The main roles of fault detection and diagnosis (FDD) for industrial processes are to make an effective indicator which can identify faulty status of a process and then to take a proper action against a future failure or unfavorable accidents. In order to enhance many process performances (e.g., quality and throughput), FDD has attracted great attention from various industrial sectors. Many traditional FDD techniques have been developed for checking the existence of a trend or pattern in the process or whether a certain process variable behaves normally or not. However, they might fail to produce several hidden characteristics of the process or fail to discover the faults in processes due to underlying process dynamics. In this paper, we present current research and developments of FDD approaches for process monitoring as well as a broad literature review of many useful FDD approaches.

The objective of this paper is to develop a method for constructing confidence intervals for misclassification rates in a gauge repeatability and reproducibility (R&R) study. Confidence intervals are computed using generalized inference methods. Simulation results suggest confidence coefficients are generally greater than the stated value when a sufficient number of parts and operators are selected for the R&R study.

Task composition in cloud manufacturing involves the selection of appropriate services from the cloud manufacturing platform and combining them to process the task with the purpose of achieving its expected performance. Calculation methods for achieving the performance expected by customers when the task has two or more composition patterns (e.g. sequential and switching pattern) are necessary because most tasks have multiple composition patterns in cloud manufacturing. Previous studies, however, have focused only on a single composition pattern. In this paper, we regard a task as a directed acyclic graph, and propose graph-based algorithms to obtain cost, execution time, quality and reliability of a task having multiple composition patterns. In addition, we model the task composition problem by introducing cost and execution time as performance attributes, and quality and reliability as basic attributes in the Kano model. Finally, an experiment to compare the performances of three metaheuristic algorithms (namely, variable neighbourhood search, genetic, and simulated annealing) is conducted to solve the problem. The experimental result shows that the variable neighbourhood search algorithm yields better and more stable solutions than the genetic algorithm and simulated annealing algorithms.

This paper proposes an extended data envelopment analysis (DEA) model for deriving eco-efficiency. In order to derive eco-efficiency, the proposed model utilizes the concepts of operational efficiency and environmental efficiency. Since DEA can separately measure operational efficiency and environmental efficiency, the treatment for constructing the unified indicator is required to ultimately evaluate eco-efficiency through balancing operational and environmental concerns. To achieve this goal, we define the environmental stringency as the business condition reflecting the degree of enforcing environmental regulations across the firms or particular industries in different countries. The proposed model provides flexibility, as required by the pollution-intensity of industry, in that it allows the decision maker to evaluate DMU’s (decision-making unit) eco-efficiency appropriately depending on the business environment. We present a case of agricultural production systems to help readers understand what eco-efficiency becomes when we vary the stringency conditions. Through the illustrative example, this paper presents the potential application by which different environmental stringencies can successively be incorporated in DEA.