EXTRACTING AND MODIFYING THE VIBRATION CHARACTERISTIC PARAMETERS OF WATERMELON BASED ON EXPERIMENTAL MODAL MEASUREMENT AND FINITE ELEMENT ANALYSIS FOR HOLLOW HEART DEFECT DETECTION

Hollow heart defect seriously influences the taste and storability of watermelon. In this study, a non-destructive detection system based on an impulse vibration method was developed to detect hollow watermelon. First, acceptable agree-ment between the theoretical and experimental models of watermelon proved the suitability of investigating the relationship between hollow heart defect and vibration characteristic parameters by finite element analysis (FEA). Through modal anal-ysis, the optimum location for the detection sensor was determined at the opposite location or 90 degrees from the excitation point. The normalized second to fourth resonance frequencies (f(2n), f(3n), and f(4n)) and the peak value at the second frequency (A(2)) were extracted as latent variables for prediction of hollow watermelon. The technical parameters of the pressurized-air excitation device were then modified in orthogonal tests, and the best combination of technical parameters was as follows: air pressure of 275 kPa, excitation distance of 9 cm, and pulse width of 200 ms. In the qualitative discrimination of hollow watermelon, the results showed that a back-propagation neural network (BPNN) using 13 vibration characteristic param-eters had the best classification performance, with accuracies of 91.7% and 88.9% for the calibration and prediction sets. In the quantitative analysis of hollow rate, the best prediction result was achieved with the BPNN (r(p) = 0.829, RMSEP = 0.016), which selected ten vibration characteristic parameters as input variables. Therefore, it is feasible to detect hollow watermelon by impulse vibration, and this method has potential to be applied in on-line defect detection.