistics performance. It should be noted that the evaluation framework presented in this paper is not confined to performance measurement case and can also be exploited in addressing other multiple criteria decision-making problems incorporating uncertainty.

A novel hybrid methodology for short-term wind power forecasting based on adaptive neuro-fuzzy inference system

With the increased penetration of wind power into the electric grid of China, many challenges emerge due to its fluctuation and intermittence. In this context, it is crucial to achieve higher accuracy of the short-term wind power forecasting for safe and economical operation of the power system. Hence, this paper proposes a novel hybrid methodology for short-term wind power forecasting, successfully combining three individual forecasting models using the adaptive neuro-fuzzy inference system (ANFIS). The backpropagation neural network (BPNN), radial basis function neural network (RBFNN), and least squares support vector machine (LSSVM) are selected as the individual forecasting models. A new data preprocessing method based on Pearson correlation coefficient (PCC) is also applied for selecting proper inputs for three individual models. Results obtained show the advancement of the PCC based data preprocessing method. Also, the comparison studies demonstrate that the proposed hybrid methodology presents a significant improvement in accuracy with respect to three individual models.

The Double-Bay Layout Problem

The layout of a semiconductor manufacturing facility can play a significant role in reducing operating costs and improving productivity. This paper introduces the double-bay layout problem that is encountered in semiconductor fabrication. This new problem not only considers the assignment and relative ordering of machines in two bays but also determines the exact location of each machine, and incorporates two objectives of minimizing material handling cost and layout area. A hybrid methodology combining a multi-objective genetic algorithm with linear programming is proposed to solve this problem. The genetic algorithm effectively identifies the set of non-dominated machine sequences, while the linear program uses the relative assignments obtained by the genetic algorithm to determine optimal absolute machine locations. Experimental results indicate that the proposed hybrid methodology finds Pareto-optimal solutions for small-scale problems and high-quality solutions for problems of practical size.

SHORT-TERM TRAFFIC FLOW PREDICTION USING A METHODOLOGY BASED ON AUTOREGRESSIVE INTEGRATED MOVING AVERAGE AND GENETIC PROGRAMMING

The accurate short-term traffic flow forecasting is fundamental to both theoretical and empirical aspects of intelligent transportation systems deployment. This study aimed to develop a simple and effective hybrid model for forecasting traffic volume that combines the AutoRegressive Integrated Moving Average (ARIMA) and the Genetic Programming (GP) models. By combining different models, different aspects of the underlying patterns of traffic flow could be captured. The ARIMA model was used to model the linear component of the traffic flow time series. Then the GP model was applied to capture the nonlinear component by modelling the residuals from the ARIMA model. The hybrid models were fitted for four different time-aggregations: 5, 10, 15, and 20 min. The validations of the proposed hybrid methodology were performed by using traffic data under both typical and atypical conditions from multiple locations on the I-880N freeway in the United States. The results indicated that the hybrid models had better predictive performance than utilizing only ARIMA model for different aggregation time intervals under typical conditions. The Mean Relative Error (MRE) of the hybrid models was found to be from 4.1 to 6.9% for different aggregation time intervals under typical conditions. The predictive performance of the hybrid method was improved with an increase in the aggregation time interval. In addition, the validation results showed that the predictive performance of the hybrid model was also better than that of the ARIMA model under atypical conditions.

An empirical study for integrating XP with VTSP to improve business process

Actual problems that threaten organizations are the excessive unnecessary organizational processes. The Business Process Reengineering (BPR) methodology is developed to improve the return of investment rates within organization. BPR guides to rearranging processes and removing unnecessary ones and consolidating the remaining processes into linear open system. Unfortunately, usage of modern Information Technology doesn't solve such problems in the Middle East countries and especially Egypt and doesn't realize the expected results. The limitations and drawbacks of IT projects refer mainly to the dependency on plan-driven team software process methodology that could not achieve frequently requirement changes of customers and usually exceeds estimated budget of the project. This research adopted the eXtreme Programming methodology using virtual team software process work providers in order to avoid these drawbacks and applied the proposed hybrid methodology to three main departments within Suez Canal Authority in Egypt.

An integrated approach to machine selection problem using fuzzy SMART-fuzzy weighted axiomatic design

In respond to new market requirements and competitive positioning of manufacturing companies selecting optimal machines that are consistent with manufacturing goals is of crucial importance. As it involves multiple conflicting criteria and inherent ambiguity and vagueness, election of a suitable machine can be regarded as a fuzzy multi-criteria decision making problem. In this study, for the first time in the literature, an integrated approach consisting of fuzzy simple multiattribute rating technique (SMART) approach and fuzzy weighted axiomatic design (FWAD) approach is proposed to determining the optimal continuous fluid bed tea dryer for a privately owned tea plant operating in Turkey. The weights of the evaluation criteria are calculated via fuzzy SMART and then FWAD is utilized to rank competing machine alternatives in terms of their overall performance. In the FWAD application phase, five experts have determined functional requirements (FRs) and have rated alternatives. Therefore, individual fuzzy opinions were required to be aggregated in order to set up a group consensus. A group decision analysis, referred to as the least squares distance method is used to aggregating the ratings of FRs and alternatives. It is concluded that the proposed hybrid methodology is a robust decision support tool for ranking machine alternatives under fuzzy environment and furthermore, it can be exploited for other fuzzy decision making problems, as well.

A novel hybrid optimization methodology to optimize the total number and placement of wind turbines

Due to increasing penetration of wind energy in the recent times, wind farmers tend to generate increasing amount of energy out of wind farms. In order to achieve the target, many wind farms are operated with a layout design of numerous turbines placed close to each other in a limited land area leading to greater energy losses due to ‘wake effects’. Moreover, these turbines need to satisfy many other constraints such as topological constraints, minimum allowable capacity factors, inter-turbine distances, noise constraints etc. Thus, the problem of placing wind turbines in a farm to maximize the overall produced energy while satisfying all constraints is highly constrained and complex. Existing methods to solve the turbine placement problem typically assume knowledge about the total number of turbines to be placed in the farm. However, in reality, wind farm developers often have little or no information about the best number of turbines to be placed in a farm. This study proposes a novel hybrid optimization methodology to simultaneously determine the optimum total number of turbines to be placed in a wind farm along with their optimal locations. The proposed hybrid methodology is a combination of probabilistic genetic algorithms and deterministic gradient based optimization methods. Application of the proposed method on representative case studies yields higher Annual Energy Production (AEP) than the results found by using two of the existing methods.

Radio Access Technology Selection in Heterogeneous Wireless Networks Using a Hybrid Fuzzy-Biogeography Based Optimization Technique

Radio access technology (RAT) selection in heterogeneous wireless networks is a challenging task to achieve guaranteed quality of service (QoS). This paper proposes a hybrid methodology in order to accomplish QoS through high service connectivity and reliable network transparency in a wireless heterogeneous system. The proposed hybrid methodology integrates a non-homogenous biogeography based optimization (NHBBO) with a parallel fuzzy system (PFS). The PFSs are employed to determine the probability of RAT selection, which acts as an input to the NHBBO procedure. Thus the NHBBO decide over the defined multi-point decision making algorithm to select the best RAT in the given heterogeneous network. The key role of the proposed technique is to optimize the weight coefficients of multi-point decision making algorithm and ensure maximum user satisfaction ratio to select best RAT. Several experiments are carried out using the proposed NHBBO---PFS technique to demonstrate the effectiveness and robustness in producing solutions compared to a few existing methods for RAT selection in heterogeneous wireless networks.

Integration of fuzzy ANP and fuzzy TOPSIS for evaluating carbon performance of suppliers

Previous studies have proven that enterprises addressing green supply chain management problem may produce an apparent improvement to their stockholder interests. According to the report of Kearney (Carbon Disclosure Project: supply chain report 2010. CDP, London, 2010), more than 80 % of the carbon emissions are generated from the suppliers’ activities in a company’s performance. Many members of the project claimed that they will reassess their suppliers as soon as possible. Therefore, to combine the carbon management issue and supplier evaluating problem turns to be a very crucial work. Therefore, this study intends to develop a framework of the supplier evaluating process for carbon management by integrating fuzzy ANP and fuzzy TOPSIS approaches. Thirteen criteria of carbon management under four dimensions were identified by literature review and modified according to the opinion of seven experts in the environmental department. The model result in a case company shows that three of the most important criteria are “carbon governance,” “carbon policy” and “carbon reduction targets.” The proposed hybrid methodology has great ability to explain the vagueness of decision maker’s expression and better discrimination power to evaluate suppliers in carbon management.

A new hybrid optimization algorithm for multiple mobile robots navigation based on the CS-ANFIS approach

In this article, a novel hybrid navigation technique is discussed for multiple mobile robots in an unknown clustered environment. This new hybrid navigational methodology is based on the cuckoo search algorithm for training the premise part and the least square estimation method for training the consequent parameters of the adaptive neuro-fuzzy inference system. The proposed hybrid optimal path planner is developed based upon a reference motion, direction, distances between the robot and the obstacles, and distances between the robot and the target, to calculate the suitable steering angle. In order to avoid collision against one another, a set of collision prevention rules are embedded into each robot controller, using the Petri Net model. The effectiveness of the algorithm has been demonstrated through a series of simulation experiments. The experimental results are conducted in the laboratory, using a real mobile robot to validate the versatility and effectiveness of the proposed hybrid technique. A comparison of the simulation and experimental results showed, that there is good agreement between them. The results obtained from the proposed hybrid technique are validated by comparison with the results from other intelligent techniques. Finally, it is concluded that the proposed hybrid methodology is efficient and robust in the sense, that it can be implemented in the robot for navigation in any complex terrain.

A grey-based decision-making approach for selecting a reverse logistics provider in a closed loop supply chain

Return of used products is gaining great worldwide attention due to resource depletion, environmental degradation, government legislation, and public awareness. Nowadays, reverse logistics is considered very important for organisations to improve their environmental and financial performance. Therefore, industries are turning to third–party reverse logistics providers (3PRLPs) for reusing, recycling, and remanufacturing of their products. In this paper, a multi–criteria decision making (MCDM) model is developed to guide the selection process of best 3PRLP. The proposed hybrid methodology is based on analytical hierarchy process (AHP) and grey relational analysis for 3PRLP selection and evaluation. This paper uses grey numbers for expressing ambiguity of the real world data and subjectivity of decision makers' assessments and presents a grey possibility degree for ranking 3PRLPs. To validate the capability of the proposed model a numerical example is presented in an automotive industry. Finally, managerial implications and future research directions conclude the paper.

Ranking alternative strategies by SWOT analysis in the framework of the axiomatic fuzzy set theory and the ER approach

SWOT Strengths, Weaknesses, Opportunities and Threats analysis is one of the most widely used strategic planning and decision making tool. However, it still has some structural problems such as the lack of prioritization of the alternatives, and too many extractable strategies. In this paper, we suggest a new approach to ranking the strategy alternatives via the SWOT analysis by making use of the Axiomatic Fuzzy Set AFS theory to find the best description of the alternatives and use the Evidential Reasoning ER approach in the light of AFS to rank the alternatives. The advantages of using the hybrid method AFS theory and ER approach to rank the alternatives are that: arbitrary “values in between” of the Expected Utilities are avoided; Decision Makers DMs do not need to give subjective judgments to the values of the degree of belief but instead, degrees of belief are directly obtained from the database via AFS theory. A comparison analysis with previous methodologies is made, and it is shown than the proposed hybrid methodology provides a far higher flexibility and effectiveness.

Selecting “The Best” ERP system for SMEs using a combination of ANP and PROMETHEE methods

Enterprise Resource Planning (ERP) system, which integrates all of the units within an organization at the information level, plays an important role for a successful enterprise. With the right ERP system, it is easier to provide coordination between the units, eliminate waste and make faster and better decisions. Adopting an ERP system is a significant investment decision for a firm, therefore a great deal of attention should be given to the selection of the right system. Since there are a large number of criteria to consider in selecting an ERP system, the process itself is regarded as a complex multi-criteria decision making problem. In this study, two prevalent multi-criteria decision making techniques, Analytic Network Process (ANP) and Preference Ranking Organization Method for Enrichment Evaluations (PROMETHEE), are used in combination to better address the ERP selection problem. First, ANP is used to determine the weights of all criteria, and then, the obtained weights are used in the PROMETHEE method for optimal ranking of the alternative system choices. To demonstrate the viability of the proposed methodology, an application case is performed on the ERP selection problem for the Small Medium Enterprises (SMEs) in İstanbul, Turkey. The proposed hybrid methodology successfully ranked the alternatives and identified the best ERP system based on the information obtained from a number of SMEs participated in this study.

Wavelet-based adaptive simulations of three-dimensional flow past a square cylinder

AbstractThe wavelet-based eddy capturing approach is extended to three-dimensional bluff body flows, where the flow geometry is enforced through Brinkman volume penalization. The wavelet-collocation/volume-penalization combined method is applied to the simulation of vortex shedding flow behind an isolated stationary prism with square cross-section. Wavelet-based direct numerical simulation is conducted at low supercritical Reynolds number, where the wake develops fundamental three-dimensional flow structures, while wavelet-based adaptive large-eddy simulation supplied with the one-equation localized dynamic kinetic-energy-based model is performed at moderately high Reynolds number. The present results are in general agreement with experimental findings and numerical solutions provided by classical non-adaptive methods. This study demonstrates that the proposed hybrid methodology for modelling bluff body flows is feasible, accurate and efficient.

A bi-objective constrained optimization algorithm using a hybrid evolutionary and penalty function approach

Constrained optimization is a computationally difficult task, particularly if the constraint functions are nonlinear and non-convex. As a generic classical approach, the penalty function approach is a popular methodology which degrades the objective function value by adding a penalty proportional to the constraint violation. However, the penalty function approach has been criticized for its sensitivity to the associated penalty parameters. Since its inception, evolutionary algorithms have been modified in various ways to solve constrained optimization problems. Of them, the recent use of a bi-objective evolutionary algorithm in which the minimization of the constraint violation is included as an additional objective has received significant attention. In this article, a combination of a bi-objective evolutionary approach with the classical penalty function methodology is proposed, in a manner complementary to each other. The evolutionary approach provides an appropriate estimate of the penalty parameter, while the solution of an unconstrained penalized function by a classical method induces a convergence property to the overall hybrid algorithm. The working of the procedure on a number of standard numerical test problems and an engineering design problem is demonstrated. In most cases, the proposed hybrid methodology is observed to take one or more orders of magnitude fewer function evaluations to find the constrained minimum solution accurately than some of the best reported existing methodologies.