Data-analytics-based factory operation strategies for die-casting quality enhancement

Abstract

This paper proposes data-analytics-based factory operation strategies for the quality enhancement of die-casting. We rst de ne the four main problems of die casting that result in lower quality: [P1] gaps between the input and output casting parameter values, [P2] occurrence of preheat shots, [P3] lateness of defect distinction, and [P4] worker-experience-based casting parameter tuning. To address these four problems, we derived seven tasks that should be conducted during factory operation: [T1] implementation of exploratory data analysis (EDA) for investigating the trends and correlations between data, [T2] deduction of the optimal casting parameter output values for the production of fair-quality products, [T3] deduction of the upper and lower control limits for casting parameter input-output gap management, [T4] development of a preheat shot diagnosis algorithm, [T5] development of a defect prediction algorithm, [T6] development of a defect cause diagnosis algorithm, and [T7] development of a casting parameter tuning algorithm. The details of the proposed dataanalytics-based factory operation strategies with regard to the casting parameter input and output data, data preprocessing, data analytics method used, and implementation are presented and discussed. Finally, a case study of a diecasting factory in South Korea that has adopted the proposed strategies is introduced.

Universal Model for the Quality Analysis of Aluminium Alloys Castings

“…Achieving and maintaining a permanent competitive advantage means for manufacturers to orient the management system to increase the quality of products offered, efficiency and innovation in the implementation of manufacturing processes [1][2][3]. Various management strategies are widely described in the literature, as well as the actions taken in this area [4][5][6][7][8]. Economic progress has contributed to the fact that, in addition to the quality of products and services offered, ISO standardization has become an additional criterion determining the success of enterprises [9,10].…”

Quality Control of Semi-Solid Die Casting by Filling Pressure Based on Machine Learning Method

“…The reason for the existence of quality problems is that most factories lack data analytic [3]. To overcome this resistance, real-time production data is ought to be monitored to recognize unsuitable process that can cause quality problems and hence the model that correlate them should be built [4].…”

Advances in Metal Casting Technology: A Review of State of the Art, Challenges and Trends—Part II: Technologies New and Revived

“…In terms of the actual information extraction, they compare several AI methods like decision trees, random forests, neural networks and support vector machines (SVM). These various approaches are compared to each other in terms of accuracy achieved, both in a bare state and when using training data imbalance compensation [347]. The interested reader may find several more examples of this or similar cases.…”

“…Typically, for an established production process, this is not the case; in practice, there will be far more good quality parts than rejects [328], which means that compensation efforts are needed. On a theoretical basis, compensation can be achieved via techniques like SMOTE (synthetic minority oversampling technique)-also employed by Kim and Lee [347]-which increase numbers in the underrepresented group by numerically constructing additional input-output combinations [348]. Kim et used this technique in combination with random forest (RF) algorithms in order to improve training data for a defect prediction task in an HPDC setting [349].…”