基于模拟退火优化BP神经网络的变形监测数据预测方法

针对BP神经网络模型用于变形监测数据处理时容易陷入局部极小值并且收敛速度慢的问题，提出一种基于模拟退火(Simulated Annealing,SA)算法优化BP神经网络的建筑物变形预测方法，利用SA的全局寻优能力对BP神经网络的模型参数进行优化，使参数迭代过程始终保持较高的“温度”和“能量”，从而确保BP神经网络能够得到全局最优解的同时具备较高的预测精度和收敛速度。采用实际算例对所提SA-BP方法在低信噪比和小样本条件下的预测精度进行验证，结果表明所提方法相对于传统BP神经网络法和小波方法能够获得更高的预测精度，并且在小样本和低信噪比条件下优势更加明显。     

Performance-based modelling of long-term deterioration to support rehabilitation and investment decisions in drinking water distribution systems

Managing the urban drinking water system in the long term in order to maintain system performance can be challenging due to the difficulty of modelling future deterioration of the networks. This paper establishes a methodology for cohort survival models where historical (empirical) data on decommissioning ages of pipes are used to calibrate survival functions of pipe cohorts according to service level targets. The benefit of the approach is that remaining useful life of pipes, future renewal rates and investment needs can be governed by a required level of service in the network. A case study shows how the methodology can be applied to a cohort of drinking water pipes to create a ‘calibration curve’, which is a survival function calibrated with empirical data.     

基于并行多通道卷积长短时记忆网络的轴承寿命预测方法

在预测轴承剩余使用寿命时，数据间的时序特性是一个可以利用的重要隐藏信息。为了更好地提取具有时序信息的特征用于预测，提出了一种基于并行多通道卷积长短时记忆网络（PMCCNN-LSTM）的剩余使用寿命预测模型。该模型主要由两部分组成：前端为并行多通道卷积网络（PMCCNN），提取信号特征，挖掘数据的时序特性，并采用逐层训练和微调的方式提升参数的收敛性；后端为长短时记忆（LSTM）网络，基于特征进行剩余使用寿命预测，并采用加权平均的方法对预测结果进行平滑处理。在一个轴承加速寿命实验的公开数据集上使用留一法验证了该模型的准确性，实验结果表明：所提模型的平均误差与最大误差分别比传统的卷积神经网络（CNN）低23.38%和15.84%，比传统的LSTM低24.14%和19.01%，比卷积长短时记忆网络（CNN-LSTM）低30.32%和23.09%。     

红外菲涅尔透镜的注射超声辅助成型优化

为了提升聚合物红外菲涅尔透镜的光学性能,以其表面微沟槽的成型质量为目标,提出了一种高效的注射超声辅助成型方法,并对工艺参数进行了综合质量优化。首先分析了超声振动对聚合物的加热和加压效应,设计了一套一模两腔的对比试验模具;接着以红外菲涅尔透镜的调制传递函数MTF和齿形平均高度h为优化质量目标,设计了四步骤的多目标优化流程,通过试验设计、基于BP神经网络的质量目标与注射工艺参数关系建模、基于NSGA-Ⅱ的多目标优化和试验验证进行工艺参数的综合优化。实验结果表明:该多目标优化流程具有很高的精度,MTF和h的平均预测误差MPE分别为4.16%和3.32%;注射超声辅助成型的菲涅尔透镜微沟槽具有更高的复制质量,其齿沟槽平均高度h增加了15.6%,且h值的波动量随着h值的增大而增大,MTF值受齿高h均匀性的影响大于齿高h对其的影响。     

Performance analysis of large-scale MIMO system for wireless backhaul network

In this paper, we present a performance analysis of large-scale multi-input multi-output (MIMO) systems for wireless backhaul networks. We focus on fully connected N nodes in a wireless meshed and multi-hop network topology. We also consider a large number of antennas at both the receiver and transmitter. We investigate the transmission schemes to support fully connected N nodes for half-duplex and full-duplex transmission, analyze the achievable ergodic sum rate among N nodes, and propose a closed-form expression of the achievable ergodic sum rate for each scheme. Furthermore, we present numerical evaluation results and compare the resuts with closed-form expressions.     

Reduced basis method for managed pressure drilling based on a model with local nonlinearities

To circumvent restrictions of conventional drilling methods, such as slow control actions and inability to drill depleted reservoirs, a drilling method called managed pressure drilling (MPD) has been developed. In MPD, single-phase flow processes can be modeled as a feedback interconnection of a high-order linear system and a low-order nonlinear system. These nonlinearities appear locally both inside and at the boundaries of the computational domain. To obtain a fast simulation platform for real-time purposes (eg, online model-based controller implementation), model order reduction is required for MPD. However, the local nonlinearities render applying model order reduction techniques challenging. In this study, a new approach is proposed to deal with such nonlinearities within the reduced basis (RB) context and it is successfully tested on a model for MPD. Contrary to the classical RB technique, the proposed approach not only does not generate nonphysical spikes at the locations of these local nonlinearities but also yields high speedup factors. The obtained reduced-order model can be used for efficient online simulation and controller design for drilling systems with MPD.     

基于深度学习的传感器优化布置方法

针对传感器优化布置(optimal sensor placement,简称OSP)问题,提出了一种新的使用深度神经网络的解决方案,并以简化的桥梁形状的桁架结构中的振动测试传感器优化为例进行了验证。首先,选择一种传统的传感器优化布置方法,对自动化生成的大量不同的桁架结构分别进行传感器优化布置计算,将所得优化布置结果在进行数据预处理后构建出深度学习方法所需要的训练集与验证集;其次,使用Python语言和深度学习框架TensorFlow设计实现与本研究问题适配的深度神经网络模型并训练;然后,随机生成了新的桁架结构参数;最后,将深度神经网络输出的传感器布置结果和传统方法的计算结果进行了比较,验证了本研究方法的有效性以及在速度上、可移植性与可扩展性方面的性能优势。     

基于多元神经网络融合的分布式资源空间文本分类研究

针对实体产业对科技资源的服务需求,以服务效应作为资源文本分类标准,提出一种基于多元神经网络融合的分布式资源空间文本分类模型。设计了包含词嵌入层、卷积层、双向门控循环单元层、注意力机制层和softmax层的多元神经网络通路;在此基础上采用基于需求—效应—资源分类策略,完成了从定性科技资源需求到定量资源服务效应求解,再到定性科技资源输出的映射变换,重点解决了分布式科技资源局部和全局语义特征形式多样、文本长距离依赖特征显著、重要资源信息难以准确识别的问题,进而从分布式科技资源空间中快速准确地获取效应知识,提升实体产业产品研发效率和创新能力;通过万方专利科技资源数据集验证了所提方法的可行性和有效性,为更加全面地挖掘资源文本特征和按需服务实体产业提供了一种新的思路和手段。     

基于双应力加速寿命试验的关节轴承寿命预测与可靠性分析

自润滑关节轴承寿命主要是由衬垫的磨损性能决定的,但衬垫的磨损一般是非线性的,使得寿命难以预测。采用同时改变载荷和摆频2种应力的方法进行加速寿命试验,建立以pv值、磨损量退化数据为输入参数,寿命值为输出参数的灰色神经网络预测模型。经验证该预测模型对关节轴承寿命预测的最大误差仅为7.33%,平均误差仅为3.892%。对不同加速应力下自润滑关节轴承可靠性进行评估,结果表明,关节轴承的可靠性在L_(10)(可靠度为90%时的寿命)之前下降趋势缓慢,然后迅速下降,pv值越大可靠性下降越迅速;随着pv值的增大,关节轴承寿命近似呈指数下降,经验证可用逆幂率加速模型反映二者关系。