黄河下游生态径流量计算研究

选取黄河下游地区花园口、高村、利津3个代表站的实测月径流量系列,利用逐月均频率计算法和改进的Tennant法2种历史流量计算方法分别计算了3个代表站的生态径流过程.结果表明:虽然2种计算方法原理不同,但是由逐月均频率计算法得到的适宜生态径流量大都在改进的Tenannt法所得结果的最佳或极好范围之内,只有个别月份与最佳范围的数值有一定的差值,但也位于可接受的范围内.     

基于改进蚁群算法的集装箱装卸顺序优化研究

为缩短船舶在港时间,提高码头的作业效率,应用改进蚁群算法对集装箱装卸顺序的组合优化问题进行求解。首先结合柔性作业车间调度理论与集装箱装卸过程中船舶和岸桥的实际情形,建立集装箱装卸顺序调度模型;然后针对基本蚁群算法易出现早熟现象和收敛速度慢等问题,通过动态的改变信息素的挥发度与信息素强度,同时按照改进的信息素更新策略更新各路径的信息素,从而跳出局部最优;最后运用C#.NET语言对基于改进蚁群算法的集装箱装卸顺序问题进行仿真与步骤分析,验证了改进蚁群算法的有效性。实践证明,改进后的蚁群算法基本上克服了传统算法自身的不足,能够对集装箱装卸顺序优化,缩短作业时间。     

通航机场场面运动目标检测方法

针对传统YOLOv3(you only look once-v3)算法目标检测精度较低、收敛速度较慢等问题,提出了一种改进的YOLOv3算法,分别对主干网络和损失函数进行了改进。采用迁移和冻结相结合的训练方法,以提升目标检测的精确度和速度。基于改进的YOLOv3算法对西南某通航机场3种不同场景下的运动目标检测效果进行了对比分析。结果表明,改进的YOLOv3算法对正常天气场景下的场面运动目标检测效果要明显优于雾天和雨天场景,对飞机目标的检测效果明显优于车辆和行人目标;3类目标的检测精度、召回率、平均精度值(mean average precision, mAP)分别达到92.96%、80.51%、91.96%,GPU处理速度为74.0帧/s,较传统YOLOv3算法和YOLOv4算法性能均有明显提升。     

改进遗传算法求解带不相关并行机的HFSP

以最小化最大完工时间为目标的不相关并行机混合流水车间调度问题.首先建立了不相关并行机混合流水车间调度问题的数学模型;然后提出了改进的遗传算法进行求解.为弥补遗传算法的迭代后期容易陷入局部搜索的缺陷,在传统遗传算法的基础上利用改进的自适应交叉和变异概率因子及模拟退火局部搜索策略,增强遗传算法在迭代后期跳出局部最优的能力....     

考虑质量衰退的批量调度与预防性维护的联合优化

针对生产调度过程中由于设备退化引起产品质量劣化的问题,构建了考虑质量与设备状态之间的耦合关系以及生产批次可分的批量流调度与预防性维护的联合优化模型。假设设备存在"受控"和"失控"两种状态,利用设备"失控"状态下产生的不合格品作为媒介描述上游设备与下游设备之间的随机依赖性,以最小化期望完工时间以及总成本为优化目标建立了数学模型;设计改进的差分进化算法对模型进行求解;通过数值实验验证了算法的收敛性,并通过对比实验对模型性能进行分析,结果显示了该联合优化模型的有效性。     

Diagnosis of multiple faults using a double parallel two-hidden-layer extreme learning machine

Multiple faults are easily confused with single faults.In order to identify multiple faults more accurately,a highly efficient learning method is proposed based on a double parallel two-hidden-layer extreme learning machine,called DPTELM.The DPT-ELM method is a variant of an extreme learning machine(ELM).There are some issues with ELM.First,achieving a high accuracy requires too many hidden nodes;second,the direct connection between the input layer and the output layer is ignored.Accordingly,to deal with the above-mentioned problems,DPT-ELM extends the single-hidden-layer ELM to a two-hidden-layer ELM,which can achieve a desired performance with fewer hidden nodes.In addition,a direct connection is built between the input layer and the output layer.Since the input layer weights and the thresholds of the two hidden layers are determined randomly,this simplifies the improved model and shortens the calculation time.Additionally,to improve the signal to noise ratio(SNR),an adaptive waveform decomposition(AWD)algorithm is used to denoise the vibration signal.Then,the denoised signal is used to extract the eigenvalues by the time-domain and frequency-domain methods.Finally,the eigenvalues are input to the DPT-ELM classifier.In this paper,two groups of rolling bearing data at different speeds,which were collected from a real experimental platform,are used to test the method.Each set of data includes three single fault states,two complex fault states and a healthy state.The experimental results demonstrate that the DPT-ELM method achieves fast learning speed and a high accuracy.Moreover,based on 10-fold cross-validation,it proves to be an effective method to improve the accuracy with fewer hidden nodes.     

基于改进NSGA-Ⅱ的左转待行区交叉口配时优化控制

为进一步提高道路交叉口综合性能,选取青岛市典型的南京路与江西路交叉口,建立设有左转待行区域的优化模型,利用改进的快速非支配遗传算法对交叉口车辆延误及机动车CO排放两方面进行优化。通过VISSIM软件搭建模型,验证算法有效性。结果表明,改进后算法搜索效率提高了57.4%,多目标优化配时后,车均延误下降了11.7%,CO排放减少了13.5%,平均排队长度降低了11.3%,HC和NOx排放均下降了2.7%。该算法有效地提高了交叉口通行能力和环境效益。     

多元正态分布均值参数估计的Γ-非容许性

本文考虑了正态分布均值参数估计的Γ-非容许性。首先给出了微分不等式△(x)=Ψ(x)sum from i=1 to p(v_i(x_i)(?)_i~(i(1))(x))+sum from i=1 to p(w_i(x)(?)_i~2(x))<0较广的一类解,然后证明了James-Stein型估计量是Γ-非容许的,并给出了改进估计量。     

有机同系物光电子能谱的递变规律（Ⅱ）

首次提出共轭体系光电子能谱的同系递变规律；表示式为：Ｉｐ＝ａ＋ｂ．ｋ＋１／２ｎ＋３并用非共轭体系光电子能谱的数据对该递变规律进行检验。     

Test Studies on Performances of TGP Total Gradation Concrete

The Three Gorges Project （TGP） is the largest water conservancy and hydropower complex in the world, with a concrete consumption of 28 million m^3 in total. For such a significant world-attracting project, first rate quality concrete is needed. Various mechanical and deformation performances of hydraulic mass concrete are determined conventionally by the wet screening method to make small specimens and the test results of the small standard specimens are taken to represent the properties of the mass concrete. However, the quantity of the coarse aggregate after wet screening would be reduced by 30% or so and the gel materials would increase by 20% or so, thus causing significant differences between the properties of the small concrete specimen and that of the total gradation concrete. To well understand the performances of the total gradation concrete of TGP dam, test studies have been performed on the total gradation concrete, including compressive strength, split tensile strength, elastic modulus, ultimate tension, dry shrinkage, self volume defomation, creep, seepage prevention, and so on, and comparison made with the small standard specimens to find out the relationship between them, which have provided scientific gound for the design, operation and safety verification of the TGP dam.