Explore the vast range of titles available.

In this paper, we have utilized artificial neural networks (ANN) for pattern recognition of the most common patterns which occur in quality control charts. After detecting such patterns, it is possible to relate these patterns to their causes. This could find extreme importance for on-line quality monitoring and on-line trouble shooting. It could be possible to detect problems before they become serious and the operator has to shut the line down or the process may produce defective parts. In this work, we have attempted to explore the effect of the training parameters on the performance of the neural network. The training parameters are important because they emphasis the required performance and the accuracy required from the neural network. A resolution IV fractional factorial experiment is utilized to explore a portion of the range of selected parameters to obtain better performance of the neural network. The results showed that many parameters usually assigned by experience such as minimum shift, shift range, population size and shift percentage, have significant effect on the performance of the ANN, while others such as network size and window size do not have major significance on the performance of the net. [PUBLICATION ABSTRACT]

The cement industry provides high wear environment for many casting units which results in high production costs and consumes both the time and efforts of different available skills to investigate and replace the worn parts. Aims to consider a predictive system for the wear of such units that will reduce the related unpredicted incidents. In this work, cement mill shell liners are non-repairable castings and subjected to accelerated deterioration process as the operational hours and hence the production increases. Both decision variables and their interaction were used to construct models that best describe the wear process of the shell lines for two compartments' ball mill. Data from past records were used and analyzed using the statistical package SPSS version 10.0. Findings - The best regression model for each compartment was found to be exponential function but with different shape parameters. Some data were used to validate the model using statistical calculations of errors. The proposed models were used to develop the best operational time for liners' replacement strategy. The findings of the optimal replacement time resulted in higher mill productivity, lower specific power consumption, reduced spare parts cost and reduced production loss for unjustified mill stoppages. Develops a mathematical model for cement mill shell liners' life to determine the optimal replacement strategy. [PUBLICATION ABSTRACT]

The paper presents an intelligent system to enhance mass lesions in digitized mammogram images. This system can assist radiologists in detecting mass lesions in mammogram images as an early diagnosis of breast cancer. In this paper, the early detection of mass lesion is visually detected by enhancing mass lesions in mammogram images using hybrid neuro-fuzzy technique. Fuzzified engine is proposed as a first step to convert all pixels in mammogram image to a fuzzy value using three linguistic labels. After that, artificial neural networks are used instead of the inference engine to accurately detect the mass lesions in the mammogram images in a short time. Finally, five linguistic labels are used as a defuzzifier engine to restore the mammogram image. Processed mammogram images are extensively evaluated using two different types of mammogram resources, mammographic image analysis society (MIAS) and University of South Florida (USF) databases. The results show that the proposed intelligent computer aided diagnosis system can successfully enhance the mass lesions in mammogram images with minimum number of false positive regions.

In the cement industries maintenance cost consumes approximately 20-25 per cent of the total production cost, which comes in the second rank after the energy cost. Therefore, cement plants in Jordan, taken as a case study that represents developing countries, are facing big challenges in reducing both energy and maintenance costs. In order to improve the maintenance system in the Fuhais plant, auditing of the existing maintenance system had been conducted, since this step is essential in improving any maintenance system. A quantitative (statistical) method was used in order to determine the weakness points in the existing maintenance system. Where based upon this auditing, several actions and strategies were put in a medium-range plan to resolve the problems and improve the system.

Purpose - The cement industry provides high wear environment for many casting units which results in high production costs and consumes both the time and efforts of different available skills to investigate and replace the worn parts. Aims to consider a predictive system for the wear of such units that will reduce the related unpredicted incidents.Design methodology approach - In this work, cement mill shell liners are non-repairable castings and subjected to accelerated deterioration process as the operational hours and hence the production increases. Both decision variables and their interaction were used to construct models that best describe the wear process of the shell lines for two compartments' ball mill. Data from past records were used and analyzed using the statistical package SPSS version 10.0.Findings - The best regression model for each compartment was found to be exponential function but with different shape parameters. Some data were used to validate the model using statistical calculations of errors. The proposed models were used to develop the best operational time for liners' replacement strategy.Practical implications - The findings of the optimal replacement time resulted in higher mill productivity, lower specific power consumption, reduced spare parts cost and reduced production loss for unjustified mill stoppages.Originality value - Develops a mathematical model for cement mill shell liners' life to determine the optimal replacement strategy.

Purpose The cement industry provides high wear environment for many casting units which results in high production costs and consumes both the time and efforts of different available skills to investigate and replace the worn parts. Aims to consider a predictive system for the wear of such units that will reduce the related unpredicted incidents. Designmethodologyapproach In this work, cement mill shell liners are nonrepairable castings and subjected to accelerated deterioration process as the operational hours and hence the production increases. Both decision variables and their interaction were used to construct models that best describe the wear process of the shell lines for two compartments' ball mill. Data from past records were used and analyzed using the statistical package SPSS version 10.0. Findings The best regression model for each compartment was found to be exponential function but with different shape parameters. Some data were used to validate the model using statistical calculations of errors. The proposed models were used to develop the best operational time for liners' replacement strategy. Practical implications The findings of the optimal replacement time resulted in higher mill productivity, lower specific power consumption, reduced spare parts cost and reduced production loss for unjustified mill stoppages. Originalityvalue Develops a mathematical model for cement mill shell liners' life to determine the optimal replacement strategy.

Just-In-Time (JIT) can be defined as a production system designed to eliminate waste in manufacturing environment. Toyota has established the kanban system to maintain its Just-In-Time production. Since the number of kanbans in the kanban system is equivalent to the amount of inventory of a part, it should be kept as small as possible. A mathematical programming model and a solution procedure for the kanban system in a multi-stage, assembly-tree-structure production setting with limited inventory capacity for each stage, variable demand, unreliable machines, and multi-product production capability were developed. The kanban system was modeled as a stochastic process. The obtained stochastic model was transformed into an equivalent mixed integer nonlinear programming model with large number of variables and constraints. This model can assist the production manager in determining an optimal kanban utilization policy in the system. The objective is to minimize the total inventory investment. Number of detached kanbans, WIP materials, and raw materials which are injected into the system by management at the beginning of the planning horizon are treated as the decision variables. As a result of an intensive search for a tool to solve the model using either a standard technique or a heuristic one, tabu search was found to have the versatility in applications and the superiority over other alternative heuristic methods. Due to that and to the complex nature of the problem, tabu search was used to solve the model. The model solution procedure was coded using FORTRAN 77. Examples were developed and presented to illustrate the model and solution procedure. Different combinations of levels of the parameters of the kanban system were studied in detail. This helps in utilizing the proposed model and solution procedure in planning and managing the real JIT production systems. Furthermore, the impact of changing the inventory capacity of each stage, the expected demand for the final product, the production capacity of each workstation, the reliability level of each workstation, and the container capacity on the number of kanbans in the system were investigated in detail.

In the cement industries maintenance cost consumes approximately 2025 per cent of the total production cost, which comes in the second rank after the energy cost. Therefore, cement plants in Jordan, taken as a case study that represents developing countries, are facing big challenges in reducing both energy and maintenance costs. In order to improve the maintenance system in the Fuhais plant, auditing of the existing maintenance system had been conducted, since this step is essential in improving any maintenance system. A quantitative statistical method was used in order to determine the weakness points in the existing maintenance system. Where based upon this auditing, several actions and strategies were put in a mediumrange plan to resolve the problems and improve the system.