This work researched apple quality identification and classification from real images containing complicated disturbance information (background was similar to the surface of the apples). This paper proposed a novel model based on convolutional neural networks (CNN) which aimed at accurate and fast grading of apple quality. Specific, complex, and useful image characteristics for detection and classification were captured by the proposed model. Compared with existing methods, the proposed model could better learn high-order features of two adjacent layers that were not in the same channel but were very related. The proposed model was trained and validated, with best training and validation accuracy of 99% and 98.98% at 2590th and 3000th step, respectively. The overall accuracy of the proposed model tested using an independent 300 apple dataset was 95.33%. The results showed that the training accuracy, overall test accuracy and training time of the proposed model were better than Google Inception v3 model and traditional imaging process method based on histogram of oriented gradient (HOG), gray level co-occurrence matrix (GLCM) features merging and support vector machine (SVM) classifier. The proposed model has great potential in Apple’s quality detection and classification.

As a key component of a drip irrigation system, the performance of the drip irrigation emitters is mainly determined by the flow channel structures and structural parameters. In this study, a novel type of circular water-retaining labyrinth channel (CWRLC) structure emitter was proposed, inspired by the effect of roundabouts that make vehicles slow down and turn. Using the single-factor experiment method, the influence of the hydraulic performance of CWRLC emitters was researched under different circular radii. The internal flow characteristics and energy dissipation mechanism were analyzed by a computational fluid dynamics (CFD) simulation. It can be seen from the analysis that the energy dissipation abilities of the flow channel depend on the proportion of low-speed vortex areas. The larger the proportion of low-speed vortex areas, the smaller the flow index of the CWRLC emitter. Quadrate water-retaining labyrinth channel (QWRLC) and stellate water-retaining labyrinth channel (SWRLC) structures were obtained by structural improvements for increasing the proportion of low-speed vortex areas. The simulation results showed that the flow indexes of two improved structural emitters were significantly decreased. CWRLC, QWRLC, SWRLC, and widely used tooth labyrinth channel (TLC) emitters were manufactured by using technologies of electrical discharge machining (EDM) and injection molding (IM). The physical test results showed that the SWRLC emitter achieved the best hydraulic performance compared with the other three emitters. Therefore, the SWRLC emitter has a broad prospect of application in water-saving irrigation.

Autonomous excavators are gradually gaining attention because they can reduce the waste of human resources and improve the efficiency. This study proposed a complete coverage path planning algorithm for autonomous excavators based on the Rotating Calipers Path Planning (RCPP) algorithm, which called the Excavator-Rotating Calipers Path Planning (E-RCPP) algorithm. This study uses boustrophedon cellular decomposition (BCD) to decompose the construction area to obtain the convex and non-convex sub-areas without obstacles, and describes a non-decomposition principle to determine whether to decompose non-convex areas that are difficult to plan. To obtain the optimal path, an adaptive spacing adjustment model which is used to adjust the spacing between parallel paths is designed. To improve the coverage rate at the corner, this study proposed a novel boundary corner turning method. The algorithm's cost function considers the path length, the number of turns, the coverage rate and the overlap rate. The Digital Orthophoto Map (DOM) of the construction area is created by Unmanned Aerial Vehicle (UAV) and cropped into three polygonal areas, the 2D top-views of the them are used for simulation experiments to verify the performance of E-RCPP algorithm, the results show that the E-RCPP algorithm has better performance when applied to the complete coverage path planning for excavator compared with the traditional RCPP algorithm.