AbstractTo scientifically and effectively predict the shelf life of damaged Korla fragrant pears, this paper explores the effects of maturity, storage temperature, and damage degree on their shelf life, which was furthermore predicted employing three neural network modeling methods: Back Propagation Neural Network, General Regression Neural Network (GRNN), and Adaptive Network‐based Fuzzy Inference System (ANFIS). A prediction model was then built to achieve the optimal prediction of the shelf life of damaged Korla fragrant pears. The results suggest that maturity, storage temperature, and damage degree exert a significant effect on the shelf life of fragrant pears, and are inversely proportional to the shelf life length; the damaged fragrant pears still have storage value, which can be stored at low temperature according to different damage degree to prolong the shelf life of damaged fragrant pears; the prediction model of maturity, storage temperature, and damage degree on the shelf life of fragrant pears is built based on well‐trained neural networks using the GRNN and ANFIS model, and the ANFIS model with gaussmf input membership function yields the best performance in predicting the shelf life of damaged fragrant pears (root mean square error = 3.5190; R2 = 0.9881). The results offer theoretical guidance for the selection of optimal storage conditions and the effective prediction of the shelf life of fruits and vegetables.Practical applicationsBefore the Korla fragrant pears are stored in the warehouse, the practitioners will directly discard damaged fruits, causing a lot of waste and economic losses. The damaged fragrant pears can be temporarily stored and preserved, and they can be processed and sold in time before the end of the critical shelf life, thereby increasing the economic income of practitioners. Therefore, three neural networks—Back Propagation Neural Network, General Regression Neural Network, and Adaptive Network‐based Fuzzy Inference System—are evaluated for their ability to predict the shelf life of damaged fragrant pears. A shelf life model of damaged fragrant pears is then constructed and screened out, and employed to realize the prediction of the shelf life of damaged fragrant pears. This method is also suitable for predicting the shelf life of other damaged fruits.