Using data mining methods for manufacturing process control

Važan, Pavel; Janikova, Dominika; Tanuška, Pavol; Kebísek, Michal; Červeňanská, Zuzana

doi:10.1016/j.ifacol.2017.08.986

Cited by 31 publications

(19 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Research showed that traditional methods such as SVN, KNN, random forest, boosting tree and others give worse results in data prediction than neural networks. These are the reasons why neural networks will be an everyday part of our lives in the future [10].…”

Section: Resultsmentioning

confidence: 99%

Convolutional Networks Used to Classify Video and Audio Data

Nikmon

Budjač

Kuchár

et al. 2019

Research Papers Faculty of Materials Science and Technology Slovak University of Technology

View full text Add to dashboard Cite

Deep learning is a kind of machine learning, and machine learning is a kind of artificial intelligence. Machine learning depicts groups of various technologies, and deep learning is one of them. The use of deep learning is an integral part of the current data classification practice in today’s world. This paper introduces the possibilities of classification using convolutional networks. Experiments focused on audio and video data show different approaches to data classification. Most experiments use the well-known pre-trained AlexNet network with various pre-processing types of input data. However, there are also comparisons of other neural network architectures, and we also show the results of training on small and larger datasets. The paper comprises description of eight different kinds of experiments. Several training sessions were conducted in each experiment with different aspects that were monitored. The focus was put on the effect of batch size on the accuracy of deep learning, including many other parameters that affect deep learning [1].

show abstract

Section: Resultsmentioning

confidence: 99%

Convolutional Networks Used to Classify Video and Audio Data

Nikmon

Budjač

Kuchár

et al. 2019

Research Papers Faculty of Materials Science and Technology Slovak University of Technology

View full text Add to dashboard Cite

show abstract

“…As the data is collected from various streams of product development and manufacturing, it needs to be stored in databases, accessed and processed to transform them into valuable information for virtual space. As data mining is one way of finding possible useful patterns from the present databases [43], therefore it is potentially a key factor 09/16/2018 for improving the status of virtual spaces in DT. First, the large variety of data during manufacturing results in bigger and complex databases which makes data mining difficult [43].…”

Section: Data: Variety Mining Big Data and Ownershipmentioning

confidence: 99%

“…As data mining is one way of finding possible useful patterns from the present databases [43], therefore it is potentially a key factor 09/16/2018 for improving the status of virtual spaces in DT. First, the large variety of data during manufacturing results in bigger and complex databases which makes data mining difficult [43]. Second, data mining is not very often utilised in manufacturing.…”

Section: Data: Variety Mining Big Data and Ownershipmentioning

confidence: 99%

See 1 more Smart Citation

Challenges of Digital Twin in High Value Manufacturing

Singh¹,

Shehab²,

Higgins³

et al. 2018

SAE Technical Paper Series

View full text Add to dashboard Cite

Digital Twin (DT) is a dynamic digital representation of a real-world asset, process or system. Industry 4.0 has recognised DT as the game changer for manufacturing industries in their digital transformation journey. DT will play a significant role in improving consistency, seamless process development and the possibility of reuse in subsequent stages across the complete lifecycle of the product. As the concept of DT is novel, there are several challenges that exist related to its phase of development and implementation, especially in high value manufacturing sector. The paper presents a thematic analysis of current academic literature and industrial knowledge. Based on this, eleven key challenges of DT were identified and further discussed. This work is intended to provide an understanding of the current state of knowledge around DT and formulate the future research directions.

show abstract

“…On the other hand, with the rapid development of data mining technology and the gradual popularization of information systems such as PDM, CAPP, ERP and MES in recent years, data mining on the assembly process data becomes a feasible solution to achieve assembly performance prediction [3]. Kretschmer introduces the implementation for knowledge-based design for assembly in agile manufacturing by using data mining methods in the field of series production with high variance [4].…”

Section: Introductionmentioning

confidence: 99%

Assembly Data Mining Platform Based on Python

Zhang

Li²,

Zhang³

2018

Proceedings of Information Science and Cloud Computing — PoS(ISCC 2017)

View full text Add to dashboard Cite

There are rich data in the manufacturing information systems, but they are not utilized in an effective way. The establishement of assembly data mining platform is to take advantage of the data to improve assembly process. Assembly factors and assembly data mining templates are the core tables in the assembly database. The methods of dealing with data vacancies and noise points are pre-set in the data mining templates. Python is used as the data mining engine by script customization and algorithm library encapsulation. Firstly, Python algorithm scripts are customized when programing the platform. Then the platform generates the execution script according to the user operation. Finally, the main program of Python executes the generated script and returns the results. Also, Mlpy is applied to make corresponding algorithm processing module. The functions are pre-compiled so that the assembly technicians without knowledge of data mining can utilize the assembly data to predict the assembly performance and analyse the assembly process. ISCC2017

show abstract

Using data mining methods for manufacturing process control

Cited by 31 publications

References 9 publications

Convolutional Networks Used to Classify Video and Audio Data

Convolutional Networks Used to Classify Video and Audio Data

Challenges of Digital Twin in High Value Manufacturing

Assembly Data Mining Platform Based on Python

Contact Info

Product

Resources

About