Improvement Methods of Fuzzy Control with Intelligent Integration

Fuzzy controller can achieve satisfactory dynamic performance even for complicated process without mathematical model of the process.Its main imperfection is the existence of steady state error and ultimate oscillatory in the process output. This limits its application area. How to eliminate the steady state error while keep its good dynamic performance has been paid much attention. The strategy to introduce integral function to the conventional fuzzy control system is put forward in this paper to overcome the above problem. After expound two key factors on introducing integral action,an intelligent integral algorithm has been employed,and two methods on introduction of the intelligent integral to the fuzzy control system are proposed. Their characteristics and applied situations are summarized.     

Fuzzy Assessment of MSW Disposal Technologies

Three disposal technologies have their own advantages, and meanwhile disadvantages. Facing a special case, it is difficult to choose a proper one. By integrated analysis to three main technologies, a relatively integrated index system is established. Then by means of fuzzy mathematics (quantify and synthetically analyze the index system, make it unitary) ,a final general assessing model is founded. Finally, the paper takes a planning MSW(municipal solid waste) plant as an example, uses a two-level fuzzy assessment model with three groups of assessing factors,which include economical, environmeutal and the other factors, and concludes that composting is the most appropriate choice.     

A Self-Learing Chinese Character Recognition System

A method using possibility theory and fuzzy logic is introduced. Possibility functions of each feature are determined during training. Methods of fuzzy logic are used to combine the possibility of different features. This Chinese character recognition system consists of a pre-classifier and a two-level fine classifier. In order to handle deviations of the characters,a fuzzification of features is introduced. This method is used to develop single-font classifiers. The whole system consists of a font-classifiers and four single-font-classifiers.     

采用遗传算法计入摩擦力作用的标准斜齿轮传动模糊可靠优化

传统的齿轮强度理论不考虑齿间摩擦的影响。针对这一观点，该文以渐开线斜齿圆柱齿轮传动的小齿轮齿数、法面模数、螺旋角、齿宽系数为设计变量，以两齿轮的体积之和为最小目标函数，通过应用模糊设计理论和可靠性设计理论，建立摩擦力作用下标准斜齿圆柱齿轮传动的模糊可靠性优化设计的数学模型，并采用遗传算法对其进行优化。研究表明，效果很好。     

基于电子鼻的果园荔枝成熟阶段监测

为了无损快速监测荔枝成熟阶段,该文提出了一种基于电子鼻技术的果园荔枝成熟阶段监测方法,采用PEN3电子鼻获取挂果约25 d到果实成熟过程中6个成熟阶段荔枝样本的仿生嗅觉信息并同步获取了各成熟阶段荔枝的3项物理特征(果实直径、果实质量与果实可溶性固形物含量)。根据不同成熟阶段荔枝物理特征变化可知,荔枝果实直径与果实质量2项物理指标在挂果约32 d~39 d,以及53 d~60 d增长较快,可溶性固形物含量在挂果约32 d前无法测量,53 d~60 d阶段增长速度较慢。提取各样本电子鼻采样数据75 s时刻的各传感器响应值作为特征值后,采用载荷分析(loadings)进行传感器阵列优化,优选了传感器R2、R4、R6、R7、R8、R9和R10的响应数据进行后续分析。将优化后的传感器响应数据进行归一化处理。采用线性判别分析(linear discriminant analysis,LDA)进一步提取特征信息,降低数据中包含的冗余信息。LDA对荔枝成熟阶段的分类识别效果不佳。为进一步探究电子鼻监测果园荔枝成熟阶段的可行性,采用模糊C均值聚类分析(fuzzy C means clustering,FCM)、k最近邻函数分析(k nearest neighbor,KNN)和概率神经网络(probabilistic neural network,PNN)进行模式识别。研究结果表明,FCM对果园荔枝成熟阶段识别的正确率为89.17%。采用KNN与PNN建立识别模型后,KNN与PNN识别模型对训练集的回判正确率均为100%,对测试集的识别率均为96.67%,具有较好的分类识别效果。试验证明了采用电子鼻进行果园荔枝成熟度监测的可行性,为果园水果品质的实时监测提供参考。     

植保四轴飞行器的模糊PID控制

针对当前植保四轴飞行器在作业过程中自身载荷发生改变后的飞行控制性能下降、抵抗环境扰动能力差的问题,该文改进了传统比例积分微分(proportion,integration,differentiation,PID)控制算法,提出了一种模糊PID控制算法。该文通过研究四轴飞行器的姿态解算和飞行原理,设计了以STM32系列的单片机为核心处理器的四轴飞行控制系统。采用AHRS模块实时解算飞行器姿态参数,结合模糊控制和PID控制算法调节电机的输出量来控制飞行姿态。试验结果表明:与传统PID相比,模糊自整定PID控制算法适应性强,参数整定简单,系统的动态响应能力和稳定性获得了提高,实现了四轴飞行器的稳定飞行。该文为植保无人机控制算法研究提供了一定的参考。     

泥石流危险度的模糊综合评判

泥石流沟谷是一个复杂的“模糊”系统,它是由多种因素构成,应用模糊综合评判法,选取了7个因子作为泥石流危险度划分的主要关联因子,并且运用了灰色系统关联度分析法确定了评价因子隶属度,对泥石流沟谷危险程度进行了判别,其评价结果显示了模糊评判法具有较高的判别准确度,为进行有效的灾害防治提供了可靠的科学依据。     

Influence of acid soil on nodule numbers in relation to polyamine and tannin concentrations in roots of Phaseolus vulgaris

The relationship between soil acidity and polyamine (putrescine, spermidine, spermine) concentrations in roots was evaluated and compared to (1) nodule numbers in common beans and (2) tannin concentrations in roots. Six Phaseolus vulgaris cultivars were grown in pots in a greenhouse in soil at pH 4.5 or 5.5 and inoculated with Rhizobium leguminosarum bv. phaseoli strains. At pH 4.5 nodule numbers were strongly reduced but polyamine concentrations were 50% higher than at pH 5.5. At both pH levels putrescine and spermidine were the dominant polyamines, while the concentration of spermine was less than half of the other two. There was also a cultivar effect on the polyamine concentration, but this was much less pronounced than the pH effect. By 22 days after planting the uninoculated control plants had about 13% lower levels of polyamines than the inoculated plants. The concentrations of putrescine, spermidine, and spermine were negatively correlated with nodule numbers, but positively correlated with the root tannin content. There were no significant correlations with either root or plant dry weight.     

土地整理效益项目后综合评价方法

论文借鉴多目标多层次指标体系综合评价的理论与方法，以宁阳县伏山土地整理项目为例，构建了包括技术、经济效益、社会效益、景观与生态环境效益指标的土地整理效益项目后评价指标体系。采用特尔菲法和层次分析法相互校正的方法综合确定各评价指标权重，根据评价指标对项目成功度的效应建立各评价指标的模糊分布函数，在此基础上通过模糊综合评判得到土地整理效益项目成功度的评价结果。研究结果可供土地整理项目后的综合评价提供参考。     

农村土地综合整治社会风险评价——以南京市江宁区为例

[目的]分析农村土地综合整治社会风险水平,以弥补已有农村土地综合整治社会风险诊断中指标体系及评价方法的不足。[方法]在界定农村土地综合整治社会风险内涵的基础上,从环境、制度、经济和社会4个方面构建了社会风险的评价指标体系,采用主客观赋权法和模糊综合评价模型,对南京市江宁区良田建设工程社会风险进行评价。[结果]江宁区良田建设工程总体社会风险介于第三级"风险中等"和第四级"风险较小"之间,但更接近第三级,说明工程开展的社会风险程度不高,在当地不会造成大的社会不稳定,但对于存在的社会风险仍然需要加以防范。[结论]为了进一步规避农村土地综合整治带来的社会风险,应该从完善整治目标、健全公众参与、强化工程监管和科学评估风险4个方面采取措施,促进农村土地综合整治事业的健康有效开展。