![]() Also features in the time series data must be identified. It can be hard to instrument to collect all these process data. The number of potential causal factors is vast. Using factory data to construct machine learning models to predict the onset of defective parts is challenging for several reasons. Challenges in Foundry Quality Control and Root Cause Analysis Then in ‘ Classification Algorithm Model,’ statistical machine learning models are presented that classify process conditions where porosity defects arise. In ‘ LPDC Porosity Defect Prediction,’ casting defects monitored are discussed. In ‘ Industry 4.0 Foundry Data Collection,’ an Industry 4.0 data collection system is presented to means for digitally timestamp and track parts and associated data through the foundry. In the first section, challenges to identifying causes of defects during production operation of a LPDC foundry are presented and then related research is discussed. It is critical to quickly tune process settings in pre-series production. A typical foundry will have hundreds of different models and dozens of new product models introduced each year. However, it is helpful for quantifying causes of porosity defects. While this work can help predict porosity defectives, it cannot replace the X-ray machine for inspection. ![]() LPDC production historically has high defective rates, typically every part in production is inspected using an X-ray machine for porosity defects. These can then be used to help tune process control. With this, machine learning classifier algorithms are utilized to identify the combinations of process settings that give rise to process defects. An Industry 4.0 quality control data system can associate recorded data from all process measurement points to individual parts complete with its inspection results. A means is needed to monitor and analyze the process settings and deviations which can give rise to porosity defects. When such casting defects arise, it is often difficult to diagnose their exact root cause and thus make the correct process parameters changes. ![]() The causes of porosity defects can come from a variety of different factors, such as metal composition, hydrogen content, casting pressures, temperatures, and die thermal management to obtain directional cooling rates. Therefore, the cause and prevention of porosity defects are important considerations in quality control and create a demand to optimize the process variables to improve the part quality. They can be difficult to avoid and can compromise the integrity and performance of the components. Porosity discontinuities are one of the most frequent defects found in LPDC aluminum products. Low-pressure die casting (LPDC) is a process broadly used in industries requiring metal cast components with high performance, precision, and volume, such as the production of aluminum alloy wheel rims in the automotive industry. This work was helpful in assisting process parameter tuning on new product pre-series production to lower defectives. Porosity defect occurrence rates could be predicted using 36 features from 13 process variables collected from a considerably small sample (1077 wheels) which was highly skewed (62 defectives) with 87% accuracy for good parts and 74% accuracy for parts with porosity defects. Data were collected from a particular LPDC machine and die mold over three shifts and six continuous days. A model based on the XGBoost classification algorithm was used to map the complex relationship between process conditions and the creation of defective wheel rims. The root cause analysis is difficult, because the rate of defectives in this process occurred in small percentages and against many potential process measurement variables. With these data, supervised machine learning classification models are proposed to identify conditions that predict defectives in a real foundry Aluminum LPDC process. In this paper, industry 4.0 cloud-based systems are used to extract data. To do this, process variable measurements need to be studied against occurrence rates of defects. A need exists to optimize the process variables to improve the part quality against difficult defects such as gas and shrinkage porosity. The quality of LPDC parts is highly influenced by the casting process conditions. Low-pressure die cast (LPDC) is widely used in high performance, precision aluminum alloy automobile wheel castings, where defects such as porosity voids are not permitted.
0 Comments
Leave a Reply. |