• Title/Summary/Keyword: Manufacturing Training

Search Result 365, Processing Time 0.022 seconds

Self-Supervised Long-Short Term Memory Network for Solving Complex Job Shop Scheduling Problem

  • Shao, Xiaorui;Kim, Chang Soo
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.15 no.8
    • /
    • pp.2993-3010
    • /
    • 2021
  • The job shop scheduling problem (JSSP) plays a critical role in smart manufacturing, an effective JSSP scheduler could save time cost and increase productivity. Conventional methods are very time-consumption and cannot deal with complicated JSSP instances as it uses one optimal algorithm to solve JSSP. This paper proposes an effective scheduler based on deep learning technology named self-supervised long-short term memory (SS-LSTM) to handle complex JSSP accurately. First, using the optimal method to generate sufficient training samples in small-scale JSSP. SS-LSTM is then applied to extract rich feature representations from generated training samples and decide the next action. In the proposed SS-LSTM, two channels are employed to reflect the full production statues. Specifically, the detailed-level channel records 18 detailed product information while the system-level channel reflects the type of whole system states identified by the k-means algorithm. Moreover, adopting a self-supervised mechanism with LSTM autoencoder to keep high feature extraction capacity simultaneously ensuring the reliable feature representative ability. The authors implemented, trained, and compared the proposed method with the other leading learning-based methods on some complicated JSSP instances. The experimental results have confirmed the effectiveness and priority of the proposed method for solving complex JSSP instances in terms of make-span.

An Effect of CEO Characteristics and Marketing Activities on Management Performance of Fashion Corporate (패션기업의 최고경영자 특성과 마케팅 활동이 경영성과에 미치는 효과)

  • Ryou, Eun-Jeong;Ahn, Mi-Gang
    • Asia-Pacific Journal of Business
    • /
    • v.11 no.4
    • /
    • pp.103-119
    • /
    • 2020
  • Purpose - This study aimed to clarify the effects of CEO characteristics and marketing activities on management performance of fashion corporate by using financial statement. Design/methodology/approach - This study collected a sample of total 170 companies that can obtain the corresponding data among fashion manufacturing companies listed on KOSPI. The data of the financial statements reported from 2011 to 2018 were analyzed. Correlation analysis and multiple regression analysis were conducted. Findings - First, the more the number of CEO and the younger the CEO, the more employee welfare and training expenditures of internal marketing. The age of the CEO had a negative effect on all external marketing activities. The CEO number had a negative effect on sales promotion and advertising expenditures, but a positive effect on entertainment expenditure of external marketing. Second, as a effect of marketing activities on management performance, the welfare and training expenditures of internal marketing and entertainment expenditure of external marketing had a positive effect but sales promotion expenditure of external marketing had a negative effect on management performance. Research implications or Originality - Marketing activities that consider the differentiated factors of fashion corporate are necessary. Also, the objective accounting information can provide practical information for fashion industry.

A fast defect detection method for PCBA based on YOLOv7

  • Shugang Liu;Jialong Chen;Qiangguo Yu;Jie Zhan;Linan Duan
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.18 no.8
    • /
    • pp.2199-2213
    • /
    • 2024
  • To enhance the quality of defect detection for Printed Circuit Board Assembly (PCBA) during electronic product manufacturing, this study primarily focuses on optimizing the YOLOv7-based method for PCBA defect detection. In this method, the Mish, a smoother function, replaces the Leaky ReLU activation function of YOLOv7, effectively expanding the network's information processing capabilities. Concurrently, a Squeeze-and-Excitation attention mechanism (SEAM) has been integrated into the head of the model, significantly augmenting the precision of small target defect detection. Additionally, considering angular loss, compared to the CIoU loss function in YOLOv7, the SIoU loss function in the paper enhances robustness and training speed and optimizes inference accuracy. In terms of data preprocessing, this study has devised a brightness adjustment data enhancement technique based on split-filtering to enrich the dataset while minimizing the impact of noise and lighting on images. The experimental results under identical training conditions demonstrate that our model exhibits a 9.9% increase in mAP value and an FPS increase to 164 compared to the YOLOv7. These indicate that the method proposed has a superior performance in PCBA defect detection and has a specific application value.

A Study on Methods to Train Experts in Robot and Artificial Intelligence-Based Data Signal Processing in Response to the Increased Use of Robots (로봇의 활용증가에 따른 로봇 및 인공지능 기반 데이터 신호처리 전문가 양성 방안에 관한 연구)

  • Chung-Ho Ju;Dae-Yeon Kim;Kyoung-Ho Kim;Tae-Woong Gwon;Dong-Seop Sohn
    • Journal of the Institute of Convergence Signal Processing
    • /
    • v.25 no.2
    • /
    • pp.58-66
    • /
    • 2024
  • Robotics is a convergence technology with significant ripple effects across various industries, including manufacturing and services. Its importance has been increasingly underscored by advancements in artificial intelligence. As a crucial industry for addressing the challenges posed by a declining and aging production workforce and for enhancing manufacturing competitiveness, the training of robotics experts is now critically important. This paper examines the case of the Robot Job Innovation Center in Gumi City and proposes a strategy for training robotics experts and specialists in robot/AI-based signal processing. A core curriculum was carefully selected and implemented in actual educational settings, with key components necessary for developing a comprehensive educational framework detailed. The convergence of AI-based data signal processing and robotics represents a significant technological advancement poised to impact a wide array of industries. By proposing the comprehensive educational framework outlined in this paper, it is anticipated that related organizations will be able to effectively utilize these foundational elements to train experts in the field.

Effect of IT Manufacturing Firms' Technological Innovation Factors -From Government Support Level- (IT제조업 정부 지원 수준이 기술혁신에 미치는 영향)

  • Park, Tae-Hoon;Park, Kyung-Hye
    • Journal of Digital Convergence
    • /
    • v.10 no.6
    • /
    • pp.17-22
    • /
    • 2012
  • The technological innovation of IT industry is the competitive tool for them to survive in the environment of an intensive competition. This technological innovation is critical in the survival of firms, but various factors should be considered to embody technological innovation success. This paper aims to identify the determinant factors of the outcome which influence the technological innovation based on the IT industry, and set up a model for measuring technological innovation success. A hypothesis was established for the impact relation between technological innovation success and government support level, which was verified through the logistic regression analysis. In conclusion, in terms of government support, IT manufacturing companies to the success of product innovation, technology development(R&D) and commercialization of direct support is needed for the financial support. And, the success of process innovation is accomplished through manpower training of technical personnel.

A study on recognition of noise and hearing threshold among workers in a cosmetics manufacturing factory (일개 화장품 제조업체 근로자의 소음 인식도와 청력역치 조사에 관한 연구)

  • Eoh, WonSouk;Ham, WanShik;Kim, Hyunwook
    • Journal of Korean Society of Occupational and Environmental Hygiene
    • /
    • v.21 no.3
    • /
    • pp.162-167
    • /
    • 2011
  • To identify the relationship between types of job classification (typical and atypical) and the levels of recognition of noise and the hearing threshold shift, a total of 457 workers in a cosmetic company were studied utilizing a questionnaire and the audiometric hearing test. The results were analyzed by factor analysis, t-test, and general linear model, as appropriate. The results showed that atypical workers had higher level of noise recognition but had lower levels of hearing ability, noise exposure, and the knowledge on hearing loss prevention, compared with those of typical workers. The high noise level group of typical workers showed higher threshold shift levels than that of atypical workers. Significant differences were found at 4 kHz for both ears and in right ear only for hearing threshold shift after adjusting age.

Study on Life Evaluation of Die Casting Mold and Selection of Mold Material (다이캐스팅 금형의 내구 수명평가와 금형강 소재 선정에 대한 연구)

  • Kim, Jinho;Hong, Seokmoo;Lee, Jong-Chan
    • Journal of the Korean Society of Manufacturing Process Engineers
    • /
    • v.12 no.3
    • /
    • pp.7-12
    • /
    • 2013
  • In Die casting process, the problem of die degradation is often issued. In oder to increase of die life the material degradation of die steel was investigated using test core pins. Three test core pins were positioned in front of the gate entry and observed washout and soldering resistance during Mg die casting process. The test parameters are set as different commercial die materials, coatings condition and hardness of die surface. Usign 220t magnesium die casting machine was employed to cast AZ91 magnesium alloys. After 150 shots, macroscopic observation of die surface was carried out. Additional 50 cycles later, test pins were chemically cleaned with 5% HCl aqueous solution to find out the existence of washout and soldering layers. Microstructural characterization of die surface and the die roughness measurement were performed together. Computational simulation using AnyCasting program was also beneficial to correlate the extent of die damage with the position of test pin inside die cavity. As results, the optimal combination of die steel with productive coating as well as its hardness was drawn out. it will be helpful to decide the material and condition considering increasing of tool life.

A novel approach to predict surface roughness in machining operations using fuzzy set theory

  • Tseng, Tzu-Liang (Bill);Konada, Udayvarun;Kwon, Yongjin (James)
    • Journal of Computational Design and Engineering
    • /
    • v.3 no.1
    • /
    • pp.1-13
    • /
    • 2016
  • The increase of consumer needs for quality metal cutting related products with more precise tolerances and better product surface roughness has driven the metal cutting industry to continuously improve quality control of metal cutting processes. In this paper, two different approaches are discussed. First, design of experiments (DOE) is used to determine the significant factors and then fuzzy logic approach is presented for the prediction of surface roughness. The data used for the training and checking the fuzzy logic performance is derived from the experiments conducted on a CNC milling machine. In order to obtain better surface roughness, the proper sets of cutting parameters are determined before the process takes place. The factors considered for DOE in the experiment were the depth of cut, feed rate per tooth, cutting speed, tool nose radius, the use of cutting fluid and the three components of the cutting force. Finally the significant factors were used as input factors for fuzzy logic mechanism and surface roughness is predicted with empirical formula developed. Test results show good agreement between the actual process output and the predicted surface roughness.

Development of Hardware-linked Simulation Platform for Automation Mechanism Training (자동화 메커니즘 교육을 위한 하드웨어 연동형 시뮬레이션 플랫폼 개발)

  • Kim, Hyun-Hee;Park, Sung-Su;Lee, Kyung-Chang;Hwang, Yeong-Yeun
    • Journal of the Korean Society of Manufacturing Process Engineers
    • /
    • v.14 no.4
    • /
    • pp.34-42
    • /
    • 2015
  • As the industry environment is changing to automated systems, engineering education at university has changed with industrial development. Industry technology will be developed, and the industry environment will become more complicated. Therefore, the knowledge that undergraduates have to acquire in university will be extensive. Industries need a person with expertise to react quickly to rapidly changing technology. Therefore, universities need to endeavor to cultivate manpower in technical fields. This is difficult because the contents of engineering education must react quickly to rapidly changing industry technology. This paper proposes a hardware-linked simulation platform for engineering education on the well-used systems in industrial sites.

Precise Control of Inchworm Displacement Using the LQG/LTR Technique (LQG/LTR 기법을 이용한 이송자벌레 변위의 정밀 제어)

  • Jeon, Yoon-Han;Hwang, Yun-Sik;Park, Heung-Seok;Kim, In-Soo
    • Journal of the Korean Society of Manufacturing Technology Engineers
    • /
    • v.24 no.4
    • /
    • pp.414-420
    • /
    • 2015
  • In this study, the linear quadratic Guassian loop transfer recovery (LQG/LTR) control technique was combined with an integrator and applied to an inchworm having piezoelectric actuators for precise motion tracking. The piezoelectric actuator showed nonlinear response characteristics, including hysteresis, due to its ferroelectric characteristics and the residual displacement phenomenon. This paper proposes a feedback control scheme using the LQG/LTR controller with an integrator to improve the ability to track the response to complex input signals and to suppress the phenomenon of hysteresis and residual vibration. Experimental results show that the developed feedback control system for an inchworm can track the various motion contours quickly without residual vibration or overshoot.