基于自适应神经模糊网络的果蔬抓取力控制

运用自适应神经模糊推理系统设计了农业机器人果蔬抓取力智能控制器。以当前抓取力和滑觉传感器信号的小波变换细节系数作为控制器的输入,末端执行器两指闭合距离作为控制器的输出。基于减法聚类建立模糊推理模型,通过调整聚类半径来优选模糊规则数。给出了训练样本数据集采集方法,并应用梯度下降与最小二乘混合训练算法辨识了控制器的前件参数和结论参数。对所设计的控制器进行了实验验证,结果表明该控制器能够适应果蔬质量、表面摩擦特性等方面的差异。抓取力超调量得到了限制,最大值小于0.8 N,可以避免给抓取对象造成机械损伤。     

Studies on the humus forms of forest soils

Samples described in the previous paper were analyzed for humus composition by the method of Kumada el al,, elementary composition of humic acids, nitrogen distribution among humic acid, fulvic acid, and humin, and organic matter composition by the modified Waksman method. The samples obtained by physical fractionation from each horizon of Higashiyama soil were as follows: f₁ and f₂ from the L layer, f₁, f₂ and f₃ from the F layer, f₁ f₂, sand, silt, and clay fractions from the H-A and A horizons.

With the progress of decomposition, the following tendencies were rather clearly observed.

The extraction ratio of soluble humus, amounts of humic acid and fulvic acid, and PQ, value tended to increase with some exceptions. The degree of humification of humic acid proceeded. Most humic acids belonged to the Rp type, but those of the clay fractions belonged to the B type.

As for the elementary composition of humic acid, transitional changes from the Lf₁ to the clay fraction of the A horizon were observed. But differences in elementary composition among humic acids were far less, compared with those among whole fractions.

Nitrogen contents in humic, fulvic, and humin fractions increased with the progress of decomposition and humiliation, and the largest relative increase was found in fulvic acid nitrogen.

According to the modified Waksman's method, the amounts of residues and protein increased, while the total amounts of each extract, except for the HCl extract, and the amounts of sugars and starch, phenolic substances, hemicelluloses and pectin, and cellulose decreased. Sugars and starch comprised only a small portion of the hot water extract, and polyphenols substances comparable to sugars and starch were also found in the extract. Hemicelluloses and pectin accounted for only about one-half of the HCl extract. Several characteristic differences in the elementary composition of extracts and residues were found.

Pheopigments existed in benzene-ethanol extracts and their amounts seemed to decrease from Lf₁ to Ff₂.     

Comparison of the new methodologies for predicting the CSP strength of rotor yarn

This paper provides preliminary results on the relative performance of the adaptive neuro-fuzzy system inference (ANFIS) model versus linear multiple regression method, when applied to the use of cotton fiber properties to predict spun yarn strength obtained from open-end rotor spinning. Fiber properties and yarn count are used as inputs to train the two models and the output (dependent variable) would be the count-strength-product (CSP) of the yarn. The predictive performances of the two models are estimated and compared. We found that the ANFIS has a better average prediction successful in comparison with linear multiple regression model.     

ANFIS与多元回归模型在ET0实时预报中的对比研究

以气象数据为自变量,Penman Monteith方程计算值ET_0为应变量,分别建立了多元回归模型和自适应神经模糊推理系统(ANFIS)模型,对ET_0预测结果对比分析,ANFIS预测ET_0结果相对于多元线性回归具有精度高(1ANFIS预测ET_0模型输入项完全可以从当前短期气象预报中获得,程序运行操作简单,在辽阳市实时灌溉预报中有一定的推广意义,具有实用价值。     

工程车辆挡位决策的自适应神经模糊推理系统

提出了一种自适应神经模糊推理系统，并利用在ZL50E装载机传动系统换挡实验中获得的数据进行验证性仿真。仿真结果表明，该档位决策系统可根据操作工况环境实现正确的变速箱挡位决策。它将模糊推理与神经网络有机地结合起来，克服了模糊推理不具备学习功能和神经网络不能表达模糊语言的缺点，使模糊推理与神经网络的应用范围更加广泛，是实现挡位决策的行之有效的方法。     

应用自适应神经模糊推理系统(ANFIS)的ET0预测

参照作物腾发量是计算作物需水量和进行灌溉预报的基础要素。该文利用自适应神经模糊推理系统(ANFIS)所具有的直接通过模糊推理实现输入层与输出层之间非线性映射能力，和神经网络的信息存储和学习能力，将其应用于参照作物腾发量预测中。根据相关分析，输入变量选择日照时数和日最高气温；用5年共1827个数据组对系统进行训练，建立了参照作物腾发量预测系统。利用该系统对近年213个数据组进行了实际预测，与Penman-Monteith方法计算结果进行比较，结果相关性良好。     

基于ANFIS的球形农业物料Re-C关系曲线的拟合

指出了利用传统的关联式方法求解球形农业物料阻力系数的缺陷，基于ANFIS重新建立模型，实现了对Re-C关系曲线的拟合。利用新方法和传统方法进行计算，结果表明，经训练的ANFIS能很好的反应Re-C之间的函数关系，利用Re-C拟合曲线计算阻力系数是可靠的。     

Selection of a Suitable Soft Computing Model for Estimation of Soil Cation Exchange Capacity

ABSTRACT

Measuring of soil cation exchange capacity (CEC) is difficult and time-consuming. Therefore, it is essential to develop an indirect approach such as pedotransfer functions (PTFs) to predict this property from more readily available soil data. The aim of this study was to compare multiple linear and nonlinear regression, adaptive neurofuzzy inference system, and an artificial neural network (ANN) model to develop PTFs for predicting soil CEC. One hundred and seventy-one soil samples were used into two subsets for training and testing of the models. The model's prediction capability was evaluated by statistical indicators that include RMSE, R², MBE, and RI. Results showed that the ANN model had the most reliable prediction when compared with other models. This study provides a strong basis for predicting soil CEC and identifying the most determinant properties influencing soil CEC in the north regions of Iran. Analytical framework results could be applied to other parts of the world with similar challenges.

Abbreviations: ANFIS: Adaptive Neuro-Fuzzy Inference System; ANN: Artificial Neural Network; CEC: Cation Exchange Capacity; CV: Coefficient of Variation; FFBP: Feed-Forward Back-Propagation; FIS: Fuzzy Inference System; MBE: Mean Bias Error; MF: Membership Function; MLR: Multiple Linear Regressions; MNLR: Multiple Non-Linear Regressions; MLP: Multi-layer Perceptron; OC: Organic Carbon; PTFs: Pedotransfer Functions; R²: Determination Coefficient; RI: Relative Improvement; RMSE: Root Mean Square Error; SD: Standard Deviation     

自适应神经一模糊推理系统在水库边坡稳定性评价中的应用

针对水库边坡稳定性影响因子之间复杂的非线性关系,利用自适应神经模糊推理系统（ANFIS）能够同时处理确定性和不确定性信息以及动态非线性分析的能力,提出了基于ANFIS的水库边坡稳定性评价方法。将渗透系数、水位降速、孔隙压力比、坡角、坡高、凝聚力、内摩擦角、重度8个参数作为输入,以水库边坡稳定性系数作为输出,基于21个工程实例,建立了基于ANFIS的水库边坡稳定性评价模型。该模型对训练样本拟合的相关系数为0.999 96,对检测样本的预测相关系数为0.977 48,优于BP神经网络模型。对江西省某水库边坡稳定性进行了预测,结果发现所建立的ANFIS模型对考虑多影响因子耦合作用的水库边坡稳定性有较好的预报功能。     

ET_0预测的卡尔曼滤波修正ANFIS模型研究

实时、准确地对作物需水量的预测是实现智能节水灌溉的关键技术。预测模型的合理选择及精度提高是作物需水决策系统的核心。本文将陕西西安地区的气象数据环境信息引入自适应神经模糊推理(ANFIS)作物参考蒸腾量(ET_0)预测模型,应用卡尔曼滤波器对气象数据经ANFIS建模得到的ET_0预测值进行滤波去噪,以提高模型的预测精度,并通过仿真和实验验证,从理论和实践两个方面来验证模型的精度。仿真结果得到,反映模型预测值与真实值之间拟合程度的均等系数(EC)值校正前为0.93,校正后达到0.98。实验结果得到,ANFIS预测模型的平均绝对误差是28.94%,平均相对误差是26.37%,卡尔曼修正后的ANFIS预测模型的平均绝对误差是7.24%,平均相对误差是6.59%。仿真和实验结果表明,利用卡尔曼滤波对ANFIS预测模型进行修正,可以提高预测的精度,经卡尔曼修正后的ANFIS模型能更佳地反映ET_0的变化趋势。