Evaluating operation benefit of agricultural machinery using semi-supervised BP_Adaboost

Management level and user benefits have greatly contributed to agricultural machinery in recent years. The operational efficiency of agricultural machinery was commonly used to evaluate the utilization rate, operator driving ability, and management efficiency of agricultural machinery. However, the current operational efficiency of agricultural machinery cannot fully represent the overall operational efficiency of agricultural machinery. For example, although the low-power agricultural machinery has low operational efficiency, the generated benefits are not lower than that of high-power agricultural machinery, if the operating time is saturated. In addition, the quality of agricultural machinery operation can seriously affect operational efficiency. Therefore, it is necessary to consider the key influencing factors on the efficiency of agricultural machinery operations. In this study, a comprehensive and comprehensive evaluation was conducted on agricultural machinery operations. The operational efficiency was then evaluated on each agricultural machine using influencing factors. The daily operational information of each machine was taken as a piece of data on that day. The operation status of operators and agricultural machinery were checked to identify the influencing factors on the efficiency of operations, in order to improve the management level and revenue of agricultural machinery. The data was collected from the 32000 deep loosening operations of agricultural machinery. The results show that the main influencing factors on the daily operation efficiency of agricultural machinery were directly obtained, including the daily operation area, fuel consumption, operation quality, repeated operation rate, missed operation rate, and the proportion of effective operation time. The BP_Adaboost neural network (NN) training model was used to evaluate the efficiency of agricultural machinery operation. Manually grading was replaced to avoid the large workload and extremely low efficiency from the subjective factors, inconsistent standards, and labeling errors, due to the large number of agricultural machinery and the large amount of homework data. A comparison was made on the training model and manual grading to predict the remaining data. Manual scoring standards were effectively used to establish the predictive models. A small number of samples were selected to predict the operational efficiency of agricultural machinery. The low accuracy was obtained in the training model if there were too few labeled samples. If the additional labeled samples were added, manual grading was less labor-saving. Semi-supervised BP_Adaboost was utilized to evaluate the efficiency of agricultural machinery operations, where manually scoring some data was marked the daily efficiency. One part was used as training samples, whereas, another part was used as testing samples. The BP_Adaboost was then used to reduce the manual labeling of training samples for the high accuracy of the training model, where the remaining unrated data was predicted after training the model. 1 000 samples were selected from 32 000 deep loosening operation data for labeling, of which 500 were used as training samples and 500 were used as testing samples. The highest prediction accuracy was achieved in the semi-supervised method for the selected experimental data when the probability threshold was 97%. If the threshold was too large, there was only a limited increase in samples; If the sample was too small, misclassified samples led to low accuracy. Therefore, there was a significant impact on the sample selection and termination in semi-supervised methods. The prediction accuracies were achieved in 93.36% and 97.03%, respectively, using the BP_Adaboost, and semi-supervised BP_Adaboost with training samples. Statistical analysis was conducted on 32 000 agricultural machinery operation data from the experiment. The effectiveness of the improved model was obtained by combining the partial power agricultural machinery with different-width machines. The operation efficiency varied greatly in the power agricultural machinery when paired with different width machines. The optimal combination of agricultural machinery was recommended to enhance the operational capabilities, according to the operational efficiency. The accuracy of the improved model was higher than that of using the BP_Adaboost alone, depending largely on the selection of the probability threshold. The generalization and standards can be expected for the different datasets and the optimal thresholds. A more reasonable probability threshold can be selected to assign different weights to various indicators for the better performance of the improved model.