Quality Control Using Agent Based Framework

Quality Control Using Agent Based Framework

Tzu-Liang (Bill) Tseng (University of Texas at El Paso, USA), Chun-Che Huang* (National Chi Nan University, Taiwan), Yu-Neng Fan (National Taiwan University, Taiwan) and Chia-Hsun Lee (National Chi Nan University, Taiwan)
Copyright: © 2015 |Pages: 13
DOI: 10.4018/978-1-4666-5888-2.ch515
OnDemand PDF Download:
List Price: $37.50

Chapter Preview



To date, quality has given attention to a manufacturing strategic plan to increase efficiency of the company through improving resource utilization and satisfying the needs of customers in terms of price and reliability, with result in achieving manufacturing success in a highly competitive manufacturing market (Bothe 1997; Relyea 2011).

In recent literature, it indicates that quality is the only strategic component that influences manufacturing performance (Amoako-Gyampah and Acquaah 2008). To ensure the quality in a machining process, it is important to response the dynamic environment quickly. Some machining processes, operated by human resource, contain high uncertainty and may be difficult in automation implementation. Therefore, it is crucial to discover the significant features for the production process to facilitate quality analysis and control.

According to literatures, decision rules are appreciated to support for the QC procedures while diverse variations occur in the machining process (Xu et al. 2011). Moreover, the QC issues are normally associated with different data formats/structures and observed in the manufacturing process. In other words, the QC related operations and entities are therefore distributed in a heterogeneous environment. Consequently, an effective prediction model utilized significant features for part quality is demanded in contemporary manufacturing.

The literatures of agent technology applied in QC area are numerous. For example, Ouyang et al. (2009), Sepúlveda et al. (2007), Chakravorty (2009) that describe QC models composed of software components that represent the types of agents. However, few previous literatures focus on “efficient quality improvement” and “data integration.” The aforementioned studies did not provide a whole picture of agent-based QC crossing all functions and propose a global architecture for agents, specifically focusing on efficient quality improvement. Furthermore, they do not consider the heterogeneity problems while the agent technology is applied. The objective of this book chapter is to develop an agent-based system to enhance the efficient quality improvement and solve the heterogeneity related problems. The agents in the system autonomously plan and pursue their actions and sub-goals, to cooperate, coordinate, and negotiate with others, and to respond flexibly and intelligently to dynamic and unpredictable situations in a virtual way.

In this chapter, the agent based framework is proposed to augment effective part quality control. Under the agent technology based framework, three main stages are identified and constructed for the QC prediction system (Figure 1).

Figure 1.

The framework of the proposed hybrid data mining approach

Key Terms in this Chapter

Knowledge Management: Manage knowledge in an efficient way through knowledge externalization, sharing, innovation, and socialization.

Agent-Based: A class of computational models for simulating the actions and interactions of autonomous agents (both individual or collective entities such as organizations or groups) with a view to assessing their effects on the system as a whole.

Quality Control: A procedure or set of procedures intended to ensure that a manufactured product or performed service adheres to a defined set of quality criteria or meets the requirements of the client or customer.

Data Mining: An interdisciplinary subfield of computer science, is the computational process of discovering patterns in large data sets involving methods at the intersection of artificial intelligence, machine learning, statistics, and database systems. The overall goal of the data mining process is to extract information from a data set and transform it into an understandable structure for further use.

Rough Set Theory: A Rough Set (RS) based rule induction approach to select significant features and derive decision rules is used at this stage. Basically, features characterize each object in the database, and the approach discovers the dependencies between features and objects.

Rule Induction: Rule induction is an area of machine learning in which formal rules are extracted from a set of observations. The rules extracted may represent a full scientific model of the data, or merely represent local patterns in the data.

Fuzzy Set Theory: A Fuzzy Set (FS) approach is used due to the following reasons: First, the FS method enables fast and easy synthesis and modification of the control rule base; Second, the FS method can be integrated into the quality controller to compensate for process variations. The FS application includes Type 1 and Type 2 FS. Different types of FS express different strengths to handle heterogeneous factors as well as variables in the process.

Complete Chapter List

Search this Book: