Manufacturing service supply-demand optimization with dual diversities for industrial internet platforms

Hao, Ruiyang; Cheng, Ying; Zhang, Yongping; Tao, Fei

doi:10.1016/j.cie.2021.107237

Cited by 23 publications

(8 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared with other methods, our model achieves an AP 50 of 77.9% and an AR of 52.4%, with an average improvement of AP 50 of 2.5% and AR of 1.7%, and the results of the experiments reveal that our model is capable of detecting defects. Possible future work is also summarized as follows (1) The lack of datasets is an important issue in deep learning, so we need more robust contrastive learning models that can enable the model to learn richer features on limited datasets. (2) The proposed model is suitable for defect detecton of fabric images with non-patterned backgrounds and regular patterns, and detection methods for irregular patterned backgrounds can be further explored.…”

Section: Discussionmentioning

confidence: 99%

“…Fabric defect detection is one of the most significant directions in defect detection, since it prevents defective items from reaching the market and ensures the manufacturer's reputation. With the advancement of technologies such as artificial intelligence and industrial internet [1], a large amount of data include images can be collected and stored intact, making automated defect detection possible. In addition, due to the emergence of deep neural networks in computer vision, many defect detection models based on convolutional neural networks have emerged one after another Defect detection algorithms have been a popular study subject with the current advancement of deep learning.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Effective fabric defect detection using contrastive learning and layered fusion network

Xie

Weijie

2023

Fourteenth International Conference on Graphics and Image Processing (ICGIP 2022)

View full text Add to dashboard Cite

Defect detection is a very important topic in industrial inspection. Due to the rapid expansion of computer computing power, manual-based defect detection approaches is no longer satisfactory, and deep learning-based detection techniques are increasingly being applied to defect detection tasks. contrastive learning is better for defect detection tasks due to the advantages of its label-free training method. So the Efficient Fabric Defect Detector (EFDD), a high-efficiency defect detector based on contrastive learning approach and layered fusion network, is proposed in our paper. First, we propose the Layered Fusion network to encode defect types with different scale sizes and improve the feature extraction ability of the model. Second, a universal structure with an attention module is introduced, this module can be integrated into ResNet with little overhead. Third, we investigate the impact of parallel enhancement strategies on model training in the data imbalance, different combinations can affect the model to different degrees. Finally, we evaluate the model using three classical public datasets and the average improvement of EFDD over the three datasets is AP 2.1%, AR 1.5% compared to other contrastive learning methods. Compared to the supervised methods, our model accuracy is close to or even exceeds that of the supervised methods.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Effective fabric defect detection using contrastive learning and layered fusion network

Xie

Weijie

2023

Fourteenth International Conference on Graphics and Image Processing (ICGIP 2022)

View full text Add to dashboard Cite

show abstract

“…For smart manufacturing, the industrial Internet connects the physical world and cyberspace ( Srinidhi et al, 2019 ; He L. et al, 2020 ). Furthermore, as a result of user-producer collaboration, production efficiency can be improved, while product design can be more accommodating to users’ emotional needs ( Hao et al, 2021 ; Otto et al, 2021 ). Therefore, when purchasing products and services, the most important factor to consider is how to provide consumers with an emotional experience that exceeds their expectations through design innovation ( Bu et al, 2021 ; Wehrle et al, 2021 ).…”

Section: Literature Reviewmentioning

confidence: 99%

Investigate the Influencing Factors of Industrial Design Platform Demand: From the Perspective of Emotional Interaction

Zhang¹,

Yang²,

Tong³

et al. 2022

Front. Psychol.

View full text Add to dashboard Cite

With the deep integration of industries brought about by big data technology, users’ design needs are diversifying and individuating. Thanks to big data technology, users’ diverse design needs can be precisely met. Meanwhile, big data can be used to realize emotional interaction for personalized design needs of users, resulting in a better user experience. Using grounded theory to mine user demand text data, this paper investigates the influencing factors of emotional interaction and dynamic resource allocation in the digital design supply chain. The results show that government-driven factors have a direct impact on the demand for industrial design in user emotional interactions. Market factors are the most fundamental in the development of an industrial design service platform, and universities play an important role in this. Furthermore, a lack of market sensitivity stems from a lack of emotional interaction with users, resulting in a schism between industry, university, and research, which has become a major impediment to the development of China’s industrial design industry. This study not only lays the theoretical groundwork for understanding the mechanisms of user emotional interaction on IDSPs, but it also points the way forward for future industrial design service platform development.

show abstract

“…Industrial Internet is a result of integrating global industrial systems with advanced computing, analysis, sensing technology and Internet connectivity. It is proposed to realize the interconnection between physical world and cyberspace, realize intelligent manufacturing, centralize geographically distributed manufacturing resources, and realize resource sharing and cooperation among manufacturing enterprises in the form of manufacturing services [11]. The essence of industrial Internet is to connect and integrate equipment, production lines, factories, suppliers, products and customers closely through an open and global IIP.…”

Section: A°the Concept and Architecture Of Iipmentioning

confidence: 99%

Assessment of Industrial Internet Platform Application in Manufacturing Enterprises: System Construction and Industrial Practice

Zhou

Zhang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

To evaluate the effectiveness of the industrial Internet platform(IIP) applied by manufacturing enterprises, this study proposes a set of assessment systems for guiding and standardizing the application of IIP. Our assessment framework is established based on five dimensions: strategy and organization; basic conditions; platform application; business innovation; and efficiency and benefit. We collect IIP application data from more than 1400 manufacturing enterprises in China. The application performance of the IIP in manufacturing enterprises were comprehensively analyzed from different perspectives such as equipment on the cloud, industrial knowledge accumulation and reuse, and industrial APP innovative application. The research results show that the overall score of IIP application in China is 31.76 according to our assessment criterion. The breadth and depth of platform application need to be improved. Furthermore, this study provides guidance to a wide range of potential market participants, such as manufacturing enterprises, service providers and relevant policy makers, to assess the effectiveness of platform application.

show abstract

Manufacturing service supply-demand optimization with dual diversities for industrial internet platforms

Cited by 23 publications

References 32 publications

Effective fabric defect detection using contrastive learning and layered fusion network

Effective fabric defect detection using contrastive learning and layered fusion network

Investigate the Influencing Factors of Industrial Design Platform Demand: From the Perspective of Emotional Interaction

Assessment of Industrial Internet Platform Application in Manufacturing Enterprises: System Construction and Industrial Practice

Contact Info

Product

Resources

About