A Novel On-Site-Real-Time Method for Identifying Characteristic Parameters Using Ultrasonic Echo Groups and Neural Network

On-site and real-time non-destructive measurement of elastic constants for materials of a component in a in-service structure is a challenge due to structural complexities,such as ambiguous boundary,variable thickness,nonuniform material properties.This work develops for the first time a method that uses ultrasound echo groups and artificial neural network(ANN)for reliable on-site real-time identification of material parameters.The use of echo groups allows the use of lower frequencies,and hence more accommodative to structural complexity.To train the ANNs,a numerical model is established that is capable of computing the waveform of ultrasonic echo groups for any given set of material properties of a given structure.The waveform of an ultrasonic echo groups at an interest location on the surface the structure with material parameters varying in a predefined range are then computed using the numerical model.This results in a set of dataset for training the ANN model.Once the ANN is trained,the material parameters can be identified simultaneously using the actual measured echo waveform as input to the ANN.Intensive tests have been conducted both numerically and experimentally to evaluate the effectiveness and accuracy of the currently proposed method.The results show that the maximum identification error of numerical example is less than 2%,and the maximum identification error of experimental test is less than 7%.Compared with currently prevailing methods and equipment,the proposefy the density and thickness,in addition to the elastic constants.Moreover,the reliability and accuracy of inverse prediction is significantly improved.Thus,it has broad applications and enables real-time field measurements,which has not been fulfilled by any other available methods or equipment.

Optimal Deep Convolutional Neural Network for Vehicle Detection in Remote Sensing Images

Object detection(OD)in remote sensing images(RSI)acts as a vital part in numerous civilian and military application areas,like urban planning,geographic information system(GIS),and search and rescue functions.Vehicle recognition from RSIs remained a challenging process because of the difficulty of background data and the redundancy of recognition regions.The latest advancements in deep learning(DL)approaches permit the design of effectual OD approaches.This study develops an Artificial Ecosystem Optimizer with Deep Convolutional Neural Network for Vehicle Detection(AEODCNN-VD)model on Remote Sensing Images.The proposed AEODCNN-VD model focuses on the identification of vehicles accurately and rapidly.To detect vehicles,the presented AEODCNN-VD model employs single shot detector(SSD)with Inception network as a baseline model.In addition,Multiway Feature Pyramid Network(MFPN)is used for handling objects of varying sizes in RSIs.The features from the Inception model are passed into theMFPNformultiway andmultiscale feature fusion.Finally,the fused features are passed into bounding box and class prediction networks.For enhancing the detection efficiency of the AEODCNN-VD approach,AEO based hyperparameter optimizer is used,which is stimulated by the energy transfer strategies such as production,consumption,and decomposition in an ecosystem.The performance validation of the presentedmethod on benchmark datasets showed promising performance over recent DL models.

Identification of pulse-like ground motions using artificial neural network

For more than 20 years,the concept of near-fault pulse-like ground motion has been a topic of great interest due to its distinct characteristics,particularly due to directivity or fling effects,which are hugely influenced by the rupture mechanism.These unexpected characteristics,along with their effective frequency,energy rate,and damage indices,create a near-fault,pulse-like ground motion capable of causing severe damage to structures.One of the most common approaches for identifying these ground motions is done by conducting wavelet decomposition of the ground motion time history to extract a pulse signal and eventually categorize an earthquake by comparing the original signal to the residual one.However,to overcome the intensive calculations required in this approach,this study proposes using artificial neural networks to identify pulse-like ground motions through classification to predict their pulse period by means of regression analysis.Furthermore,the study is intended to evaluate the reliability and accuracy of various artificial neural networks in identifying pulse-like ground motions and predicting their pulse periods.In general,the results of the study have shown that the artificial neural network can identify pulse-like earthquakes and reliably predict their pulse period.

Comparing the efficiency of artificial neural networks in sEMG-based simultaneous and continuous estimation of hand kinematics

Surface Electromyography(sEMG)plays a key role in many applications such as control of Human-Machine Interfaces(HMI)and neuromusculoskeletal modeling.It has strongly nonlinear relations to joint kinematics and reflects the subjects’intention in moving their limbs.Such relations have been traditionally examined by either integrated biomechanics and multi-body dynamics or gesture-based classification approaches.However,these methods have drawbacks that limit their usability.Different from them,joint kinematics can be continuously reconstructed from sEMG via estimation approaches,for instance,the Artificial Neural Networks(ANNs).The Comparison of different ANNs used in different studies is difficult,and in many cases,impossible.The current study focuses on fairly evaluating four types of ANN over the same dataset and conditions in proportional and simultaneous estimation of 15 hand joint angles from 10 sEMG signals.The presented ANNs are Feedforward,Cascade-Forward,Radial Basis Function(RBFNN),and Generalized Regression(GRNN).Each ANN is applied to its special parametric study.All the methods efficiently solved the regression problem of the complex multi-input multi-output bio-system.The RBFNN has the best performance over the others with a 79.80%mean correlation coefficient over all joints,and its accuracy reaches as high as 92.67%in some joints.Interestingly,the highest accuracy over individual joints is 93.46%,which is achieved via the GRNN.The good accuracy suggests that the proposed approaches can be used as alternatives to the previously adopted ones and can be employed effectively to synchronously control multi-degrees of freedom HMI and for general multi-joint kinematics estimation purposes.

Implementation of Radial Basis Function Artificial Neural Network into an Adaptive Equivalent Consumption Minimization Strategy for Optimized Control of a Hybrid Electric Vehicle

Continued increases in the emission of greenhouse gases by passenger vehicles have accelerated the production of hybrid electric vehicles. With this increase in production, there has been a parallel demand for continuously improving strategies of hybrid electric vehicle control. The goal of an ideal control strategy is to maximize fuel economy while minimizing emissions. Methods exist by which the globally optimal control strategy may be found. However, these methods are not applicable in real-world driving applications since these methods require a priori knowledge of the upcoming drive cycle. Real-time control strategies use the global optimal as a benchmark against which performance can be evaluated. The goal of this work is to use a previously defined strategy that has been shown to closely approximate the global optimal and implement a radial basis function (RBF) artificial neural network (ANN) that dynamically adapts the strategy based on past driving conditions. The strategy used is the Equivalent Consumption Minimization Strategy (ECMS), which uses an equivalence factor to define the control strategy and the power train component torque split. An equivalence factor that is optimal for a single drive cycle can be found offline with a priori knowledge of the drive cycle. The RBF-ANN is used to dynamically update the equivalence factor by examining a past time window of driving characteristics. A total of 30 sets of training data (drive cycles) are used to train the RBF-ANN. For the majority of drive cycles examined, the RBF-ANN implementation is shown to produce fuel economy values that are within ±2.5% of the fuel economy obtained with the optimal equivalence factor. The advantage of the RBF-ANN is that it does not require a priori drive cycle knowledge and is able to be implemented in real-time while meeting or exceeding the performance of the optimal ECMS. Recommendations are made on how the RBF-ANN could be improved to produce better results across a greater array of driving conditions.

Artificial Neural Network Method Based on Expert Knowledge and Its Application to Quantitative Identification of Potential Seismic Sources

In this paper,an approach is developed to optimize the quality of the training samples in the conventional Artificial Neural Network(ANN)by incorporating expert knowledge in the means of constructing expert-rule samples from rules in an expert system,and through training by using these samples,an ANN based on expert-knowledge is further developed.The method is introduced into the field of quantitative identification of potential seismic sources on the basis of the rules in an expert system.Then it is applied to the quantitative identification of the potential seismic sources in Beijing and its adjacent area.The result indicates that the expert rule based on ANN method can well incorporate and represent the expert knowledge in the rules in an expert system,and the quality of the samples and the efficiency of training and the accuracy of the result are optimized.

Study of Synthesis Identification in Cutting Process with Fuzzy Neural Network

With the development of industrial production modernization, FMS and CIMS will become more and more popularized. For its control system is increasingly modeled, intellectualized and automatized, in order to raise the reliability and stability in the manufacturing process, the comprehensive monitoring and diagnosis aimed at cutting tool wear and chatter become more and more important and get rapid development. The paper tried to discuss of the intellectual status identification method based on acoustics-vibra characteristics of machining process, and propose that the working conditions may be taken as a core, complex fuzzy inference neural network model based on artificial neural network theory, and by using various kinds of modernized signal processing method to abstract enough characteristics parameters which will reflect overall processing status from machining acoustics-vibra signal as information source, to identify different working condition, and provide guarantee for automation and intelligence in machining process. The complex network is composed of NNw and NNs, Each of them is composed of BP model network, NNw is weight network at rule condition, NNs is decision-making network of each status. Y out is final inference result which is to take subordinate degree as weight from NNw, to weight reflecting result from NNs and obtain status inference of monitoring system. In the process of machining, the acoustics-vibor signal were gotten by the acoustimeter and the acceleration piezoelectricity detector, the date is analysed by the signal processing software in time and frequency domain, then form multi feature parameter vector of criterion pattern samples for the different stage of cutting chatter and acoustics-vibra multi feature parameter vector. The vector can give a accurate and comprehensive description for the cutting process, and have the characteristic which are speediness of time domain and veracity of frequency domain. The research works have been practically applied in identification of tool wear, cutting chatter, experiment results showed that it is practicable to identify the cutting chatter based on fuzzy neural network, and the new method based on fuzzy neural network can be applied to other state identification in machining process.

Simultaneous Identification of Thermophysical Properties of Semitransparent Media Using a Hybrid Model Based on Artificial Neural Network and Evolutionary Algorithm

A hybrid identification model based on multilayer artificial neural networks(ANNs) and particle swarm optimization(PSO) algorithm is developed to improve the simultaneous identification efficiency of thermal conductivity and effective absorption coefficient of semitransparent materials.For the direct model,the spherical harmonic method and the finite volume method are used to solve the coupled conduction-radiation heat transfer problem in an absorbing,emitting,and non-scattering 2D axisymmetric gray medium in the background of laser flash method.For the identification part,firstly,the temperature field and the incident radiation field in different positions are chosen as observables.Then,a traditional identification model based on PSO algorithm is established.Finally,multilayer ANNs are built to fit and replace the direct model in the traditional identification model to speed up the identification process.The results show that compared with the traditional identification model,the time cost of the hybrid identification model is reduced by about 1 000 times.Besides,the hybrid identification model remains a high level of accuracy even with measurement errors.

An Intelligent Identification Approach of Assembly Interface for CAD Models

Kinematic semantics is often an important content of a CAD model(it refers to a single part/solid model in this work)in many applications,but it is usually not the belonging of the model,especially for the one retrieved from a common database.Especially,the effective and automatic method to reconstruct the above information for a CAD model is still rare.To address this issue,this paper proposes a smart approach to identify each assembly interface on every CAD model since the assembly interface is the fundamental but key element of reconstructing kinematic semantics.First,as the geometry of an assembly interface is formed by one or more adjacent faces on each model,a face-attributed adjacency graph integrated with face structure fingerprint is proposed.This can describe each CAD model as well as its assembly interfaces uniformly.After that,aided by the above descriptor,an improved graph attention network is developed based on a new dual-level anti-interference filtering mechanism,which makes it have the great potential to identify all representative kinds of assembly interface faces with high accuracy that have various geometric shapes but consistent kinematic semantics.Moreover,based on the abovementioned graph and face-adjacent relationships,each assembly interface on a model can be identified.Finally,experiments on representative CAD models are implemented to verify the effectiveness and characteristics of the proposed approach.The results show that the average assembly-interface-face-identification accuracy of the proposed approach can reach 91.75%,which is about 2%–5%higher than those of the recent-representative graph neural networks.Besides,compared with the state-of-the-art methods,our approach is more suitable to identify the assembly interfaces(with various shapes)for each individual CAD model that has typical kinematic pairs.

多源车载数据驱动的地铁轨道不平顺智能识别方法

针对轨道不平顺检测成本高与时效性低等不足,从车辆动态响应与轨道不平顺之间的相关性为切入点,提出一种多源车载数据驱动的轨道不平顺智能识别方法。首先,建立地铁车辆系统动力学模型,获取车辆振动与运动姿态响应数据;其次,通过相关性分析算法,选取强相关性数据,制作网络模型数据集;最后,建立卷积神经网络-长短期记忆网络(CNN-LSTM),通过粒子群算法优化(PSO)神经网络模型参数,建立PSO-CNN-LSTM模型,实现对轨道不平顺的识别拟合。研究结果表明:在车辆动态响应信号中,与横向信号与轨道不平顺之间的相关性相比,垂向信号的更强,同时,车体的运动姿态如车体点头角速度与不平顺有明显的相关性。所提出的PSO-CNN-LSTM模型轨道垂向与横向不平顺识别拟合度分别达0.92和0.76。与经典的全连接神经网络FCNN和支持向量机SVR相比,PSO-CNN-LSTM有更好的识别效果与时效性。

智能汽车轨迹跟踪MPC-RBF-SMC协同控制策略研究

针对自动驾驶车辆行驶过程中模型失配以及外部环境干扰导致车辆轨迹跟踪环节精确性不高的问题,提出了一种结合车辆运动学模型预测控制(MPC)、径向基(RBF)神经网络和滑模控制(SMC)的轨迹跟踪控制策略。通过建立车辆运动学MPC模型计算当前状态车辆期望横摆角速度,并将其与实际横摆角速度的偏差输入RBF-SMC控制器,利用RBF快速逼近非线性模型的特点,结合滑模控制输出前轮转角,实现车辆的横向轨迹跟踪控制。仿真结果表明,与传统的控制器相比,该方法轨迹跟踪精度显著提高,并在不同行驶工况下表现出较好的鲁棒性。

不同产地葛根药材的高光谱结合人工神经网络鉴别

采用高光谱结合人工神经网络(ANN)方法建立了不同产地葛根药材的鉴别方法。采集6种不同产地葛根药材的高光谱数据,使用Savitzky-Golay平滑滤波对原始光谱数据预处理,结合人工神经网络方法建立葛根产地鉴别模型。结果表明,与未经预处理的光谱数据模型准确率相比,Savitzky-Golay平滑滤波后建立的ANN模型识别测试集分类准确率达到99.00%。因此,高光谱技术结合人工神经网络能够实现快速、准确地鉴别葛根产地,是一种很有前景的葛根药材鉴别方法。

基于ABC-BP神经网络的地铁盾构隧道地层识别及复合比预测

为研究盾构掘进过程中掘进参数与地层情况的关联性,建立盾构掘进过程中的机-岩关系,依托南京地铁6号线某盾构施工区间数据进行复合地层下掘进参数的统计分析。首先,利用掘进参数与地层的相关性,采用人工蜂群算法优化的BP神经网络,建立可根据掘进参数识别开挖面地层并描述复合地层组合情况的ABC-BP神经网络模型;然后,针对盾构区间进行地层识别和区间内2种复合地层的复合比预测。结果表明:1)盾构掘进参数的波动范围与均值随开挖面所处地层变化,且依地层不同呈现一定规律性;2)地层类别预测结果表明,模型对上软下硬地层、中风化泥质砂岩、粉质黏土的识别召回率分别为94.1%、96.6%、96%,总体识别准确率为95%;3)针对复合比的预测结果表明,相较于其他机器学习模型,ABC-BP模型的平均绝对误差、均方根误差均减小且样本回归值提升,在预测精度和预测稳定性方面具有一定的优越性。

Path Planning for AUVs Based on Improved APF-AC Algorithm

With the increase in ocean exploration activities and underwater development,the autonomous underwater vehicle(AUV)has been widely used as a type of underwater automation equipment in the detection of underwater environments.However,nowadays AUVs generally have drawbacks such as weak endurance,low intelligence,and poor detection ability.The research and implementation of path-planning methods are the premise of AUVs to achieve actual tasks.To improve the underwater operation ability of the AUV,this paper studies the typical problems of path-planning for the ant colony algorithm and the artificial potential field algorithm.In response to the limitations of a single algorithm,an optimization scheme is proposed to improve the artificial potential field ant colony(APF-AC)algorithm.Compared with traditional ant colony and comparative algorithms,the APF-AC reduced the path length by 1.57%and 0.63%(in the simple environment),8.92%and 3.46%(in the complex environment).The iteration time has been reduced by approximately 28.48%and 18.05%(in the simple environment),18.53%and 9.24%(in the complex environment).Finally,the improved APF-AC algorithm has been validated on the AUV platform,and the experiment is consistent with the simulation.Improved APF-AC algorithm can effectively reduce the underwater operation time and overall power consumption of the AUV,and shows a higher safety.

双层次装配语义智能识别与设置方法

作为装配体模型中的重要内容,即装配语义,目前大多采用人工交互的方式进行设置,过程往往费时低效.为解决此问题,提出一种双层次装配语义智能识别与设置方法.首先,改进现有的图注意力网络,将其拓展为双层次识别网络,实现透过各种几何形状,智能识别每个零件模型表面的典型运动副接口;其次,改进现有反向传播人工神经网络的网络结构以提高网络性能,智能识别每个零件模型所有运动副接口上蕴含的装配约束类型及关联的几何实体;最后,基于上述识别的信息,任意2个零件模型之间自动搜索配对的运动副接口和装配约束几何实体,并快速且半自动地设置它们之间完整的装配语义.为有效地支持上述网络模型训练,构建了一个包含2787个CAD零件模型的数据集.实验表明,该方法对运动副接口和装配约束的类型及关联几何实体识别的准确率均超过93.0%.同时,与现有的相关工作相比,所提方法具有有效地适用于快速设置各种装配体模型其装配语义的优势和潜力.

无人车目标识别主干网络技术特点对比分析

目标识别是无人车自动驾驶视觉感知模块的核心技术之一。当前,目标识别主要依靠主干网络提取特征,进而对目标进行分类与回归。通常情况下,无人车嵌入式计算平台的计算与存储能力有限,为了降低主干网络的算力与存储量,提升无人车的计算速度与效率,对目标分类任务的主干网络进行综合比较分析。围绕卷积核、感受野、池化层、全连接层、激活函数等,以cifar10和cifar100为实验数据,从理论分析与数据实践层面,对主干网络算子的选择与网络搭建进行分析对比,总结、归纳特征提取主干网络搭建的主要思路与做法。结果表明,该分析结论对目标分类主干网络在嵌入式无人车系统中的应用具有一定的理论指导与参考价值。

基于变权模糊综合法与人工神经网络的地铁车辆转向架系统健康状态评价

[目的]相较于现代地铁车辆普遍采用的计划修和故障修的维修模式,状态修可以在优化维修策略和成本的同时,把握车辆系统的健康状态和运行情况。为实现状态修,需对车辆系统健康状态进行准确评价。[方法]以地铁车辆转向架系统为对象,对其健康状态的评价方法进行深入研究。依据转向架系统组成具有层次性的特点,以劣化度为依据,将层次分析法和变权理论相结合,根据模糊综合评判思路,建立基于劣化度的地铁车辆转向架健康状态变权模糊综合评价模型,提出建模流程;通过选取的地铁车辆转向架系统健康状态评价指标对其进行健康状态评估,获得样本数据;利用样本数据对BP神经网络、支持向量机和随机森林三种不同的人工神经网络进行训练,利用实际测试数据判断三种不同类型人工神经网络的评价效果。[结果及结论]随机森林模型对地铁车辆转向架系统健康状态的识别能力最强,可实现对地铁车辆转向架系统的智能化健康评估。