PMA Supplier Selection Using the Mahalanobis Taguchi System

PMA Supplier Selection Using the Mahalanobis Taguchi System

T.T. Wong (The Hong Kong Polytechnic University, Hong Kong)
Copyright: © 2008 |Pages: 8
DOI: 10.4018/978-1-59904-885-7.ch162
OnDemand PDF Download:
No Current Special Offers


Most hi-tech industries owe at least some of their success to being in the right place at the right time. This is especially true for the aircraft parts manufacturer approval (PMA) industry. A PMA is both a design approval and a production approval. It is issued for the production of modification or replacement parts for aircraft, which includes materials, parts, processes, and appliances. In the current economic climate, airlines throughout the world are looking for partners with financial stability. The reason is simple, they want partners that will continue to support them with extra savings opportunities in the short and long-term future. As more and more PMA companies are advertising through the Internet, a supplier performance measurement model applying to each of these networked organizations will facilitate the airline selection of long-term PMA partners. In this chapter, the Mahalanobis Taguchi System (MTS) approach, a multivariate data based selection system, will be used to identify the promising PMA suppliers. Suppliers who are known to be promising are called promising groups and their performance data sets are used to create a reference metric for the promising PMA supplier population. In view of the synergetic performance of neural network and data mining technologies, it is expected that this MTS-based PMA partner selection method, implementing through a neural data mining system (NDMS) will provide a practical solution in the identification of the promising PMA suppliers.

Key Terms in this Chapter

Online Analytical Processing(OLAP): A category of software tools that provides analysis of data stored in a database. OLAP tools enable users to analyze different dimensions of multi-dimensional data. The major component of OLAP is the OLAP server, which sits between a client and a database management system (DBMS). The OLAP server understands how data is organized in the database and has special functions for analyzing the data. OLAP servers are available for nearly all the major database systems.

Signal-to-Noise Ratio: The ratio of desired sound to undesired background noise. The larger the figure, the purer is the sound. Dr. Taguchi’s signal-to-noise ratios (S/N), which are log functions of desired output, serve as objective functions for optimization, help in data analysis and prediction of optimum results.

Original Equipment Manufacturer (OEM): Manufacturers who resell another company’s product under their own name and branding. An OEM refers specifically to the act of a company re-branding a product to its own name and offering its own warranty, support, and licensing of the product. The term is really a misnomer because OEMs are not the original manufacturers; they are the customizers.

Parts Manufacturer Approval (PMA): Both a design approval and a production approval. It is issued for the production of modification or replacement parts, which includes materials, parts, processes, and appliances.

Mahalanobis Space (MS): A database containing the means, standard deviations, and correlation structure of the variables in the reference group.

Neural Networks: A network of computational nodes which are interconnected by links. Instead of capturing rules like an expert system does, neural network relies on using input/output data patterns to train the network. Its links are modified to capture the knowledge, so that after it has been adequately trained, it can provide appropriate responses to new input data.

Data Mining: Analysis of data in a database using tools which look for trends or anomalies without knowledge of the meaning of the data. Data mining was invented by IBM, who holds some related patents.

Complete Chapter List

Search this Book: