Browsing by Author "Ferdous Sarwar, Dr."

Now showing 1 - 4 of 4

Application of DMAIC methodology for increasing total quality in ready-made garment
(Department of Industrial & Production Engineering, BUET, 2023-08-19) Shafiullah Shuvo, Md.; Ferdous Sarwar, Dr.
The economy of the world is changing rapidly. Bangladesh is no exception in this case. Moreover, most of the economy of Bangladesh relies on the Ready-made garment (RMG) sector at this moment. So it is very important to stay competitive in the global market. To maintain sustainable economic growth and compete in the global market, the resources need to be utilized precisely. To do this, reaching the required quality in every product is a must. Again, it is mandatory for an industry to maximize profit margin and minimize the production cost to survive in the global business arena. But rejected or defective garments are the main barrier. Considering this issue, defect minimizationby applying DMAIC (Define, Measure, Analyze, Improve and Control) methodology in a private garments factoryis the prime objective of this research. Especially, sewing defects were identified and analyzed here. Several tools such as Flow chart, SIPOC (Suppliers, Inputs, Process, Outputs, and Customers), Quality Function Deployment(QFD) were applied to get better visualization of the present state of the factory. Then most occurring defects were detected by performing Pareto chart. It showed that six types of defects were responsible for 70% of the total defects. Furthermore, the root causes of these major defects were found out by applying cause and effect diagram. In the end, the severity among these major defects were identified by using Failure Modes and Effects Analysis (FMEA) technique and provided some action plans to prevent these defects.The suggestions were made based on brainstorming and the previous job experience and also got ideas from the experts from different areas of textile and ready-made garment factory. By using this method, a noticeable improvement in the sewing department can be achieved. The lower the defect rate in production, the higher the profit will be guaranteed, which will provide the organization a competitive advantage in the worldwide market. To find out the main problems and provide solutions based on those problems, DMAIC (Define, Measure, Analyze, Improve and Control) is the most organized and systematic method. Besides,using and understanding the procedure of the DMAIC methodisrelatively simple and easy.
Development of a planned preventive maintenance (PPM) model using a machine learning approach
(Department of Industrial and Production Engineering(IPE), BUET, 2020-10-24) Fouzder, Puspendu Kumar; Ferdous Sarwar, Dr.
Planned preventive maintenance with some expert system is essential for appropriate planning and utilization of maintenance policy effectively and efficiently. A number of preventive maintenance model have been developed that have identified several factors which performed the models by subjective means. However, these models often lack robustness due to bias and variance. Now, the increased availability of data opens the scope of applying machine learning technique to predict the maintenance requirement more accurately and cost effectively.The aim of this research work is to develop a planned preventive maintenance model by using machine learning algorithms (SVM and SVR) that can forecast the maintenance requirements more accurately and cost effectively. To develop the model machine reliability is considered and the reliability depends on various subjective and objective measures which is a data driven approach. The subjective and objective features of Diesel Generator (DG) have been selected from literature and expert opinions and the data are collected from field survey. Two separate feature selection methods have been used to select the best feature set to improve the model accuracy. Wrapper method used correlation-based features selection to rank the features and generate eight different feature sets following backward elimination process. Filtering method eliminates the insignificant features by ANOVA test and selects the significant feature sets. All these feature sets aregenerated a total 54 number of different models with different accuracy level. Among them the best feature set have been selected with an accuracy of 92.5% from Wrapper method. Finally, a regression model has developed using Support Vector Regression (SVR) to determine the machine reliability value.
Model for construction schedule and cost prediction using regularized gradient boosted regression tree algorithm
(2020-09-13) Tazim Ahmed, S. M.; Ferdous Sarwar, Dr.
Accurate prediction of construction schedule and cost plays critical role to project success. Many quantitative and associative models have been developed for more accurate prediction. However, these models often lack robustness due to bias and variance. Ensemble type of machine learning algorithm can perform well for prediction by balancing bias and variance. This study aims to develop construction schedule and cost prediction modelusing one of the recent ensemble machine learning algorithms named Gradient Boosted Regression Tree (GBRT).Data were obtained from 69 construction projects of Dhaka city of Bangladesh. These projects were categorized as low rise, medium rise and high rise buildings according to the number of floors. One-way ANOVA F-test has been applied to select the statistically significant features. Finally, the regularized GBRT has been applied to develop the construction schedule and cost prediction models. Performances of regularized GBRT models were compared to Support Vector Regression (SVR) and Multiple Linear Regression (MLR) models. Mean absolute percentage error (MAPE) and mean squared error (MSE) were used as performance metrics.One-way ANOVA feature selection method reveals that location, land size, floor height, floor area, number of basement, workforce level and number of floor had significant impact on schedule and cost prediction model for low rise buildings. For medium and high rise buildings,land size, floor area, number of basement, workforce level and number of floor are the most significant features. The resultsshow that regularized GBRT models havelower MAPEs and MSEs than SVR and MLR models. Therefore, regularized GBRT models have performed better than SVR and MLR models in construction schedule and cost prediction for low, medium and high rise buildings.
Performance evaluation of supply chain network in apparel industry: a case study
(Department of Industrial and Production Engineering(IPE), BUET, 2018-03-31) Aminul Islam, Md.; Ferdous Sarwar, Dr.
Supply chain management has become one of the most discussed topics in business literature and is by many organizations considered a key strategic element. Today, markets have become more dynamic with rapid changes in customer requirements. These rapid changes have increased the importance for companies to ensure that materials and information flow smoothly between the actors in a supply chain. Being able to measure supply chain performance is important since it leads to a greater understanding of the supply chain and provides important feedback on the improvement progress. In spite of companies’ and managers’ recognition of the importance of supply chain management, they often lack the ability to develop effective performance measures and metrics. In addition, relatively little literature covering PMSs and the selection of performance measures in the context of supply chain management exists. Here evaluated performance of supply chain in East west Industrial Park Ltd. A performance measure, or a set of performance measures, is used to determine the efficiency and/ or effectiveness of an existing system, or to compare competing alternative systems. Performance measures are also used to design proposed systems, by determining the values of the decision variables that yield the most desirable levels of performance. Due to complexity of supply chain nature, it is very difficult to measure its performance. In this study Supply Chain Operation Reference (SCOR) model has been used to measure supply chain performance. Four Key Performance Indicators (KPI) have been measured following the measurement of overall KPI which indicates the ultimate supply chain efficiency. The four KPI values are; Quantity and Timely Delivery 55.00%, Adherence to Production Target 69.30%, Quality Capability 14.18% and On-Time Shipment 82.83%. Overall efficiency of the supply chain is only 64.24% which is not well enough. Only On-Time-Shipment has higher KPI value. Other individual KPI values can be enriched by improving backward linkage, labor, management and production line efficiency and also improving the quality level. However, PPC and TQM will play a vital role to improve overall KPI.