Real-time quality monitoring and control system using an integrated cost effective support vector machine

Oh, YeongGwang; Busogi, Moise; Ransikarbum, Kasin; Shin, Dongmin; Kwon, Daeil; Kim, Namhun

doi:10.1007/s12206-019-1145-9

Cited by 13 publications

(7 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…which includes quality analysis, maintenance models for quality improvement, predictive analysis, industrial quality control, nonconformities handling methodologies, different correlations between process steps, six sigma, and SPC tools, continuous improvement approaches, quality optimizations, and process modelling, AR methods integration, problem-solving approaches, and lean manufacturing tools. (Teli et al, 2013;Yang et al, 2021) Quality assurance (Colledani et al, 2014;Eger et al, 2018;Haefner et al, 2014;Duong et al, 2021;Alves et al, 2021;Alexandru et al, 1998;Osanna et al, 2001;Nikolay, 2016;Ransing et al, 2016;Gewohn et al, 2018;Dantan et al, 2020;Khan et al, 2021) Quality control (Durakbasa et al, 1992;Oh et al, 2019;Wu, 2004;Korytkowski et al, 2008;Colledani, 2008;Muthu et al, 2009;Hajji et al, 2012;Villeta et al, 2012;Lv et al, 2012;Jovic et al, 2013;Ordieres-Meré et al, 2013;Achcar et al, 2013;Žapčević and Butala, 2013;Chang and Lee, 2013;Liu et al, 2014;Xia et al, 2014;Dodd et al, 2015;Filho and de Oliveira, 2016;Duffuaa and El Gaaly, 2017;Konstantas et al, 2018;Wang et al, 2018;Hofmann et al, 2019;Guo et al, 2019;Gaikwad et al, 2019;Wang and Wu, 2019;…”

Section: Quality Management Overview and Tabulationmentioning

confidence: 99%

“…Quality control in the manufacturing sector is an important part of nonconforming product management (Durakbasa et al, 1992) and strives to assure the optimum level of quality following market expectations, process capabilities, and enterprise-quality policy. The implementation of different quality control methods can be made considering the cost of quality and their implications, even the ideal scenario is with zero quality issues, moreover, the competitiveness in the market and continuous improvement lead entrepreneurs to cost-related quality decisions (Oh et al, 2019). Production data, by using graphs and SPC specifics, are used to improve efficiency and product quality (Colledani and Tolio, 2006).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Quality and Risk Management in Industrial Production Systems: A Literature Review

Baltag

Morariu

2022

Bulletin of the Polytechnic Institute of Iași. Machine Constructions Section

View full text Add to dashboard Cite

Nowadays quality management and specific tools can represent a challenge in SMEs (small and medium enterprises). To assure the expected quality of the products, SPC (statistical process control) combined with industry 4.0 specifics offer instantaneous responses and triggers for needed actions. Therefore, risk analyses are used as enablers for quality-oriented behaviour, and risk mitigation and identification, together with collected data, represent a comprehensive system that leads enterprises to achieve the expected performance level needed to remain competitive in the market. In addition, risk management and quality management cannot be treated without looking at the maintenance activities and policies which can have a considerable impact on those two. This paper provides a comprehensive literature review of the papers from the quality management sector and articles where risk management and maintenance are seen as facilitators for quality improvement with an impact on the performance level. The main contribution of each paper is listed in the table which simplifies the reader’s access to the work done in the field and the overview presented enables easy access to trends in this field and offers a starting point for future research by presenting the gaps.

show abstract

Section: Quality Management Overview and Tabulationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Quality and Risk Management in Industrial Production Systems: A Literature Review

Baltag

Morariu

2022

Bulletin of the Polytechnic Institute of Iași. Machine Constructions Section

View full text Add to dashboard Cite

show abstract

“…Among them, the BP network has weak generalization ability when modelling complex data in high dimensions (Han et al , 2021a). The SVM based on statistical learning theory is a popular classification prediction method (Oh et al , 2019a), which has been applied in fault detection, supply chain disruptions identification, pattern recognition and other fields (Oh et al , 2019b), but it cannot dig into the hidden risk of food safety. The deep learning method performs very well in processing high-dimensional data (Wang et al , 2020a), and the deeper risk of food safety can be estimated with its regression prediction ability.…”

Section: Literature Reviewmentioning

confidence: 99%

Risk early warning of food safety using novel long short-term memory neural network integrating sum product based analytic hierarchy process

Geng

Lingling

Han

et al. 2021

BFJ

View full text Add to dashboard Cite

PurposeFood safety risk brought by environmental pollution seriously threatens human health and affects national economic and social development. In particular, heavy metal pollution and nutrient deficiency have caused regional diseases. Thus, the purpose of this paper is to present a risk early warning method of food safety considering environmental and nutritional factors.Design/methodology/approachA novel risk early warning modelling method based on the long short-term memory (LSTM) neural network integrating sum product based analytic hierarchy process (AHP-SP) is proposed. The data fuzzification method is adopted to overcome the uncertainty of food safety detection data and the processed data are viewed as the input of the LSTM. The AHP-SP method is used to fuse the risk of detection data and the obtained risk values are viewed as the expected output of the LSTM. Finally, the proposed method is applied on one group of sterilized milk data from a food detection agency in China.FindingsThe experimental results show that compared with the back propagation and the radial basis function neural networks, the proposed method has higher accuracy in predicting the development trend of food safety risk. Moreover, the causal factors of the risk can be figured out through the predicted results.Originality/valueThe proposed modelling method can achieve accurate prediction and early warning of food safety risk, and provide decision-making basis for the relevant departments to formulate targeted risk prevention and control measures, thereby avoiding food safety incidents caused by environmental pollution or nutritional deficiency.

show abstract

“…The framework to pre-process the input data for SVM -based decision-making algorithms was applicable for MLAs , e.g., cost-effective SVM -based automated QMC . It incorporated inspection-related expenses (warranty cost, rework cost, inspection cost) and error types (type I and II errors) in the algorithm [ 28 ]. In this proposal, the quality check reflected the company priorities regarding cost-saving policy versus traditional SVM methods that employ the lowest inspection error rate criterion for classification.…”

Section: Theoretical Backgroundmentioning

confidence: 99%

Process monitoring for quality — A multiple classifier system for highly unbalanced data

Escobar

Macias

2021

Heliyon

View full text Add to dashboard Cite

In big data-based analyses, because of hyper-dimensional feature spaces, there has been no previous distinction between machine learning algorithms (MLAs). Therefore, multiple diverse algorithms should be included in the analysis to develop an adequate model for detecting/recognizing patterns exhibited by classes. If multiple classifiers are developed, the next natural step is to determine whether the prediction benchmark set by the top performer can be improved by combining them. In this context, multiple classifier systems (MCSs) are powerful solutions for difficult pattern recognition problems because they usually outperform the best individual classifier, and their diversity tends to improve resilience and robustness to high-dimensional and noisy data. To design an MCS, an appropriate fusion method is required to optimally combine the individual classifiers and determine the final decision. Process monitoring for quality is a Quality 4.0 initiative aimed at defect detection via binary classification. Because most mature organizations have merged traditional quality philosophies, their processes generate only a few defects per million of opportunities. Therefore, manufacturing data sets for binary classification of quality tends to be highly/ ultra-unbalanced. Detecting these rare quality events is one of the most relevant intellectual challenges posed to the fourth industrial revolution, Industry 4.0 (I 4.0). A new MCS aimed at analyzing these data structures is presented. It is based on eight well-known MLAs, an ad hoc fitness function, and a novel meta-learning algorithm. For predicting the final quality class, this algorithm considers the prediction from a set of classifiers as input and determines which classifiers are reliable and which are not. Finally, to demonstrate the superiority of the MLAs over extensively used fusion rules, multiple publicly available data sets are analyzed.

show abstract

Real-time quality monitoring and control system using an integrated cost effective support vector machine

Cited by 13 publications

References 33 publications

Quality and Risk Management in Industrial Production Systems: A Literature Review

Quality and Risk Management in Industrial Production Systems: A Literature Review

Risk early warning of food safety using novel long short-term memory neural network integrating sum product based analytic hierarchy process

Process monitoring for quality — A multiple classifier system for highly unbalanced data

Contact Info

Product

Resources

About