Online microwave drying process monitoring has been challenging due to the incompatibility of metal components with microwaves. This paper developed a microwave drying system based on online machine vision, which realized real-time extraction and measurement of images, weight, and temperature. An image-processing algorithm was developed to capture material shrinkage characteristics in real time. Constant-temperature microwave drying experiments were conducted, and the artificial neural network (ANN) and extreme learning machine (ELM) were utilized to model and predict the moisture content of materials during the drying process based on the degree of material shrinkage. The results demonstrated that the system and algorithm operated effectively, and ELM provided superior predictive performance and learning efficiency compared to ANN.

For food drying, moisture content and shrinkage are vital in the drying process. This paper is concerned with the moisture ratio modeling and prediction issues of the Hami melon drying process. First, an experimental system was developed; it included an adjustable-power microwave drying unit and an image-processing unit. The moisture contents and the areas of Hami melon slices at different times were sampled in real time. Then, the expression of the moisture ratio with regard to shrinkage was derived by using the Weierstrass approximation theorem. A maximum likelihood fitness function-based population evolution (MLFF-PE) algorithm was then put forward to fit the moisture ratio model and predict the moisture ratio. The results showed that the proposed MLFF-PE algorithm was effective at fitting and predicting the moisture ratio model of the drying process of Hami melon slices.

As an agricultural plant, the cantaloupe contains rich nutrition and high moisture content. In this paper, the estimation problem of the moisture ratio model during a cantaloupe microwave drying process was considered. First of all, an image processing-based cantaloupe drying system was designed and the expression of the moisture ratio with regard to the shrinkage was built. Secondly, a maximum likelihood principle-based iterative evolution (MLP-IE) algorithm was put forward to estimate the moisture ratio model. After that, aiming at enhancing the model fitting ability of the MLP-IE algorithm, a maximum likelihood principle-based improved iterative evolution (MLP-I-IE) algorithm was proposed by designing the improved mutation strategy, the improved scaling factor, and the improved crossover rate. Finally, the MLP-IE algorithm and MLP-I-IE algorithm were applied for estimating the moisture ratio model of cantaloupe slices. The results showed that both the MLP-IE algorithm and MLP-I-IE algorithm were effective and that the MLP-I-IE algorithm performed better than the MLP-IE algorithm in model estimation and validation.