A method and a device for predicting the shelf life of harvested fresh grapes

Abstract

The embodiment of the invention provides a method and device for predicting the shelf life of harvested fresh grapes. The method comprises the following steps: by analyzing main factors influencing the shelf life of harvested fresh grapes, calculating the shelf life of the fresh grapes in constant-temperature and variable-temperature environments by adopting an analytic hierarchy process on the basis of environmental indexes, sensory indexes and physical and chemical indexes, and generating network model training and testing data; designing the number of hidden layer nodes and a radial basis function of the network by utilizing the super-strong self-adaptive capability and self-learning capability of the RBF neural network so as to improve the convergence speed and learning capability of the network; The center and width of the radial basis function of the hidden layer are optimized by adopting fuzzy clustering, so that global optimization is ensured; The genetic algorithm is adopted to optimize the network weight value and continuously adjust the network weight value, the network is prevented from falling into a local minimum value easily, and the network stability and the generalization capability are improved.

Description

technical field [0001] The embodiments of the present invention relate to the field of crop shelf prediction, and more specifically, to a method and device for predicting the shelf life of postharvest table grapes. Background technique [0002] Fresh table grapes are not only delicious, but also have high nutritional value and economic value, and are widely loved by consumers. At the same time, the requirements for their quality and safety are getting higher and higher. However, problems such as rot, browning, dry branches, hardness attenuation, and shattering are prone to occur during post-harvest storage and transportation, which seriously affect consumers' consumption desire and cause economic losses. Shelf life is one of the important bases for consumers to understand food quality and ensure food safety. The storage environment can be controlled and adjusted in a timely manner according to the shelf life. It is of great significance to reduce economic losses. [0003] ...

AI Technical Summary

Problems solved by technology

At present, RBF neural network has been widely used in the prediction of shelf life. A lot of research results have been obtained at home and abroad on RBF prediction methods, but there are relatively few researches on the prediction of shelf life of fresh grapes.

Images