Prediction of quality in production using optimized Hyper-parameter tuning based deep learning model

被引：2

作者：

Rajendra Kannammal G. ^{[1
]}

Sivamalar P. ^{[1
]}

Santhi P. ^{[2
]}

Vetriselvi T. ^{[1
]}

Kalpana V. ^{[1
]}

Nithya T.M. ^{[1
]}

机构：

[1] Department of Computer Science and Engineering, K Ramakrishnan College of Technology, Tamilnadu, Trichy

[2] Department of Computer Science and Engineering, M Kumarasamy College of Engineering, Tamilnadu, Karur

来源：

Materials Today: Proceedings | 2022年 / 69卷

关键词：

Convolutional Neural Network; Hyper-tuning; Manufacturing Process; Predictive Model; Production Line; Smart Factories; Supply Chain;

D O I：

10.1016/j.matpr.2022.07.133

中图分类号：

学科分类号：

摘要：

Large volumes of manufacturing data may now be collected because to the growing popularity of smart Industry 4.0. Product quality may be predicted from manufacturing data acquired during production using machine learning approaches such as classification. A supply chain can benefit from eliminating uncertainty by precise forecasting at any point in the process. As a result, knowing the quality of a product batch early on can save money on recalls, packaging, and shipping. Classification methods have been extensively studied for forecasting the quality of certain manufacturing processes, but the overall obedience of production batches has not been carefully studied. Classification methods based on deep learning (Convolutional Neural Network) and optimal hyper-parameter tuning are the focus of this article, which aims to evaluate the suggested appliance production process. Existing approaches for classifying unit batches are compared to the proposed classification model in terms of several quality parameters for compliance. As a result, a model for predicting compliance quality may be built using the new method. Features and dataset knowledge are also critical in training classification models, according to this study. © 2022

引用

页码：703 / 709

页数：6

共 33 条

[1] Ren L., Zhang L., Wang L., Tao F., Chai X., Cloud manufacturing: Key characteristics and applications, Int. J. Comput. Integrat. Manuf., 30, 6, pp. 501-515, (2017)
[2] Zhu C., Rodrigues J.J., Leung V.C., Shu L., Yang L.T., Trust-based communication for the industrial Internet of Things, IEEE Commun. Mag., 56, 2, pp. 16-22, (2018)
[3] Wang X., Yang L.T., Wang Y., Ren L., Deen M.J., ADTT: A highly-efficient distributed tensor-train decomposition method for IIOT big data, IEEE Trans. Ind. Informat., (2020)
[4] Ren L., Laili Y., Li X., Wang X., Coding-based large-scale task assignment for industrial edge intelligence, IEEE Trans. Netw. Sci. Eng., (2020)
[5] Yin S., Ding S., Xie X., Luo H., A review on basic data-driven approaches for industrial process monitoring, IEEE Trans. Ind. Electron., 61, 11, pp. 6418-6428, (2014)
[6] Ren L., Cheng X., Wang X., Cui J., Zhang L., Multi-scale dense gate recurrent unit networks for bearing remaining useful life prediction, Future Gener. Comput. Syst., 94, pp. 601-609, (2019)
[7] Souza F., Araujo R., Mendes J., Review of soft sensors methods for regression applications, Chemometrics Intell. Lab. Syst., 152, 12, pp. 69-79, (2015)
[8] Luo H., Yin S., Liu T., Khan A.Q., A data-driven realization of the control-performance-oriented process monitoring system, IEEE Trans. Ind. Electron., 67, 1, pp. 521-530, (2020)
[9] Zhu H., Liu G., Zhou M., Xie Y., Abusorrah A., Kang Q., Optimizing Weighted Extreme Learning Machines for Imbalanced Classification and Application to Credit Card Fraud Detection, Neurocomputing, (2020)
[10] Jia F., Lei Y., Lu N., Xing S., Deep normalized convolutional neural network for imbalanced fault classification of machinery and its understanding via visualization, Mech. Syst. Signal. Process., 110, pp. 349-367, (2018)

← 1 2 3 4 →