To cope with large fluctuations in the demand of a commodity, it is necessary for the manufacturing system to have rapid reactive ability. This requirement may be secured by performance measurement. Although manufacturing companies have used information systems to manage performance, there has been the difficulty of capturing real-time data to depict real situations. The recent development and application of the Internet of Things (IoT) has enabled the resolution of this problem. In demonstration of the functionality of IoT, we developed an IoT-based performance model consistent with the ISA-95 and ISO-22400 standards, which define manufacturing processes and performance indicator formulas. The development comprised three steps: (1) Selection of the Key Performance Indicators of the Overall Equipment Effectiveness (OEE), and the development of an IoT-based production performance model, (2) Implementation of the IoT-based architecture and performance measurement process using Business Process Modelling and (3) Validation of the proposed model through virtual factory simulation. We investigated the effect of the IoT-workability on the OEE, based on the final results of the simulation, both for the planned and actual productions. The simulation results showed that the proposed model represented the timestamp data acquired by IoT and captured the entire production process, thus enabling the determination of real-time performance indicators.

The so-called smart factory is a novel paradigm that is rapidly gaining ground in scenarios for factories of the future. Many manufacturing companies try to raise the level of smartness by considering a number of aspects related to the smart factory. However, there is a lack of field-oriented systematic research to help them fit the interest of industry for promoting interest and diffusion of smart factory. Moreover, it is still difficult to assess whether the vision of the future factory that incorporates information and communication technologies is implemented. Therefore, in this study, we propose a smartness assessment framework for smart factories which is based on the concept of operation management so as to be easy to make manufacturing companies to understand and apply. The framework is composed of evaluation criteria and sets the weightings of the criteria using analytic network processes. From a case study based on 20 small and medium-sized manufacturing enterprises, the effectiveness of the proposed framework has been verified.

Quality management is important for maximizing yield in continuous-flow manufacturing. However, it is more difficult to manage quality in continuous-flow manufacturing than in discrete manufacturing because partial defects can significantly affect the quality of an entire lot of final product. In this paper, a comprehensive framework that consists of three steps is proposed to predict defects and improve yield by using semi-supervised learning, time-series analysis, and classification model. In Step 1, semi-supervised learning using both labeled and unlabeled data is applied to generate quality values. In addition, feature values are predicted in time-series analysis in Step 2. Finally, in Step 3, we predict quality values based on the data obtained in Step 1 and Step 2 and calculate yield values with the use of the predicted value. Compared to a conventional production plan, the suggested plan increases yield by up to 8.7%. The production plan proposed in this study is expected to contribute to not only the continuous manufacturing process but the discrete manufacturing process. In addition, it can be used in early diagnosis of equipment failure.

The recent introduction of smart manufacturing, also called the ‘smart factory’, has made it possible to collect a significant number of multi-variate data from Internet of Things devices or sensors. Quality control using these data in the manufacturing process can play a major role in preventing unexpected time and economic losses. However, the extraction of information about the manufacturing process is limited when there are missing values in the data and a data imbalance set. In this study, we improve the quality classification performance by solving the problem of missing values and data imbalances that can occur in the manufacturing process. This study proceeds with data cleansing, data substitution, data scaling, a data balancing model methodology, and evaluation. Five data balancing methods and a generative adversarial network (GAN) were used to proceed with data imbalance processing. The proposed schemes achieved an F1 score that was 0.5 higher than the F1 score of previous studies that used the same data. The data preprocessing combination proposed in this study is intended to be used to solve the problem of missing values and imbalances that occur in the manufacturing process.