The electrical safety requirements of soybean milk machines with Chinese food cooking characteristics and thefunctions of liquid heating and material crushing cannot be simply constituted by combining liquid heater st...The electrical safety requirements of soybean milk machines with Chinese food cooking characteristics and thefunctions of liquid heating and material crushing cannot be simply constituted by combining liquid heater standard （IEC 60335-2-15） and kitchen appliances standard （IEC 60335-2-14）. The alternating operation of rotation and heating and the antiburnt function may be the special features of safety and performance of soybean milk machines, so it is necessary to take into account those special features in the current standards by some means.展开更多
To accurately identify soybean pests and diseases, in this paper, a kind of deep convolution network model was used to determine whether or not a soybean crop possessed pests and diseases. The proposed deep convolutio...To accurately identify soybean pests and diseases, in this paper, a kind of deep convolution network model was used to determine whether or not a soybean crop possessed pests and diseases. The proposed deep convolution network could learn the highdimensional feature representation of images by using their depth. An inception module was used to construct a neural network. In the inception module, multiscale convolution kernels were used to extract the distributed characteristics of soybean pests and diseases at different scales and to perform cascade fusion. The model then trained the SoftMax classifier in a uniformed framework. This realized the model of soybean pests and diseases so as to verify the effectiveness of this method. In this study, 800 images of soybean leaf images were taken as the experimental objects. Of these 800 images, 400 were selected for network training, and the remaining 400 images were used for the network test. Furthermore, the classical convolutional neural network was optimized. The accuracies before and after optimization were 96.25% and 95.81%, respectively, in terms of extracting image features. This type of research might be applied to achieve a degree of automation in agricultural field management.展开更多
为评估农业机械作业对大豆产量的影响,本文开展不同机型、不同压实次数的拖拉机压实试验,获取不同压实环境中的土壤物理性质和大豆产量数据,分别从影响大豆产量的机械因素、土壤因素和复合因素出发,使用多元线性回归(Multiple linear re...为评估农业机械作业对大豆产量的影响,本文开展不同机型、不同压实次数的拖拉机压实试验,获取不同压实环境中的土壤物理性质和大豆产量数据,分别从影响大豆产量的机械因素、土壤因素和复合因素出发,使用多元线性回归(Multiple linear regression,MLR)、随机森林(Random forest,RF)、自适应增强模型(Adaptive boosting,AdaBoost)、人工神经网络(Artificial neural network,ANN)4种机器学习算法建立大豆产量影响预测模型,对模型性能及模型特征重要性进行综合分析。研究结果表明,机械作业与大豆产量间关系复杂,集成学习算法(AdaBoost和RF)所建立的模型具有更好的拟合效果,模型决定系数更高;利用复合因素对大豆产量建立的模型拟合度最高,其次为机械因素和土壤因素,其中基于AdaBoost的复合因素对大豆产量影响模型其拟合程度最优,其R2为0.92,MAE为1.33%,RMSE为1.86%;机械因素、土壤因素都会影响大豆产量,其中机械压实次数以及表层和亚表层的土壤坚实度为影响大豆产量的重要因素,在实际生产中可通过减少机械作业次数、疏松表层及亚表层土壤来改善机械压实影响。展开更多
文摘The electrical safety requirements of soybean milk machines with Chinese food cooking characteristics and thefunctions of liquid heating and material crushing cannot be simply constituted by combining liquid heater standard （IEC 60335-2-15） and kitchen appliances standard （IEC 60335-2-14）. The alternating operation of rotation and heating and the antiburnt function may be the special features of safety and performance of soybean milk machines, so it is necessary to take into account those special features in the current standards by some means.
基金Supported by 2017 Harbin Application Technology Research and Development Funds Innovation Talent Project(2017RAQXJ079)
文摘To accurately identify soybean pests and diseases, in this paper, a kind of deep convolution network model was used to determine whether or not a soybean crop possessed pests and diseases. The proposed deep convolution network could learn the highdimensional feature representation of images by using their depth. An inception module was used to construct a neural network. In the inception module, multiscale convolution kernels were used to extract the distributed characteristics of soybean pests and diseases at different scales and to perform cascade fusion. The model then trained the SoftMax classifier in a uniformed framework. This realized the model of soybean pests and diseases so as to verify the effectiveness of this method. In this study, 800 images of soybean leaf images were taken as the experimental objects. Of these 800 images, 400 were selected for network training, and the remaining 400 images were used for the network test. Furthermore, the classical convolutional neural network was optimized. The accuracies before and after optimization were 96.25% and 95.81%, respectively, in terms of extracting image features. This type of research might be applied to achieve a degree of automation in agricultural field management.
