Level: Intermediate
(Uses machine translation)
Prepared foods such as dumplings are usually cooked without precise process control of cooking parameters. The objective of this work is to customize the cooking process of dumplings based on different dumpling product types. In the dumpling cooking process, water temperature and cooking time are the most important factors that determine the degree of cooking (doneness) of dumplings. Dumpling weight, dumpling type, and batch size are also variables that affect the cooking process. A structured JMPDSD platform with special properties was built to build a prediction model of cooking time. The internationally recognized ISO22000 Food Safety Management and Hazard Analysis Critical Control Point (HACCP) schema was adopted. A JMP neural fit method using modern data mining algorithms was compared with RSM. The results showed a greater prevalence of main effects from factors such as boiling temperature, product type, dumpling size/batch, and interaction effects constrained by the mixture used in the dumpling composition. In this design/analysis approach, JMP robust design optimization, Monte Carlo simulation, and HACCP control limits were employed to understand and characterize the sensitivity of dumpling cooking factors to the resulting cooking time. The holistic approach demonstrated the synergy of combining models with different projective properties: the recursive partition-based AI model estimates interaction effects using a classification schema, while classical (stepwise) regression modeling provides the ability to interpret second- or higher-order interactions, including potential curvature in quadratic terms. In this paper, we described a novel automated dumpling cooking process and analytical framework (with an AI schema) that can improve the overall process, reduce energy costs, and lower labor costs. This new methodology has the potential to change the way we think about estimating business costs and modeling profits in the foodservice industry.
To watch the announcement, click here .
Go to the Sessions page under Discovery Summit Americas.
(Please note that you will be asked to log in to your SAS Profile.)
