Adaptive multiscale convolutional neural network model for chemical process fault diagnosis

Intelligent fault recognition techniques are essential to ensure the long-term reliability of manufacturing.Due to the variations in material,equipment and environment,the process variables monitored by sensors contain diverse data characteristics at different time scales or in multiple operating modes.Despite much progress in statistical learning and deep learning for fault recognition,most models are constrained by abundant diagnostic expertise,inefficient multiscale feature extraction and unruly multimode condition.To overcome the above issues,a novel fault diagnosis model called adaptive multiscale convolutional neural network(AMCNN)is developed in this paper.A new multiscale convolutional learning structure is designed to automatically mine multiple-scale features from time-series data,embedding the adaptive attention module to adjust the selection of relevant fault pattern information.The triplet loss optimization is adopted to increase the discrimination capability of the model under the multimode condition.The benchmarks CSTR simulation and Tennessee Eastman process are utilized to verify and illustrate the feasibility and efficiency of the proposed method.Compared with other common models,AMCNN shows its outstanding fault diagnosis performance and great generalization ability.

An Intelligent Neural Networks System for Adaptive Learning and Prediction of a Bioreactor Benchmark Process

适应学习和一个高度非线性、变化时间的生物反应器基准过程的预言用神经原线，为在 G2 实时聪明的环境开发并且部署神经网络的一个图形的工具箱，和新修改 Broyden 被学习，弗莱彻， Goldfarb ，并且 Shanno ( BFGS )伪--牛顿算法。为神经网络被开发并且由介绍学习率到完整的存储器 BFGS 算法的一个新搜索方法嵌进神经原线的背繁殖(BP ) 的适应学习的修改 BFGS 算法。模拟结果证明适应学习和神经网络系统能快速追踪的预言生物反应器的变化时间、非线性的行为。

Adaptive control of machining process based on extended entropy square error and wavelet neural network

Combining information entropy and wavelet analysis with neural network,an adaptive control system and an adaptive control algorithm are presented for machining process based on extended entropy square error(EESE)and wavelet neural network(WNN).Extended entropy square error function is defined and its availability is proved theoretically.Replacing the mean square error criterion of BP algorithm with the EESE criterion,the proposed system is then applied to the on-line control of the cutting force with variable cutting parameters by searching adaptively wavelet base function and self adjusting scaling parameter,translating parameter of the wavelet and neural network weights.Simulation results show that the designed system is of fast response,non-overshoot and it is more effective than the conventional adaptive control of machining process based on the neural network.The suggested algorithm can adaptively adjust the feed rate on-line till achieving a constant cutting force approaching the reference force in varied cutting conditions,thus improving the machining efficiency and protecting the tool.

Adaptation of Video Services in ATM Networks

Transmission and switching of video services will be the important services provided bythe information superhighway,in which ATM(Asynchronous Transfer Mode)will be one ofthe key techniques.This paper discusses the adaptation of video services in ATM networksand presents a scheme of implementation.As a component of an ATM network supported bythe High Technology Research and Development Programme of China,the circuit designedwith the principle works successfully.

基于偏正结构表示的加工命名实体识别方法

制造企业积累大量的零件加工经验多以文本形式存在,如何从文本中挖掘出高质量的零件加工知识是个尚待解决的问题。针对待识别实体存在的偏正结构特征,导致实体边界界定模糊的问题,提出一种多网络协调的中文命名实体识别方法。在BERT生成字向量的过程中,通过领域自适应方法,提高字向量对工艺实体的表征能力,同时,在BiLSTM-CRF模型中引入注意力机制和多门控制的混合专家网络捕获上下文特征与实体信息。实验表明,较于当前主流的命名实体识别模型,该文提出的方法对机械零件加工实体识别的F1值达到80.15%,取得优于其他模型的最好性能。

基于依赖类型剪枝的双特征自适应融合网络用于方面级情感分析

现有的模型将基于依赖树的图神经网络用于方面级情感分析,一定程度上提升了模型的分类性能。然而,由于依赖解析技术的限制,语法解析结果的不精确导致依赖树存在大量噪声,使得模型的性能提升有限。此外,一些句子本身并不符合标准的句法结构。以往的研究以同样的置信度利用句法信息和语义信息,没有充分考虑它们对于确定方面词极性的贡献的不同,导致模型在相应的数据集上性能较差。为了克服这些困难,文中提出了一种基于依赖类型剪枝的双特征自适应融合网络。具体来说,该模型使用一种新型的混合方法,命名为依赖关系类型剪枝和邻接矩阵平滑,来缓解句法解析产生的噪声。此外,该模型通过双特征自适应融合模块充分考虑句子的句法信息的可用程度,以一种更灵活的方式将句法特征和语义特征结合起来用于方面级情感分析。在5个公开可用的数据集上进行广泛的实验,结果证明了该方法明显优于基线模型。

基于知识与AW-ESN融合的烧结过程FeO含量预测

氧化亚铁(FeO)含量是衡量烧结矿强度和还原性的重要指标,烧结过程FeO含量的实时准确预测对于提升烧结质量、优化烧结工艺具有重要意义.然而烧结过程热状态参数缺失、过程参数波动频繁给FeO含量的高精度预测带来巨大的挑战,为此,提出一种基于知识与变权重回声状态网络融合(Fusion of data-knowledge and adaptive weight echo state network, DK-AWESN)的烧结过程FeO含量预测方法.首先,针对烧结过程热状态参数缺失的问题,建立烧结料层最高温度分布模型,实现基于料层温度分布特征的FeO含量等级划分;其次,针对烧结过程参数波动频繁的问题,提出基于核函数高维映射的多尺度数据配准方法,有效抑制离群点的影响,提升建模数据的质量;最后,针对烧结过程数据驱动模型缺乏机理认知致使模型预测精度不高的问题,将过程数据中提取得到的FeO含量等级知识与AW-ESN (Adaptive weight echo state network)结合,建立DK-AWESN模型,有效提升复杂工况下FeO含量的预测精度.现场工业数据试验表明,所提方法能实时准确地预测烧结过程FeO含量,为烧结过程的智能化调控提供实时有效的FeO含量反馈信息.

健壮且自适应的学习型近似查询处理方法研究

由于在大规模数据集上执行精确查询耗时较长,因此近似查询处理(AQP)技术常被用于在线分析处理,目的是以较短的交互延迟返回查询结果,并尽可能地降低查询误差。现有的学习型AQP方法与底层数据解耦,将I/O密集型计算转化为CPU密集型计算,但是由于计算资源的限制,该类方法通常基于随机的数据样本进行模型训练,此类训练数据会引起稀有群组缺失问题,导致模型预测准确性不高。针对上述问题,提出一种基于分层样本学习的混合型和积网络模型,并基于该模型设计一种AQP框架。分层样本能够有效避免稀有群组缺失现象,基于该样本训练的模型预测准确性大幅提升。此外,针对数据动态更新的情况,提出一种模型自适应更新策略,使得模型能够及时检测数据偏移现象并自适应地执行更新。实验结果表明,与基于抽样和基于机器学习的AQP方法相比,该模型在真实数据集和合成数据集上的平均相对误差分别约降低18.3%和2.2%,在数据动态更新的场景下,其准确性和查询时延均呈现出良好的稳定性。

基于数据驱动的离心泵轴承特征分析及寿命预测

离心泵是工业中能量转换和流体输送的核心设备,其部件滚动轴承的可靠性对整个机组的安全运行尤为关键。为了解决目前滚动轴承寿命预测问题,对滚动轴承剩余寿命的最佳预测方案进行了研究。首先,从数据驱动和试验出发,利用试验台采集所得的离心泵轴承正常及故障状态下的数据,分析了时域、频域、时频域各特征在不同工况中的表现差异,发现了时域特征、频域特征、小波包分解能量特征、完全自适应噪声完备集合经验模态分解(CEEMDAN)能量特征可以捕捉到不同工况下的故障信息;然后,以单调性、趋势性指标加权分数为依据,结合特征的敏感性分析结果,优选出了轴承在全寿命周期中表现突出的12个特征,经核主成分分析(KPCA)-长短期记忆网络(LSTM)降维处理后,构建出了能够表征离心泵轴承退化过程的一维特征量;最后,对比分析了LSTM网络、反向传播(BP)网络和卷积神经(CNN)网络的预测效果。研究结果表明:LSTM网络的均方根误差(RMSE)为0.402,平均绝对百分比误差(MAPE)为0.332,预测精度在三者中最好,模型平均训练时间为12.6 s,可见LSTM网络在预测精度及模型训练时间上更具优势。

基于可解释深度卷积网络的空时自适应处理方法

在实际应用中,空时自适应处理(STAP)算法的性能受限于足够多独立同分布(IID)样本的获取。然而,目前可有效减少IID样本需求的算法仍面临一些问题。针对这些问题,该文融合数据驱动和模型驱动思想,构建了具有明确数学含义的多模块深度卷积神经网络(MDCNN),实现了小样本条件下对杂波协方差矩阵快速、准确、稳定估计。所构建MDCNN网络由映射模块、数据模块、先验模块和超参数模块组成。其中,前后端映射模块分别对应数据的预处理和后处理;单组数据模块和先验模块共同完成一次迭代优化,网络主体由多组数据模块和先验模块构成,可实现多次等效迭代优化;超参数模块则用来调整等效迭代中可训练参数。上述子模块均具有明确数学表述和物理含义,因此所构造网络具有良好的可解释性。实测数据处理结果表明,在实际非均匀杂波环境下该文所提方法杂波抑制性能优于现有典型小样本STAP方法,且运算时间较后者大幅降低。

基于AI的5G网络智能优化与自适应调整

文章探讨了人工智能(Artificial Intelligence,AI)在5G网络优化与自适应调整中的应用,重点涵盖网络规划与设计、资源分配与管理、网络维护与故障检测等方面。通过数据驱动的优化方法、深度强化学习以及实时数据处理与反馈机制,实现网络性能的显著提升。此外,进一步讨论了动态频谱管理、自适应负载均衡、网络切片动态调整、实时流量预测以及网络资源实时分配等自适应调整技术。

Neural network processing for adaptive line enhancement

This paper describes the inverstigation devoted to establish suitable weights in a feed-forward neural network realizing the narrow-band filtering map in the case of adaptive line enhanccment(ALE) by the utility of the optimum common learning rate back propagation (OCLR BP) algorithm. It is found that a feed-forward network with 64 linear input and output neurons, and 8 odd sigmoid neurons in the hidden layer, i.e. an (64→8→64) architecture, could establish the specific input-output function in the case of relatively low signal-to-noise radio. Only is an input signal consisting of mixed periodic and broad-band components available to the network system. After learning, both the 'fanning-in-connection patterns', each of which consists of weights fanning into a hidden-neuron from all the outputs of input-neurons, and the 'fanning-out-connection patterns', each of which consists of weights fanning out from a hidden-neuron to all the inputs of output-neurons, are tuned to the periodic signals. The nonlinear map formed by this neural network provided substantial improvement in performance over that formed by an Adaline-ALE with same frequency resolution.

Optimum Setting Strategy for WTGS by Using an Adaptive Neuro-Fuzzy Inference System

With the popularization of wind energy, the further reduction of power generation cost became the critical problem. As to improve the efficiency of control for variable speed Wind Turbine Generation System (WTGS), the data-driven Adaptive Neuro-Fuzzy Inference System (ANFIS) was used to establish a sensorless wind speed estimator. Moreover, based on the Supervisory Control and Data Acquisition (SCADA) System, the optimum setting strategy for the maximum energy capture was proposed for the practical operation process. Finally, the simulation was executed which suggested the effectiveness of the approaches.

A GAUSSIAN MIXTURE MODEL-BASED REGULARIZATION METHOD IN ADAPTIVE IMAGE RESTORATION

A GMM (Gaussian Mixture Model) based adaptive image restoration is proposed in this paper. The feature vectors of pixels are selected and extracted. Pixels are clustered into smooth,edge or detail texture region according to variance-sum criteria function of the feature vectors. Then pa-rameters of GMM are calculated by using the statistical information of these feature vectors. GMM predicts the regularization parameter for each pixel adaptively. Hopfield Neural Network (Hopfield-NN) is used to optimize the objective function of image restoration,and network weight value matrix is updated by the output of GMM. Since GMM is used,the regularization parameters share properties of different kind of regions. In addition,the regularization parameters are different from pixel to pixel. GMM-based regularization method is consistent with human visual system,and it has strong gener-alization capability. Comparing with non-adaptive and some adaptive image restoration algorithms,experimental results show that the proposed algorithm obtains more preferable restored images.

含乙烯基胺酯键聚醚类可逆交联聚合物的制备及性能研究

利用三种分子量相同但重复单元不同的双乙酰乙酸酯封端聚醚与三(2-氨基乙基)胺交联形成含乙烯基胺酯动态化学键的可逆交联聚合物,也称共价自适应网络。重点考察了构筑单元对动态交联网络的结构、热性能、力学性能及动态性能的影响。结果表明,当构筑单元链柔性更强时,网络中的分子链更容易运动,表现出较大的延展性及较低的模量。此外,在高温下动态网络的网络拓扑重排速度更快,应力松弛时间更短。不同于其他动态交换反应,乙烯基胺酯动态交换活化能由于交换机制的不同表现出明显的双温度响应。

Early Detection of Heartbeat from Multimodal Data Using RPA Learning with KDNN-SAE

Heartbeat detection stays central to cardiovascular an electrocardiogram(ECG)is used to help with disease diagnosis and management.Existing Convolutional Neural Network(CNN)-based methods suffer from the less generalization problem thus;the effectiveness and robustness of the traditional heartbeat detector methods cannot be guaranteed.In contrast,this work proposes a heartbeat detector Krill based Deep Neural Network Stacked Auto Encoders(KDNN-SAE)that computes the disease before the exact heart rate by combining features from multiple ECG Signals.Heartbeats are classified independently and multiple signals are fused to estimate life threatening conditions earlier without any error in classification of heart beat.This work contained Training and testing stages,in the preparation part at first the Adaptive Filter Enthalpy-based Empirical Mode Decomposition(EMD)is utilized to eliminate the motion artifact in the signal.At that point,the robotic process automation(RPA)learning part extracts the effective features are extracted,and normalized the value of the feature then estimated utilizing the RPA loss function.At last KDNN-SAE prepared training for the data stored in the dataset.In the subsequent stage,input signal compute motion artifact and RPA Learning the evaluation part determines the detection of Heartbeat.So early diagnosis of heart failures is an essential factor.The results of the experiments show that our proposed method has a high score outcome of 0.9997.Comparable to the CIF,which reaches 0.9990.The CNN and Artificial Neural Network(ANN)had less score 0.95115 and 0.90147.

基于精确时间协议的工业无线传感器网络时间同步方法

针对工业无线传感器网络(IWSNs)中复杂链路环境、温度波动等造成的链路时延动态变化、时钟计时干扰、时间戳获取不确定等问题,提出一种基于精确时间协议(PTP)的IWSNs时间同步方法。首先,融合PTP双向时间同步过程的时钟计时干扰、非对称链路时延噪声,建立时钟状态空间模型和观测模型;其次,构建反向自适应卡尔曼滤波算法以滤除噪声干扰;然后,利用反向估计和正向估计的时钟状态归一化新息比值来评估噪声统计模型的合理性;最后,在设定检测阈值后,动态调整时钟状态过程噪声,以实现时钟参数的精确估计。仿真结果表明,相较于经典卡尔曼滤波算法和PTP,在不同时钟计时精度下,反向自适应卡尔曼滤波算法估计的时钟偏移和偏移率均有较小且更稳定的误差标准差,有效解决了噪声不确定等原因造成的卡尔曼滤波发散问题,提高了时间同步的可靠性。

基于T-S模型的自适应神经模糊推理系统及其在热工过程建模中的应用

在工业热工过程控制中,被控对象动态特性往往表现出非线性、时变性、大迟延和大惯性等特点,这使得难以对其建立比较精确的模型,从而难于精确表达热工过程及实施整体优化控制。针对热工过程建模难的现状,为达到建立精确非线性模型的目的,提出1种基于T-S模型的自适应神经模糊系统(ANFIS)模糊建模方法。该方法通过对模糊系统的结构辨识和参数辨识,使神经模糊网络能够自主、迅速有效地收敛到要求的输入和输出关系,从而达到精确建模的目的。仿真结果验证了所提出的算法的有效性,将其应用到热工过程建模中可获得高精度的非线性模型。

基于模糊层次分析法的多属性垂直切换算法

为实现移动节点在不同网络间的无缝切换,保证业务的连续性,提出了一种基于模糊层次分析法的多属性垂直切换算法.根据人类思维具有模糊性的特点,对各属性间的相对重要程度进行比较时用模糊数来表示比较结果,并建立模糊判决矩阵,以解决传统算法中判决矩阵的一致性与人类思维一致性之间存在的差异问题.为了提高切换的有效性,结合对用户运动状态、目标基站负载状态的判断,设计了一种自适应可变时长的定时器.仿真结果表明,文中算法能够提高切换性能和系统的吞吐量,降低系统的丢话率.