Papers by Abdullahil Azeem
Page 1. - 1459 - Application of Adaptive Neuro-Fuzzy Inference System (ANFIS) to predict the ulti... more Page 1. - 1459 - Application of Adaptive Neuro-Fuzzy Inference System (ANFIS) to predict the ultimate bearing capacity of shallow foundation on cohesionless soil Saeed Shakiba rad Graduate Student, Department of Civil Engineering ...
2009 1st International Conference on the Developements in Renewable Energy Technology (ICDRET), 2009
Solar PV Micro-Utility is the concept of Solar PV extension where power rather than the solar ele... more Solar PV Micro-Utility is the concept of Solar PV extension where power rather than the solar electric systems are offered to the rural poor. In this system, one will never be the owner of the system, but one can use the Solar PV system by paying a daily tariff. Several rural markets have already been electrified through Solar PV under
Techniques and Principles, 2012
This paper addresses the selection of optimal shift numbers considering inventory information, cu... more This paper addresses the selection of optimal shift numbers considering inventory information, customer requirements and machine reliability using fuzzy logic.
International Journal of Industrial Engineering Computations, 2011
In this paper, an artificial neural network (ANN) model is developed to determine the optimum lev... more In this paper, an artificial neural network (ANN) model is developed to determine the optimum level of finished goods inventory as a function of product demand, setup, holding, and material costs. The model selects a feed-forward back-propagation ANN with four inputs, ten hidden neurons and one output as the optimum network. The model is tested with a manufacturing industry data and the results indicate that the model can be used to forecast finished goods inventory level in response to the model parameters. Overall, the model can be applied for optimization of finished goods inventory for any manufacturing enterprise in a competitive business environment.
Journal of Mechanical Engineering, 2009
practices to improve manufacturing performances in manufacturing companies. The focus of this wor... more practices to improve manufacturing performances in manufacturing companies. The focus of this work is to find out the frequencies and time duration of machine breakdowns as well as the major causes of breakdowns affecting productivity. Total quality management (TQM) was introduced to improve continually the products or services to increase the customer satisfaction level. SPC is an important tool of TQM. Again HDS is the real time view of production floor of any manufacturing industry. In usual practice, SPC is used as quality control tool. However in this research SPC is used to increase total output identifying major loss times from various machine breakdowns using HDS. Successful implementation of the recommendations of this paper can significantly improve the manufacturing performance of a manufacturing environment.
International Journal of Services and Operations Management, 2013
Job shop scheduling problems are one of the oldest combinatorial optimisation problems being stud... more Job shop scheduling problems are one of the oldest combinatorial optimisation problems being studied. In this paper, fuzzy processing times of operations and fuzzy due dates of jobs are considered to incorporate fuzziness in the problem. Percentage of inventory consumption and profit earned form the orders are also considered in this fuzzy multi-objective job shop scheduling problem. Fuzzy inference system (FIS) is used to calculate the job weights based on the percentage of inventory consumption for a particular job and profit can be earned from the jobs. Average weighted tardiness, number of tardy jobs, total flow time and idle times of machines are considered as objectives which should be minimised. In this paper, genetic algorithm (GA) is used as a heuristic technique with specially encoded chromosomes that denotes the complete schedule of the jobs. A local search technique, simulated annealing (SA) is also used to compare the results obtained in two different methods. Different problem sizes has been tested and the fitness function values and computation times of the problems for each method is compared.
International Journal of Quality and Innovation, 2009
International Journal of Productivity and Performance Management, 2013
ABSTRACT Purpose – Managers encounter many decisions that require the simultaneous use of differe... more ABSTRACT Purpose – Managers encounter many decisions that require the simultaneous use of different types of data in their decision-making process. A critical decision area for managers is the performance evaluation of personnel, whether individually or as a member of a team. Performance evaluation is critically essential for the effective management of the human resource of an organization and evaluation of staff that help develop individuals, improve organizational performance, and feed into business planning. Design/methodology/approach – Performance evaluations require and often involve disparate types of information that are vague, incomplete, objective, and subjective. This paper proposes a performance evaluation system of employees considering various performance evaluation criteria using fuzzy logic. The main task in the proposed approach involves determining the performance indices of employees considering their respective performance in various qualitative and quantitative evaluation criteria and then selecting the best employee who holds highest performance index comparing all the indices. Findings – A model is developed for any kind of organization where performance evaluation is significantly important for staff motivation, attitude and behavior development, communicating and aligning individual and organizational aims, and fostering positive relationships between management and staff. Fuzzy control is used to determine the overall performance index by combining results of the performance in selected criteria and provided it in numerical values which will undoubtedly ensure convenience of the concerned human resource personnel during performance rating calculation. Originality/value – This is the first time, a performance evaluation model is developed using fuzzy approach for any kind of organization where performance evaluation is significantly important for staff motivation, attitude and behavior development, communicating and aligning individual and organizational aims, and fostering positive relationships between management and staff.
International Journal of Production Research, 2012
International Journal of Logistics Systems and Management, 2014
In this paper, a production inventory model with reliability of production process is developed t... more In this paper, a production inventory model with reliability of production process is developed to minimise total inventory cost. Production, setup, holding, inspection, depreciation, rejection and backorder cost are considered to develop the model. The economic production lot size and the reliability of the production process along with the production period are the decision variables and total cost per cycle is the objective function which is to be minimised. A meta-heuristic particle swarm optimisation (PSO) algorithm is applied to solve the unconstrained non-integer non-linear form of objective function. Some numerical examples have been presented to explain the model. The results obtained from PSO algorithm are compared with results obtained from genetic algorithm (GA) applying on the same inventory model. Comparison clearly shows the superiority of PSO results over GA results thus makes PSO a better choice for this kind of modelling.
International Journal of Industrial and Systems Engieering, 2013
This paper develops an artificial neural network (ANN) model to forecast the optimum demand as a ... more This paper develops an artificial neural network (ANN) model to forecast the optimum demand as a function of time of the year, festival period, promotional programmes, holidays, number of advertisements, cost of advertisements, number of workers and availability. The model selects a feed-forward back-propagation ANN with 13 hidden neurons in one hidden layer as the optimum network. The model is validated with a furniture product data of a renowned furniture company. The model has also been compared with a statistical linear model named Brown's double smoothing model which is normally used by furniture companies. It is observed that ANN model performs much better than the linear model. Overall, the proposed model can be applied for forecasting optimum demand level of furniture products in any furniture company within a competitive business environment.
International Journal of Computer Aided Engineering and Technology, 2012
The parametric interpolators of modern CNC machines use Taylor's series approximation to generate... more The parametric interpolators of modern CNC machines use Taylor's series approximation to generate successive parameter values for the calculation of x, y, z coordinates of tool positions. In order to achieve greater accuracy, higher order derivatives are required at every sampling period which complicates the calculation for contours represented by NURBS curve. In addition, this method calculates the chordal error in a given segment through estimation of the curvature neglecting a fraction of the error. In order to avoid calculating higher derivatives and make the calculations simpler, this paper proposes the classical fourth-order Runge-Kutta (RK) method for the determination of successive tool positions requiring the calculation of the first derivatives only. Furthermore, a method of estimating the chordal error on the average value of parameters at the end points of a given curve segment is proposed here that does not require the calculation of curvature at every segment. Finally, a variable feedrate interpolation scheme is designed combining the RK method of parameter calculation and the proposed method of chordal error calculation. Results show that reduced chordal error and feedrate fluctuations are achievable with the proposed interpolator compared to the conventional interpolator based on Taylor's approximation with higher order terms.
International Journal of Business Information Systems, 2013
Power demand forecasting is a significant factor in the planning and economic and secure operatio... more Power demand forecasting is a significant factor in the planning and economic and secure operation of modern power system. This research work has compared different forecasting techniques and opted to find out better technique in context of power generation, which varies rapidly from time to time. The dataset has been generated from yearly demand of electricity of Bangladesh for last five years. Year, irrigation season, temperature and rainfall amount have been considered as input parameters where as single output is demand of load in adaptive neuro-fuzzy inference system (ANFIS). Another artificial intelligence technique, artificial neural network (ANN) has been used to validate the output results. The best suited traditional technique for forecasting power generation is seasonal forecasting. Seasonal forecasting is also used to compare with ANFIS and ANN to find out better technique. The result of experiment indicates that ANFIS is superior method to tackle forecasting of power generation from different error measures.
The International Journal of Advanced Manufacturing Technology, 2006
This paper presents a method of generating efficient three-axis ball-end milling tool paths direc... more This paper presents a method of generating efficient three-axis ball-end milling tool paths directly from point cloud data. The primary objective is to achieve high efficiency in the machining of free-form surface geometry having isolated complex machining area. The high machining efficiency is attained by segmenting the entire machining domain into distinct areas according to the geometric complexity of the data points and by using cutters of different sizes for the segmented machining areas. An iterative numerical procedure is derived to determine the critical complexity that separates the data points with higher complexity (the complex points) from those with lower complexity (the non-complex points). A larger and more efficient ball-end mill is used to machine the area defined by the non-complex points. The gouging condition of all the data points is then evaluated with respect to the given ball-end mill. The isolated complex machining area is established by enclosing both the complex points and the gouge points. The smaller and gouge-free ball-end mill for the isolated complex machining area is subsequently selected from the standard commercial cutter series. Implementation of the presented method clearly demonstrates the high efficiency of the generated tool paths.
Proceedings of the 8th International Conference on Mechanical Engineering, 2009
Pareto and cause-effect analysis are two major tools to address quality issues. This paper focuse... more Pareto and cause-effect analysis are two major tools to address quality issues. This paper focuses on the process of identifying and analyzing the defects of a pharmaceutical product using these tools. Pareto analysis is used to find out the major problems of the defective products and cause-effect analysis is considered to find out the main causes and sub causes behind that problems. To eliminate the causes and sub causes which are responsible to make defective products, it is very important to identify causes, sub causes and their exact location in the system. In this paper the main problems, causes, sub causes and exact location of causes and sub causes are identified using pareto and cause-effect analysis. Capping, edge-chipping and broken tablets have been found as the vital problems for producing defective products. Few root causes are identified though cause-effect analysis which are responsible for the mentioned problems.
International Journal of Industrial Engineering: Theory, Applications and Practice, 2010
This paper addresses the Hybrid Flow Shop (HFS) scheduling problems to minimize the total work-in... more This paper addresses the Hybrid Flow Shop (HFS) scheduling problems to minimize the total work-in-process inventory. Job scheduling problems are one of the oldest and real world combinational optimization problems. It is multi objective and complex in nature. There exist some criteria that must be taken into consideration when evaluating the quality of the proposed schedule. Consideration of job and machine reliability is very important during assignment of jobs in each stage to get realistic hybrid flow shop schedule. In this paper, flow shop problem concerns the sequencing of a given number of jobs through a series of machines in the exact same order on all machines with the aim to satisfy a set of constraint as much as possible and optimize a set of objectives. Fuzzy sets and logic can be used to tackle uncertainties inherent in actual flow shop scheduling problems. Fuzzy due dates, cost over time and profit rate result the job priority and to determine the machine priority processing time of each machine is considered. MATLAB fuzzy tool box is used to calculate the priorities of jobs and machines at different stages. Finally, jobs are assigned into machines based on a grouping and sequencing algorithm that minimizes the total work-in-process inventory.
This paper develops an artificial neural network (ANN) model to forecast the optimum level of raw... more This paper develops an artificial neural network (ANN) model to forecast the optimum level of raw materials inventory as a function of product demand, manufacturing lead-time, supplier reliability, material holding cost, and material cost. The model selects a feed-forward back-propagation ANN with twelve hidden neurons as the optimum network. We test the model with pharmaceutical company data. The results show that the model can be useful to forecast raw material inventory level in response to different parameters. We also compare the model with fuzzy inference system (FIS) and simple economic order quantity (EOQ). It can be seen that ANN model outperforms others. Overall, the model can be applied for forecasting of raw materials inventory for any manufacturing enterprise in a competitive business environment.
International Journal of Business Information Systems, 2012
Load forecasting is a significant factor in the planning and economic and secure operation of mod... more Load forecasting is a significant factor in the planning and economic and secure operation of modern power system. This research work has compared different forecasting techniques and opted to find out better technique in context of load generation, which varies rapidly from time to time. The dataset has been generated from yearly demand of electricity of Bangladesh for last five years. Four factors have been considered as input parameters (Year, Irrigation season, Temperature, Rainfall amount) where as single output is demand of load in adaptive neuro fuzzy inference system (ANFIS). Another artificial intelligence technique, artificial neural network (ANN) has been used to validate the output results. The best suited traditional technique for forecasting load generation is seasonal forecasting. Seasonal forecasting is also used to compare with ANFIS and ANN to find out better technique. The result of experiment indicates that ANFIS is superior method to tackle forecasting of load generation from different error measures.
Uploads
Papers by Abdullahil Azeem