Pneumatic Subsoiling Analysis Based On Soil Dynamics And Machine Learning

According to the characteristics of large subsoiling resistance,high subsoiling energy consumption and small subsoiling range,a pneumatic subsoiling mechanism is designed.For the analysis of soil specific resistance,soil disturbance rate and soil bulkiness under different air pressure conditions,it is concluded that pneumatic subsoiling can effectively break the bottom of the plough and can effectively achieve subsoiling and drag reduction.The analysis of the impact of air pressure on subsoiling fills the gap in this field in China.At first,the aerodynamic model of subsoiling is established,and the feasibility of the design is verified through experiments.The influence of tillage depth(25cm,30cm and 35cm),pressure(0.4MPa,0.6MPa,0.8MPa)and working speed(2.5km/h,3.0km/h,3.5km/h)on traction resistance is analyzed using the dynamic telemetry data of the sensor;Secondly,the principal component analysis is used to analyze the disturbance parameters of the pneumatic subsoiling,and the principal component analysis is used to analyze the influence of the relevant dimensions of the pneumatic subsoiling on the subsoiling,and the long short-term memory neural network is used to predict the soil disturbance surface.Due to the large workload of the comprehensive test method,the response surface method is used to analyze the resistance;Finally,a test platform was built to compare with the actual test.The aerodynamic model of subsoiling was used to predict the subsoiling resistance,and the long short-term memory subsoiling network was used to analyze the subsoiling disturbance surface.The test results showed that under the condition of pneumatic subsoiling,the traction resistance decreased by 7.28%-22.37%,and the soil disturbance coefficient was 55.49%.The effect of pneumatic subsoiling showed that it met the design requirements.Pneumatic subsoiling not only improves the problem of small stress of traditional subsoiling,but also increases the disturbance of gas to soil on the basis of traditional subsoiling,so as to achieve subsoiling effect and reduce resistance and consumption.The contribution rate of air pressure to the subsoiling resistance and the subsoiling disturbance surface is 24%and 26%.The specific resistance of subsoiling is analyzed by orthogonal test,and its significance coefficient is 0.95.In the analysis of the bottom line of subsoiling ditch by using the long short-term memory neural network(LSTM)and Bi long short-term memory subsoiling network(Bi-LSTM),the RSME of LSTM and Bi-LSTM is 4.80 and 6.55,and the determination factor R~2is 0.95 and 0.94,respectively,indicating that LSTM and Bi-LSTM can effectively predict the pneumatic subsoiling fracture;By analyzing the specific resistance of pneumatic subsoiling,it can be seen that pneumatic subsoiling can reduce the subsoiling resistance and expand the subsoiling disturbance surface,thus achieving the effects of subsoiling,drag reduction and consumption reduction.