Flexible,thermal processable,self-healing,and fully bio-based starch plastics by constructing dynamic imine network

The serious environmental threat caused by petroleum-based plastics has spurred more researches in developing substitutes from renewable sources.Starch is desirable for fabricating bioplastic due to its abundance and renewable nature.However,limitations such as brittleness,hydrophilicity,and thermal properties restrict its widespread application.To overcome these issues,covalent adaptable network was constructed to fabricate a fully bio-based starch plastic with multiple advantages via Schiff base reactions.This strategy endowed starch plastic with excellent thermal processability,as evidenced by a low glass transition temperature(T_(g)=20.15℃).Through introducing Priamine with long carbon chains,the starch plastic demonstrated superior flexibility(elongation at break=45.2%)and waterproof capability(water contact angle=109.2°).Besides,it possessed a good thermal stability and self-adaptability,as well as solvent resistance and chemical degradability.This work provides a promising method to fabricate fully bio-based plastics as alternative to petroleum-based plastics.

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

The adaptive learning and prediction of a highly nonlinear and time-varying bioreactor benchmark process is studied using Neur-On-Line, a graphical tool kit for developing and deploying neural networks in the G2 real time intelligent environment,and a new modified Broyden, Fletcher, Goldfarb, and Shanno （BFGS） quasi-Newton algorithm. The modified BFGS algorithm for the adaptive learning of back propagation （BP） neural networks is developed and embedded into NeurOn-Line by introducing a new search method of learning rate to the full memory BFGS algorithm. Simulation results show that the adaptive learning and prediction neural network system can quicklv track the time-varving and nonlinear behavior of the bioreactor.

Fast Learning in Spiking Neural Networks by Learning Rate Adaptation

For accelerating the supervised learning by the SpikeProp algorithm with the temporal coding paradigm in spiking neural networks (SNNs), three learning rate adaptation methods (heuristic rule, delta-delta rule, and delta-bar-delta rule), which are used to speed up training in artificial neural networks, are used to develop the training algorithms for feedforward SNN. The performance of these algorithms is investigated by four experiments: classical XOR (exclusive or) problem, Iris dataset, fault diagnosis in the Tennessee Eastman process, and Poisson trains of discrete spikes. The results demonstrate that all the three learning rate adaptation methods are able to speed up convergence of SNN compared with the original SpikeProp algorithm. Furthermore, if the adaptive learning rate is used in combination with the momentum term, the two modifications will balance each other in a beneficial way to accomplish rapid and steady convergence. In the three learning rate adaptation methods, delta-bar-delta rule performs the best. The delta-bar-delta method with momentum has the fastest convergence rate, the greatest stability of training process, and the maximum accuracy of network learning. The proposed algorithms in this paper are simple and efficient, and consequently valuable for practical applications of SNN.

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.

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.

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。

基于卷积神经网络的自适应波束形成

提出一种基于卷积神经网络的自适应波束形成方法,旨在通过自适应调整接收波束方向以提高通道中信号的信噪比。采用同时多波束接收信号的概念,对阵列天线接收信号以不同的相位加权并相加,即依据自适应多波束形成多通道接收。利用神经网络的非线性处理能力,在阵列接收不同来波方向信号时可以对其实现自适应波束形成。使用波束形成方式设计标签,通过比较输出信号的信噪比相对于输入信号信噪比的增益以评价该方法的有效性。仿真有效提高了信号的信噪比,接收阵列可以同时接收多个波束信号并按各输入信号的入射角度不同在不同的通道输出对应信号。

基于遗传算法的油田集输管网优化调整方法

为解决油田生产能耗大、管网造价高问题,提出基于遗传算法的油田集输管网优化调整方法。首先在油田集输管网布局一定的情况下,利用管网节点矩阵计算管网参数;其次,根据集输管网工艺流程以及热力、水力分析构建油田集输管网数学模型的目标函数;最后对管径以及其所在位置进行编码,利用Prime算法确定集油站的位置,并评估个体的适应度,再利用遗传算法获得油田集输管网优化结果。通过实际应用以及对应用结果的评估,集输管网能耗高的6个计转站吨油耗电量减少了16.5 kWh,吨油耗气量减少了12.9 m^(3),一年可节省费用56.3万元,具有明显的节能降耗效果。

图像数据增强技术原理与发展综述

图像数据增强技术在计算机视觉和机器学习领域中扮演着重要的角色。传统的图像数据增强技术包括几何变换、像素级图像变换、图像滤波等方法,但这些方法的效果受到一定的限制。因此,基于深度学习的图像数据增强技术应运而生,涌现出自适应增强、生成对抗式网格(Generative Adversarial Networks, GAN)、弱监督等技术并逐渐成为改进数据集,实现数据的增加和质量的提升,解决深度学习模型过拟合和欠拟合问题的重要手段。文中综述了传统图像数据增强技术和基于深度学习的图像数据增强技术相关原理与应用,并探讨了他们的优缺点以及未来的发展方向。

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。

Modeling and Control of Nonlinear Discrete-time Systems Based on Compound Neural Networks

An adaptive inverse controller for nonliear discrete-time system is proposed in this paper. A compound neural network is constructed to identify the nonlinear system, which includes a linear part to approximate the nonlinear system and a recurrent neural network to minimize the difference between the linear model and the real nonlinear system. Because the current control input is not included in the input vector of recurrent neural network (RNN), the inverse control law can be calculated directly. This scheme can be used in real-time nonlinear single-input single-output (SISO) and multi-input multi-output (MIMO) system control with less computation work. Simulation studies have shown that this scheme is simple and affects good control accuracy and robustness.

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.

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.

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.