Non-destructive quality assessment of Golden Delicious apple is the aim of this study. The ultrasound non-destructive testing (NDT) system in the range of 40 kHz–20 MHz ultrasonic wave was applied in combination with artificial neural network (ANN) as a powerful modeling tool. The studied quality factors were the mechanical properties including firmness, elastic modulus, and stiffness of apples. To develop the ANN models, the feed-forward neural network with the backpropagation algorithm was developed. For firmness, the best ANN model with 7-11-1 topology (7 features as inputs, 11 neurons in the hidden layer, and one output) had the highest R²_Prediction and the lowest MAE_Prediction and SE_Prediction which were equal to 0.999, 0.0836 N, and 0.1119 N, respectively. For elastic modulus, the 7-17-1 structure of ANN was the best with corresponding R²_Prediction equal to 0.999, MAE_Prediction equal to 0.0087 MPa, and SE_Prediction equal to 0.0117 MPa. The model with structure of 7-13-1 and R²_Prediction of 0.999, MAE_prediction of 0.027 N/mm, and SE_Prediction of 0.0371 N/mm was also selected for predicting the stiffness of apple. The results proved the ability of this method to non-destructively predict mechanical properties of Golden Delicious apple.

中文翻译：

---

超声波技术和人工神经网络预测金苹果的力学性能

本研究的目的是对金冠苹果进行无损质量评估。在40 kHz–20 MHz超声波范围内的超声无损检测（NDT）系统与强大的建模工具人工神经网络（ANN）结合使用。研究的品质因素是机械性能，包括苹果的硬度，弹性模量和刚度。为了开发ANN模型，开发了带有反向传播算法的前馈神经网络。为了牢固起见，具有7-11-1拓扑的最佳ANN模型（7个特征作为输入，11个隐藏层神经元和一个输出）具有最高的R ²_预测和最低的MAE_预测和SE_预测分别等于0.999、0.0836 N和0.1119N。对于弹性模量，ANN的7-17-1结构最佳，相应的R ²_预测等于0.999，MAE_预测等于0.0087 MPa ，SE_预测等于0.0117 MPa。还选择了具有7-13-1结构和R ²_预测为0.999，MAE_预测为0.027 N / mm，SE_预测为0.0371 N / mm的模型来预测苹果的硬度。结果证明了该方法能够无损预测金冠苹果的力学性能。