A Data Mining Approach for Developing Quality Prediction Model in Multi-Stage Manufacturing

Arif, Fahmi; Suryana, Nanna; Hussin, Burairah

doi:10.5120/12106-8375

Cited by 28 publications

(16 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ref. [7] Ref. (9) From the results shown in Table 1, Rough Set learning performs best among our seven models and two previous work.…”

Section: Resultsmentioning

confidence: 94%

“…[4], who used decision tree with boosting technique on the same dataset, the proposed method gain better performance that indicate the introduction of MMS characteristics can benefit the model building process. The result from the work of Arif, F. et al [7] has the good FAR, however, the very low TP rate is not applicable for quality prediction purpose. The confusion matrix of Rough Set result is shown in Table 3.…”

Section: Resultsmentioning

confidence: 95%

“…Based on CQPM definition, it is necessary to find the relationships of inter-correlated variables. PCA can then be used to transform latent variables into a new set of dimensions while they carry MMS characteristics [7]. After the feature set is selected, several classification algorithm, including decision tree, support vector machine (SVM), and Naive Bayes, will then be applied in order to train the binary classifier.…”

Section: Model Building Based On Classificationmentioning

confidence: 99%

“…To consider the characteristic of MMS, Cascade Quality Prediction Method (CQPM) [7,10] is implemented to mine the hidden relationship. Figure 2 shows the scenario of MMS and idea of CQPM.…”

Section: Model Building Based On Classificationmentioning

confidence: 99%

“…Like other machine methods, ANN have been used to solve a wide variety of tasks [5]. On the other side, some research consider the characteristics of MMS and conduct learning after extract related features [6][7][8].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Quality prediction modeling for multistage manufacturing based on classification and association rule mining

et al. 2017

View full text Add to dashboard Cite

Abstract. For manufacturing enterprises, product quality is a key factor to assess production capability and increase their core competence. To reduce external failure cost, many research and methodology have been introduced in order to improve process yield rate, such as TQC/TQM, Shewhart Cycle Deming's 14 Points, etc. Nowadays, impressive progress has been made in process monitoring and industrial data analysis because of the Industry 4.0 trend. Industries start to utilize quality control (QC) methodology to lower inspection overhead and internal failure cost. Currently, the focus of QC is mostly in the inspection of single workstation and final product, however, for multistage manufacturing, many factors (like equipment, operators, parameters, etc.) can have cumulative and interactive effects to the final quality. When failure occurs, it is difficult to resume the original settings for cause analysis. To address these problems, this research proposes a combination of principal components analysis (PCA) with classification and association rule mining algorithms to extract features representing relationship of multiple workstations, predict final product quality, and analyze the root-cause of product defect. The method is demonstrated on a semiconductor data set.

show abstract

“…Ref. [7] Ref. (9) From the results shown in Table 1, Rough Set learning performs best among our seven models and two previous work.…”

Section: Resultsmentioning

confidence: 94%

Section: Resultsmentioning

confidence: 95%

Section: Model Building Based On Classificationmentioning

confidence: 99%

“…To consider the characteristic of MMS, Cascade Quality Prediction Method (CQPM) [7,10] is implemented to mine the hidden relationship. Figure 2 shows the scenario of MMS and idea of CQPM.…”

Section: Model Building Based On Classificationmentioning

confidence: 99%