Anomaly detection of power consumption in yarn spinning using transfer learning

Xu, Chuqiao; Wang, Junliang; Zhang, Jie; Li, Xiaoou

doi:10.1016/j.cie.2020.107015

Cited by 25 publications

(13 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A CDAN model was suggested in Xu et al's (2021) [5] research to optimize the effectiveness of transfer learning for spinning power usage anomaly detection. Between the element that links the source and target networks, a clusterbased adaption layer was introduced.…”

Section: Literature Reviewmentioning

confidence: 99%

Development and Application of Information Resources for Education and Teaching of Yarn History Based on 5G Network Technology

Zhang

Yang

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Yarn education is a crucial step in producing high-quality textile end products. By offering quick insights into yarn quality, online yarn testing can reduce latency in critical process control, resulting in the manufacture of higher-quality yarns. This paper proposes the development and application of information resources for the education and teaching of yarn history based on fifth-generation (5G) network technologies. Firstly, the yarn database is preprocessed using greyscale transformation and image filtering methods. Secondly, yarn segmentation is implemented using a Multiresolution Markov Random Field (MRMRF) model. Fourier transform and two-scale attention models are used to extract statistical and relative characteristics, respectively. For classifying the yarn photos, we propose using Improved Support Vector Machine (ISVM) classification. The 5G network has been set up, and data is transferred using the Transmission Control Protocol. To enhance the performance, we propose an Improved Particle Swarm Optimization (IPSO) algorithm. The performance of the suggested methodology is analyzed and compared with existing methodologies using the MATLAB simulation tool. The suggested algorithm's classification performance suggests that the 5G framework could provide an accurate, rapid, reliable, and cost-effective solution to industrial automation.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Development and Application of Information Resources for Education and Teaching of Yarn History Based on 5G Network Technology

Zhang

Yang

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…Another remarkable approach is the one presented by Jindal et al (2020) In other reported cases, the authors work with manually labelled training data (i.e., the so-called supervised anomaly detection), although this is not the most common situation in a real environment. An exemplifying recent article of this kind is Xu et al (2021), where data belong to a newlybuilt spinning workshop for which there is insufficient historical data to detect power consumption anomalies. The authors use transfer learning to compensate for the lack of data, and hence for the potential unrepresentativeness of the knowledge captured by the developed data-based models.…”

Section: Anomaly Detection In Manufacturing Cppsmentioning

confidence: 99%

“…However, over time this trend is reversed. In B. Zhao, Qin, Gao, and Xu et al (2021) the authors design an energy saving diagnosis process in a petrochemical plant based on the dual Curvelet support vector machine (SVM). To improve the accuracy and optimize the hyper parameters of the SVM, they construct a hybrid glowworm swarm optimisation algorithm based on simulated annealing to optimize the parameters of the twin Curvelet SVM.…”

Section: Related Work and Contributionmentioning

confidence: 99%

A novel approach for the detection of anomalous energy consumption patterns in industrial cyber‐physical systems

et al. 2022

View full text Add to dashboard Cite

Most scenarios emerging from the Industry 4.0 paradigm rely on the concept of cyber‐physical production systems (CPPS), which allow them to synergistically connect physical to digital setups so as to integrate them over all stages of product development. Unfortunately, endowing CPPS with AI‐based functionalities poses its own challenges: although advances in the performance of AI models keep blossoming in the community, their penetration in real‐world industrial solutions has not so far developed at the same pace. Currently, 90% of AI‐based models never reach production due to a manifold of assorted reasons not only related to complexity and performance: decisions issued by AI‐based systems must be explained, understood and trusted by their end users. This study elaborates on a novel tool designed to characterize, in a non‐supervised, human‐understandable fashion, the nominal performance of a factory in terms of production and energy consumption. The traceability and analysis of energy consumption data traces and the monitoring of the factory's production permit to detect anomalies and inefficiencies in the working regime of the overall factory. By virtue of the transparency of the detection process, the proposed approach elicits understandable information about the root cause from the perspective of the production line, process and/or machine that generates the identified inefficiency. This methodology allows for the identification of the machines and/or processes that cause energy inefficiencies in the manufacturing system, and enables significant energy consumption savings by acting on these elements. We assess the performance of our designed method over a real‐world case study from the automotive sector, comparing it to an extensive benchmark comprising state‐of‐the‐art unsupervised and semi‐supervised anomaly detection algorithms, from classical algorithms to modern generative neural counterparts. The superior quantitative results attained by our proposal complements its better interpretability with respect to the rest of algorithms in the comparison, which emphasizes the utmost relevance of considering the available domain knowledge and the target audience when design AI‐based industrial solutions of practical value. Finally, the work described in this paper has been successfully deployed on a large scale in several industrial factories with significant international projection.

show abstract

“…The transfer learning, as an emerging learning paradigm, has become a hot research topic because it can transfer the knowledge learned from similar data to improve the model precision of a new target [28]. Such transfer can transmit the knowledge learned from sufficient data to a new environment in case of data deficiency [29], which is conducive to constructing the high-precision model under different environments. To achieve the prediction of wafer CT at different WIP levels, a transfer learning network based on hierarchical optimization was proposed in this paper.…”

Section: Related Workmentioning

confidence: 99%

Hierarchical Transfer Learning for Cycle Time Forecasting for Semiconductor Wafer Lot under Different Work in Process Levels

Wang

Gao

et al. 2021

Mathematics

Self Cite

View full text Add to dashboard Cite

The accurate cycle time (CT) prediction of the wafer fabrication remains a tough task, as the system level of work in process (WIP) is fluctuant. Aiming to construct one unified CT forecasting model under dynamic WIP levels, this paper proposes a transfer learning method for finetuning the predicted neural network hierarchically. First, a two-dimensional (2D) convolutional neural network was constructed to predict the CT under a primary WIP level with the input of spatial-temporal characteristics by reorganizing the input parameters. Then, to predict the CT under another WIP level, a hierarchical optimization transfer learning strategy was designed to finetune the prediction model so as to improve the accuracy of the CT forecasting. The experimental results demonstrated that the hierarchically transfer learning approach outperforms the compared methods in the CT forecasting with the fluctuation of WIP levels.

show abstract

Anomaly detection of power consumption in yarn spinning using transfer learning

Cited by 25 publications

References 24 publications

Development and Application of Information Resources for Education and Teaching of Yarn History Based on 5G Network Technology

Development and Application of Information Resources for Education and Teaching of Yarn History Based on 5G Network Technology

A novel approach for the detection of anomalous energy consumption patterns in industrial cyber‐physical systems

Hierarchical Transfer Learning for Cycle Time Forecasting for Semiconductor Wafer Lot under Different Work in Process Levels

Contact Info

Product

Resources

About