Abstract: This research proposed a non-destructive testing method for quality inspection of Shijiazhuang Huangguan pear based on electronic nose technology and pattern recognition method. An electronic nose(PEN3)was applied to sample black-free pears and three grades of black-core pears according to the degree of corruption. And the image acquisition system was used to take photos of the pear samples. The data was identified by the combination of principal component analysis(PCA)and linear discriminant analysis(LDA)dimension reduction methods with logistic regression(LR),support vector machine(SVM),gradient lifting tree(GBDT)and XGBoost classification methods. The average accuracy of PCA-LR,PCA-SVM,PCA-GBDT,PCA-XGBoost,LDA-LR,LDA-SVM,LDA-GBDT,LDA-XGBoost reached 75.0%,79.4%,84.4%,91.9%,73.1%,82.5%,87.5%,95.6%. The LDA-XGBoost method achieved the best classification performance with an accuracy rate of 95.6%. Experiments showed that the method was a fast,accurate and non-destructive monitoring method,which provided a new idea and method for quality inspection of Huangguan pear.