Green, healthy and sustainable development is the development direction of China’s agriculture, and stable fertilizer has become the first choice for orchard fertilizer. In this paper, in order to improve the working performance of the combined fertilizer application device of 2KF-30 type orchard stable fertilizer deep applicator, the matching degree of the combined operation of scraper and auger was taken as the research objective, and theoretical analysis, numerical simulation, and experimental verification were combined to carry out the research. Applying fuzzy theory, the comprehensive qualified rate weighted by the uniformity of fertilization and the qualified rate of fertilization was proposed as the evaluation index. The scraper shaft speed, scraper space, spiral conveyor speed, and spiral conveyor pitch were selected as the test factors, and the comprehensive qualified rate of fertilization for the combined fertilization device was taken as the evaluation index. The test design was carried out by single-factor and response surface method tests, and numerical simulations were conducted by discrete element software to analyze the optimal combination of fertilizer application parameters. The test results were analyzed based on the numerical simulation of discrete element software. The testbed was set up to verify the above optimal results. The results showed that the maximum error between the physical test and the numerical simulation was 8.67%, the minimum error was 1.75% and the overall mean error between the physical test value of the combined fertilizer application pass rate and the predicted value of the quadratic regression equation was 5.99%, which can meet the operational performance requirements of the fertilization device. The research results can provide a theoretical basis for the design and improvement of the deep fertilizing machine for orchard manure.

With the rapid development of the turtle breeding industry in China, the demand for automated turtle sorting is increasing. The automatic sorting of Chinese softshell turtles mainly consists of three parts: visual recognition, weight prediction, and individual sorting. This paper focuses on two aspects, i.e., visual recognition and weight prediction, and a novel method for the object detection and weight prediction of Chinese softshell turtles is proposed. In the individual sorting process, computer vision technology is used to estimate the weight of Chinese softshell turtles and classify them by weight. For the visual recognition of the body parts of Chinese softshell turtles, a color space model is proposed in this paper to separate the turtles from the background effectively. By applying multiple linear regression analysis for modeling, the relationship between the weight and morphological parameters of Chinese softshell turtles is obtained, which can be used to estimate the weight of turtles well. An improved deep learning object detection network is used to extract the features of the plastron and carapace of the Chinese softshell turtles, achieving excellent detection results. The mAP of the improved network reached 96.23%, which can meet the requirements for the accurate identification of the body parts of Chinese softshell turtles.