Agricultural machinery is ever-increasingly either displacing or augmenting human labor with the development of the economy and technology. Among them, fuel efficiency has a significant impact on energy conservation and emission reduction, indicating high economic and social significance. Particularly, a tractor is one of the most typical agricultural machinery. In this study, the overall energy efficiency of tractors was evaluated under actual operating conditions. The performance of tractors was also measured comprehensively. The actual energy efficiency of tractors was clearly defined and calculated as well. The common operating points of tractor engines were extracted by K-means clustering and pairwise comparison matrix, according to the shortest distance partition. The energy efficiency of 186 162 kW tractors was analyzed to propose the classification standard using tractor energy efficiency. Energy efficiency limits and energy efficiency ratio limits were determined at all levels. The average energy efficiency was compared using different operating links. The results showed that there was a significant difference in the distribution and weight between the actual eight operating points and the ISO steady-state eight operating points. The main reason was that the ISO steady-state eight operating point was targeted at non-road diesel engines, covering a wide range of engine models, power, and applications. However, the actual eight operating points were more specific, and refined for the actual operating conditions of multiple 162 kW tractor engines. The error range of tractor energy efficiency was −0.483-0.487 (kW·h)/kg using two datasets of working conditions. Therefore, the energy efficiency calculation was necessary and meaningful using the actual eight working conditions. In addition, there was a significant difference in the tractor energy efficiency using actual operating conditions, where 50% of tractor energy efficiency values were distributed in the range of 3.20 to 3.65 (kW·h)/kg, with an average value of 3.42 (kW·h)/kg. This difference was attributed to the driving habits of agricultural machinery operators, the tractor maintenance and repair levels, as well as the tractor age, resulting in the varying degrees of reduction in engine performance indicators. Then, the grading was constructed using the tractor energy efficiency, where 3.07 (kW·h)/kg was determined as the qualification limit of actual energy efficiency in the tractor. The limit values were also determined for the tractor energy efficiency ratio for levels 1-4. As such, the classification of energy efficiency levels was achieved for tractors. There was a significant variation in the average energy efficiency at different operation stages of each tractor. The rotary tillage mode presented the highest value of average energy efficiency, whereas, the walking mode was the lowest. The trend was attributed to the different engine loads of tractors at different operating stages. Therefore, there was great potential for the real-world energy efficiency performance of tractors from a user perspective. The actual operating performance of tractors was explored to establish an evaluation system applicable to the energy efficiency performance of tractors in the real world. The findings can provide the basic data for energy-saving and emission reduction in tractor engines. A strong reference can be also offered to assess the energy efficiency of agricultural machinery on application subsidy suitable for the level of green operation.

Broccoli (Brassica oleracea L.var.Italica Plenck) is one of the most important vegetables in recent years. However, manual batch harvesting cannot fully meet the high requirement of selective harvesting, due to the strong seasonal labor demand, high labor intensity, and high cost. In this study, a selective harvesting platform was designed to automatically identify and then cut the broccoli, according to the agronomic properties and morphologies. Firstly, the selective harvesting platform primarily consisted of a walking module, identification in cutting device, triggering collection device, and control system. The control system was acquired for the visual information of broccoli through the upper computer. The lower computer was used to control the overall functioning of the harvesting platform, including overall walking, plant localization, flower ball positioning, stalk cutting, and flower ball grasping. Secondly, an "identify-harvesting" integrated operation mode was designed to autonomously identify and cut operations in the broccoli selective harvesting platform. This operational mode was used to mitigate the interference from independent movements of the executing mechanisms during identification. The precise movement distances of executing mechanisms were calculated to enhance the operational accuracy. The key components of the harvesting platform were selected for the visual identity system and centering cutting mechanism for broccoli. The original image of broccoli was collected by the visual system and then processed through grayscale conversion, Gaussian filtering, and threshold segmentation. Thirdly, the dimension and centroid position of the broccoli head were calculated using pixel area and moment. A better performance was achieved in the image processing time of 2.5 s, the average contour deviation of 2.2%, and the measurement centroid position error of 4.2%. According to the interaction between the broccoli stalks and the cutting knife, a logarithmic spiral was utilized as the cutting curve, in order to design a constant slip angle cutting knife. The key cutting parameters were determined, such as a cutting knife sliding angle of 40º, a cutting radius of 135 mm, and a cutting knife length of 260 mm. Additionally, the explicit dynamic simulation of stalk cutting was conducted using ANSYS Workbench/LS-DYNA software, according to the material property parameters of broccoli stalks. Taking the cutting knife edge angle and rotational speed as the control factors, and the maximum cutting force as the experimental indicator, the optimal parameter combination of the stalk cutting was determined by the orthogonal experimental optimization. An optimal combination was obtained in the cutting knife edge angle of 20° and rotational speed of 1 rad/s. The maximum cutting force was 725.82 N, indicating better cutting quality. Finally, the cutting performance test showed that the centering cutting mechanism rapidly and smoothly cut into and cut off broccoli stalks, where the cutting surface was flat and smooth, with a cutting time of approximately 0.6 s per unit, and the 100% success rate of cutting. The performance tests on the harvesting platform showed that the visual system effectively recognized the mature broccoli plants in natural environments with better detection. The overall leakage rate of the harvesting platform was less than 10%, the detection accuracy was 90%, and the qualified rate of cutting stalks was 88.9%, fully meeting the operational requirements of selective harvesting of broccoli. This finding can provide the theoretical and practical reference for the design and development of selective harvesting equipment for broccoli.