Design and Optimization of Amino-Acid-Nitrogen Configuration System for Automatic Guangdong Soy Sauce Production

Soy sauce is a traditional condiment that plays an important role in people's daily life. The configuration process is one of the most crucial step in soy sauce production, which will directly affect the flavor and quality of the final product. However, due to the multiple variables and the control errors in the configuration system, it is still a challenging task. In this paper we propose a novel automatic soy sauce configuration system. To the best of our knowledge, this is the first work to introduce a method for automatically blending soy sauce and configuring Amino-Acid-Nitrogen (AAN) concentration for Guangdong soy sauce production. More specifically, we build a nonlinear constrained optimization model which can be set as different objective functions and constraints for corresponding purposes in different conditions. A new pretreatment configuration has been proposed to simplify the design as well as the optimization of AAN concentration model. We employed cross-method to choose initial values in order to speed up the convergence. Furthermore, we introduce an error compensation algorithm, which is based on the analysis of the final blending concentration error, to improve the accuracy of the configuration model. The proposed method has been tested with the soy sauce configuration problem. Experimental results show that our method can meet the production requirements and improve the accuracy and efficiency of soy sauce configuration process.