基于神经网络块的混合型方案设计知识库系统

文中详细描述了神经网络块的功能结构，提出了基于神经网络块的混合型专家系统结构框架，阐述了各个模块的基本功能，并成功地将其应用于复杂产品方案设计智能决策支持系统知识库的研制中。

融合注意力机制和卷积神经网络的电网暂态电压稳定评估及可解释性分析

提升复杂多变运行场景下电网稳定评估的时效性和准确性,提出一种融合注意力机制和卷积神经网络(convolutional neural network,CNN)的暂态电压稳定评估及可解释性分析方法。首先,采用卷积块注意力模块(convolutional block attention module,CB AM)提升传统CNN的特征捕获能力,考虑模型特性和网络结构设计CBAMCNN组合模块。其次,建立基于CBAM-CNN的电网暂态电压稳定评估模型,揭示运行工况多变场景下系统关键电气量和稳定状态之间的映射关系。最后,基于沙普利值加性解释(Shapley additive explanations,SHAP)理论提出数据驱动模型评估结果的可解释性分析框架,提炼影响样本稳定状态的主导特征,评估各输入特征量对模型输出结果的贡献程度。在典型受端电网仿真系统中验证了所提稳定评估方法的准确性和可解释性分析方法的有效性。

改进深度学习块卷积神经网络的人脸表情识别

设计一种改进的块卷积神经网络架构,并结合主动形状模型和局部二元模式映射实现人脸表情识别。采用主动形状模型定位人脸关键点,实现人脸姿态校正和感兴趣区域抽取;对校正后的图像进行局部二元模式映射,降低光照干扰;设计改进的卷积神经网络架构,对局部二元模式图像和感兴趣区域两个输入项进行学习和训练,建立分类器并实现人脸表情分类。人脸表情识别实验结果表明,该方法识别率高,运算效率较高。

高校科研能力的协同IWD粗糙集-块神经网络评估模型

针对高校科研能力评估过程中存在的多因素、高非线性特点,经典评估模型主观性较强,导致模型评估准确性不高的问题,提出基于协同智能水滴算法IWD和粗糙集块神经网络RBNN的高校科研能力评估模型。首先,引入智能水滴算法,并针对传统智能水滴算法固定旁域搜索范围不利于提升算法搜索效率的问题,提出一种局部空间自动缩放算法LSAS,该算法根据当前种群最优个体,自动调整下一步搜索空间大小,对进化过程进行指导,提高算法的进化效率;其次,基于粗糙集理论对高校科研能力数据进行特征预处理,简化数据计算量;最后,对块神经网络和粗糙集参数进行编码,并对高校科研能力模型进行评估。仿真结果表明,此评估模型具有较高的准确性和较快的计算效率。

基于神经网络的混凝土联锁块铺面厚度计算

利用BP神经网络计算检验了联锁块铺面块料层的厚度，重点讨论了BP神经网络的拓扑结构和修正算法，通过对检验结果进行分析比较，证明此方法在联锁块铺面块料层的厚度计算及检验中具有很好的实用价值。

基于子块集成神经网络法的PSD背景光补偿

提出一种基于神经网络高精度线性化子块网络集成插值实现光电位置敏感器件(PSD)背景光非线性补偿方法。利用神经网络具有逼近任意非线性函数的特点,通过训练,使神经网络建立在不同背景光下PSD输出与其标准值之间的非线性映射关系,实现PSD全程跟踪补偿。实验结果表明,该方法能有效地消除背景光的影响,在神经网络的输出端得到期望的线性输出。

基于TSSI和STB-CNN的跌倒检测算法

跌倒行为会给老人特别独居老人带来严重伤害,准确识别跌倒并及时报警可以有效降低这种危险。本文提出一种基于树结构骨架图像(Tree Structure Skeleton Image,TSSI)和可学习时空块卷积神经网络(Spatio-temporal Block Convolution Neural Network,STB-CNN)的跌倒检测方法。首先使用三维姿态估计算法提取人体关节点,进而获得骨架序列;然后利用基于深度优先搜索(Depth First Search,DFS)算法将骨架序列编码为TSSI;最后构建由时空差分模块、可学习时空框架和时空多分支卷积模块组成的可学习STB-CNN网络,实现跌倒检测。该方法在公开数据集和自建数据集上进行仿真实验分别取得98.6%和98.3%的准确率,优于其他相关算法。

高斯和声粗糙集BNN光纤管道泄漏监测

为解决长距离管道泄漏监测中干扰多,传统识别算法精度不高的问题,提出一种基于高斯改进和声搜索算法的粗糙集块神经网络。提出一种高斯改进和声搜索算法,利用高斯分布特性对其即兴创作过程进行改进,给出理论分析,保证改进算法的收敛性;利用粗糙集进行采集信号的特征提取预处理,使之适合神经网络处理,简化数据计算量;对粗糙集参数和块神经网络(block neural network,BNN)参数进行编码,利用改进和声搜索算法和实测数据对监控模型进行处理。仿真结果表明,该监控模型可有效对泄漏信号进行识别,精度高,满足实际需要。

α射线露点传感器非线性修正

介绍了采用半导体探测器和温度传感器研制成的α射线露点传感器的工作原理.分析了α射线露点传感器的温度特性,表明测量范围较宽时,传感器的输出易受环境温度的影响,并且成非线性.提出一种基于神经网络高精度线性化子块网络集成插值实现露点传感温度补偿方法.利用神经网络共轭梯度算法具有逼近任意非线性函数的特点,通过训练使神经网络建立在不同环境温度下传感器输出与其实际感受的电压值之间的非线性映射关系,实现α射线露点传感器温度补偿.实验结果表明,该方法不仅能有效地消除温度的影响,而且能在神经网络的输出端得到期望的线性输出.

Automated Building Block Extraction and Building Density Classification Using Aerial Imagery and LiDAR Data

This paper examines the utility of high-resolution airborne RGB orthophotos and LiDAR data for mapping residential land uses within the spatial limits of suburb of Athens, Greece. Modem remote sensors deliver ample information from the AOI （area of interest） for the estimation of 2D indicators or with the inclusion of elevation data 3D indicators for the classification of urban land. In this research, two of these indicators, BCR （building coverage ratio） and FAR （floor area ratio） are automatically evaluated. In the pre-processing step, the low resolution elevation data are fused with the high resolution optical data through a mean-shift based discontinuity preserving smoothing algorithm. The outcome is an nDSM （normalized digital surface model） comprised of upsampled elevation data with considerable improvement regarding region filling and ＂straightness＂ of elevation discontinuities. Following this step, a MFNN （multilayer feedforward neural network） is used to classify all pixels of the AOI into building or non-building categories. The information derived from the BCR and FAR building indicators, adapted to landscape characteristics of the test area is used to propose two new indices and an automatic post-classification based on the density of buildings.

Integrating artificial neural networks and geostatistics for optimum 3D geological block modeling in mineral reserve estimation:A case study

In this research, a method called ANNMG is presented to integrate Artificial Neural Networks and Geostatistics for optimum mineral reserve evaluation. The word ANNMG simply means Artificial Neural Network Model integrated with Geostatiscs, In this procedure, the Artificial Neural Network was trained, tested and validated using assay values obtained from exploratory drillholes. Next, the validated model was used to generalize mineral grades at known and unknown sampled locations inside the drilling region respectively. Finally, the reproduced and generalized assay values were combined and fed to geostatistics in order to develop a geological 3D block model. The regression analysis revealed that the predicted sample grades were in close proximity to the actual sample grades, The generalized grades from the ANNMG show that this process could be used to complement exploration activities thereby reducing drilling requirement. It could also be an effective mineral reserve evaluation method that could oroduce optimum block model for mine design.

Prediction of blast boulders in open pit mines via multiple regression and artificial neural networks

The most important objective of blasting in open pit mines is rock fragmentation.Prediction of produced boulders(oversized crushed rocks) is a key parameter in designing blast patterns.In this study,the amount of boulder produced in blasting operations of Golegohar iron ore open pit mine,Iran was predicted via multiple regression method and artificial neural networks.Results of 33 blasts in the mine were collected for modeling.Input variables were:joints spacing,density and uniaxial compressive strength of the intact rock,burden,spacing,stemming,bench height to burden ratio,and specific charge.The dependent variable was ratio of boulder volume to pattern volume.Both techniques were successful in predicting the ratio.In this study,the multiple regression method was superior with coefficient of determination and root mean squared error values of 0.89 and 0.19,respectively.

Design of motion control system of pipeline detection AUV

A great number of pipelines in China are in unsatisfactory condition and faced with problems of corrosion and cracking,but there are very few approaches for underwater pipeline detection.Pipeline detection autonomous underwater vehicle(PDAUV) is hereby designed to solve these problems when working with advanced optical,acoustical and electrical sensors for underwater pipeline detection.PDAUV is a test bed that not only examines the logical rationality of the program,effectiveness of the hardware architecture,accuracy of the software interface protocol as well as the reliability and stability of the control system but also verifies the effectiveness of the control system in tank experiments and sea trials.The motion control system of PDAUV,including both the hardware and software architectures,is introduced in this work.The software module and information flow of the motion control system of PDAUV and a novel neural network-based control(NNC) are also covered.Besides,a real-time identification method based on neural network is used to realize system identification.The tank experiments and sea trials are carried out to verify the feasibility and capability of PDAUV control system to complete underwater pipeline detection task.