scholarly journals Data-Analytics-Based Factory Operation Strategies For Die-Casting Quality Enhancement

2021 ◽  
Author(s):  
Jun Kim ◽  
Ju Yeon Lee
Keyword(s):  
Data Analytics ◽  
Die Casting ◽  
Parameter Tuning ◽  
Prediction Algorithm ◽  
Quality Enhancement ◽  
Input And Output ◽  
Diagnosis Algorithm ◽  
Casting Parameter ◽  
Worker Experience ◽  
Factory Operation

Abstract This paper proposes data-analytics-based factory operation strategies for the quality enhancement of die-casting. We first define the four main problems of die casting that result in lower quality: [P1] gaps between the input and output casting parameter values, [P2] occurrence of preheat shots, [P3] lateness of defect distinction, and [P4] worker-experience-based casting parameter tuning. To address these four problems, we derived seven tasks that should be conducted during factory operation: [T1] implementation of exploratory data analysis (EDA) for investigating the trends and correlations between data, [T2] deduction of the optimal casting parameter output values for the production of fair-quality products, [T3] deduction of the upper and lower control limits for casting parameter input–output gap management, [T4] development of a preheat shot diagnosis algorithm, [T5] development of a defect prediction algorithm, [T6] development of a defect cause diagnosis algorithm, and [T7] development of a casting parameter tuning algorithm. The details of the proposed data-analytics-based factory operation strategies with regard to the casting parameter input and output data, data preprocessing, data analytics method used, and implementation are presented and discussed. Finally, a case study of a die-casting factory in South Korea that has adopted the proposed strategies is introduced.

scholarly journals Anonymizing k Facial Attributes via Adversarial Perturbations

2018 ◽  
Author(s):  
Saheb Chhabra ◽  
Richa Singh ◽  
Mayank Vatsa ◽  
Gaurav Gupta
Keyword(s):  
Data Analytics ◽  
Visual Quality ◽  
Machine Learning Algorithms ◽  
Prediction Algorithm ◽  
Classification Result ◽  
Identity Information ◽  
Photo Collections ◽  
Facial Attributes ◽  
Incorrect Classification

A face image not only provides details about the identity of a subject but also reveals several attributes such as gender, race, sexual orientation, and age. Advancements in machine learning algorithms and popularity of sharing images on the World Wide Web, including social media websites, have increased the scope of data analytics and information profiling from photo collections. This poses a serious privacy threat for individuals who do not want to be profiled. This research presents a novel algorithm for anonymizing selective attributes which an individual does not want to share without affecting the visual quality of images. Using the proposed algorithm, a user can select single or multiple attributes to be surpassed while preserving identity information and visual content. The proposed adversarial perturbation based algorithm embeds imperceptible noise in an image such that attribute prediction algorithm for the selected attribute yields incorrect classification result, thereby preserving the information according to user's choice. Experiments on three popular databases i.e. MUCT, LFWcrop, and CelebA show that the proposed algorithm not only anonymizes \textit{k}-attributes, but also preserves image quality and identity information.

Predictive Robust Control Based on Higher-Order Sliding Mode for Passive Heave Compensator With Hydraulic Transformer

2018 ◽  
Author(s):  
Huan Yu ◽  
Jianhua Wei ◽  
Jinhui Fang ◽  
Ge Sun ◽  
Hangjun Zhang
Keyword(s):  
Compensation Effect ◽  
Sliding Mode ◽  
Parameter Tuning ◽  
Higher Order ◽  
Prediction Algorithm ◽  
Control Element ◽  
Hydraulic Transformer ◽  
Energy Conserving ◽  
Heave Motion ◽  
First Time

Passive heave compensation (PHC) system is widely applied in offshore equipment because of its superiority in energy conserving and reliability. However, it has poor adaptability to changing sea conditions and the compensation accuracy is low. Hydraulic transformer (HT), working as a pressure-flow control element, can potentially solve the problems mentioned above. In this paper, an HT based PHC (HTPHC) system is proposed for the first time, and a compensation algorithm based on higher-order sliding mode (HOSM) together with a prediction algorithm for the heave motion of the vessel is derived to get good compensation effect using the new PHC system. The prediction algorithm is proved to be effective according to the measured data of sea trials, and reduces the difficulty of designing and parameter tuning process compared with the existing ones. The effectiveness of the proposed control algorithm is evaluated with simulation, moreover, the effectiveness can still be maintained under changing sea conditions which is also verified by simulation.

scholarly journals Establishment of an IoT-based smart factory and data analysis model for the quality management of SMEs die-casting companies in Korea

2019 ◽  
Vol 15 (10) ◽  
pp. 155014771987937
Author(s):  
Sangwoo Park ◽  
Kim Changgyun ◽  
Sekyoung Youm
Keyword(s):  
Data Analysis ◽  
Internet Of Things ◽  
Die Casting ◽  
Smart Factory ◽  
Analysis Model ◽  
Data Mining Technique ◽  
Casting Parameter ◽  
The Government ◽  
Casting Industry ◽  
Smart Factories

In this research, an Internet of things–based smart factory was established for a die-casting company that produces automobile parts, and the effect of casting parameters on quality was analyzed using data collected from the system. Most of the die-casting industry in Korea consists of small- and medium-sized enterprises with inferior finances and skeptical views about the establishment of a smart factory. In response, the Korean government is providing various types of support to spread the implementation of smart factories for small- and medium-sized enterprises. Although small- and medium-sized enterprises have become more active in establishing smart factories according to the government policies, the effect of smart factories requires real-time monitoring. A monitoring system has been built but the data collected are not being utilized properly. Therefore, it is necessary to establish a system suitable for the die-casting environment and data analysis purposes and to utilize it to enable the analysis of data. To this end, we established to smart factory that provides data based on the Internet of things. Among the data collected, casting parameter data were analyzed through a data mining technique to establish a relationship between casting parameters and the quality of production. It is expected that a method of systematic implementation will be provided to die-casting companies that want to build smart factories in the future and that a plan for managing casting parameter by-product will be established. In addition, algorithms that can solve the problem of multi-collinearity among the casting parameters and aid in the development of new products are needed to detect optimum casting parameters.

Sign in / Sign up

Export Citation Format

Share Document