Development of a network data envelopment analysis (DEA) model to measure the performance of the production line

The production line in manufacturing industry usually consists of several processes and must go through performance measurement to determine whether they are efficient or inefficient. One of the methods widely used for performance measurement by the organizations is the Data Envelopment Analysis (DE...

Full description

Saved in:
Bibliographic Details
Main Author: Nor Affaf, Mohd Zainal Abiddin
Format: Thesis
Language:English
Published: 2020
Subjects:
Online Access:http://umpir.ump.edu.my/id/eprint/30392/1/Development%20of%20a%20network%20data%20envelopment%20analysis%20%28DEA%29%20model.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The production line in manufacturing industry usually consists of several processes and must go through performance measurement to determine whether they are efficient or inefficient. One of the methods widely used for performance measurement by the organizations is the Data Envelopment Analysis (DEA). Data Envelopment Analysis (DEA) is a non-parametric technique used to measure the efficiency of the Decision Making Units (DMUs) which use common inputs to produce common outputs, while DMU refers to the entity that is going to be measured by the DEA. The DEA is considered to be one of the most widely used techniques to measure the performance of the DMUs. However, the organizations cannot use the traditional DEA model to obtain the efficiency scores for internal production line because this model cannot measure the inside of the production line and does not take into account the relationship between each process. Thus, the Network DEA can be used to measure the performance of the production line in details by measuring the processes in the production line as well. The organizations need to consider the relationship between each of the process because when some of the processes do not perform efficiently, then it might affect the efficiency of the entire processes as well. The objectives of this research are to develop the Network DEA model based on the actual production line and to obtain the efficiency scores from the Network DEA model developed. This research begins by reviewing previous researches to study the DEA techniques and the data required. Then, the data consist of the inputs consumed and the outputs produced by each sub DMUs was collected to be implemented during the network model development and the efficiency calculation. During this research, the framework of developing the Network DEA model was created as a guideline for the researchers or the companies to develop the network model based on their own production line. The network model was developed in this research and they reflected the actual production line and also show the relationship of each sub DMUs measured in details. This network model also acts as a validation to the framework acknowledge that the models developed in this research or that are going to be developed in the future using this framework can be a passable representation of the production line in the real world. Once the model was developed, the calculations of the efficiency were done by using the software called MaxDEA and the results obtained were displayed in table. Among all five DMUs, DMU 2 and DMU 3 were shown to be efficient with the overall efficiency scores of 1 and DMU 1 was shown to be the most inefficient with the lowest overall efficiency scores of 0.988602. Although DMU 1, DMU 4 and DMU 5 were inefficient, the total efficiency scores for each of them were approximately close to 1. In conclusion, a Network DEA model was developed based on the actual production line in one of the companies in Malaysia. The efficiency scores of the Network DEA model developed was also obtained using the network model developed. As for contributions, the Network DEA model can be developed by companies based on their actual production line to measure the internal production line and to detect where the inefficiency might occur during the production. In other words, it can help companies to strive for continuous improvement only where necessary.