Li Yaoming

Multi-scale edge detection of rice internal damage based on computer vision

Damage is easy to occur during the process of harvesting, classification, packaging, transporting, processing, preservation and selling etc. and the detection of internal damage is a difficult problem. Rice kernels were classified as those with none, single, double or multiple stress cracks. An image processing algorithm was used to enhance the object and reduce noise in the acquired image. At the same time a machine -vision system was developed to detect different types of stress cracks in rice kernels. None and single stress cracks were the easiest to detect. Careful positioning of the kernel over the lighting aperture was necessary for accurate detection of double and multiple stress cracks. This system provided an average accuracy of approximately 96.5% to none crack, 93.4% to single crack, 84.2%to double cracks and 83.4% to multiple cracks compared to human inspection. The processing time was between 0.45 and 0.12 s/kernel.

Experimental study on flexural mechanical properties of corn stalks

Flexural mechanical properties of four kinds of corn stalks were studied on the WDW-300 type micro-control electronic universal material test machine. The load- deformation curves of corn stalks and the maximum load, elastic modulus, flexural strength and deformation value were obtained in the way of 3-point bending. The influence of varieties, cross-sectional area, growth areas and moisture content on the mechanical properties of corn stalks was analyzed. The result that the bending process can be made of linear elastic process, non-linear elastic process and bending fracture process was got. The average anti-flexural strength and elastic modulus of corn stalks are 7.85MPa and 0.15GPa. Differences of Linear elastic range and deformation value of stalks bending exist in the varieties. Under other condition of the same, a positive correlation linear relationship was founded between the maximum load and cross-sectional area of corn stalks. With the increasing of growth areas, the maximum load was decreased gradually. Test result has important guiding significance to the design of high efficiency and low energy consumption corn harvester.

Prediction for Working Performance of Air-and-screen Cleaning Unit Based on the epsilon-SVR Method

On the basis of analyzing disadvantages of conventional prediction model of air-and-screen cleaning device, a new regression model based on support vector machine was proposed to predict and control of cleaning process precisely. Parameters of e-SVR models were determined utilizing non-heuristic Grid Search, heuristic GA and PSO which could avoid the choice of randomness. The effect of samples in different on prediction performance of e- SVR was analyzed compared with BP. The results indicate that the prediction property of e-SVR is better than BP especially in small-sample.

Test method research of rape adhesion properties based on image technology

In this paper, the author puts forward a new adhesion properties test method, which define the adhesion rate by the residual adhesion area to measure interface adhesion properties when the traditional method measured by adhesive force cannot work. The residual adhesion area was calculated by matlab language with image technology. Adhesion properties test of the interface between rape mixture materials and screen matrix was carried out to help illuminate this new test method. The results show that the adhesion rate of the interface between rape mixture materials and screen matrix was 9.5% with error less than 2%. It is also show that this method can be used to test adhesion properties effectively.

Finite Element Analysis of Input Gears in a Gearbox of Combine Harvester

The input gears from the first stage of a combine harvester gearbox have been subjected to experimental testing. A three-dimensional finite element model was established by using Solid Works and the effect of an external load distribution along the gear tooth width was added according to actual working situations. In the Solid Works/Simulation module, the contact relation was established based on the real assembly relations, and to calculate Von Mises stress, on the teeth. Through modal analysis, the gears teeth frequency was analyzed contrastively with the inherent model of the transmission and analyzed the influence of them. The experiment was carried out in the self-made gearbox fatigue test bed. The results indicate that serious pitting appeared on the surface of the teeth when the working time was over 500 hours and the input gears were not measurably distorted, which basically coincides with the analyzed results of the theory.