基于LSTM-Informer模型的液压支架压力时空多步长预测

目前多步液压支架压力预测大多为单步液压支架压力的累计预测,单步累计次数越多,累计误差就越大,影响预测精度。针对该问题,提出了一种基于长短时记忆(LSTM)-Informer模型的液压支架压力时空多步长预测方法。采用卡尔曼滤波消除液压支架压力数据中的振动噪声后,在工作面端部和中部各选取相邻的5台液压支架压力数据建立2个时空数据集(数据集1和数据集2),并对时空数据进行标准化预处理。将时空数据输入LSTM模型提取时空特征,并将提取的时空特征输入Informer模型的编码器,经过位置编码后利用多头概率稀疏自注意力来关注压力序列的变化特征,经过最大池化和一维卷积消除最终输出特征图的冗余组合。利用多头概率稀疏自注意力来关注压力序列的变化特征,将Informer模型的解码器改为全连接层,得到液压支架压力的预测结果。实验结果表明:与基于门控循环单元(GRU)、LSTM和Informer模型的预测方法相比,基于LSTM-Informer模型的预测方法在预测6,12,24步长液压支架压力时的均方根误差(RMSE)和平均绝对误差(MAE)均最小;其中基于数据集1预测的6步长液压支架压力的RMSE分别降低了41.63%,49.74%,11.85%,MAE分别降低了41.75%,50.00%,12.00%;基于数据集2预测的6步长液压支架压力的RMSE分别降低了48.15%,59.86%,19.88%,MAE分别降低了49.87%,54.90%,13.16%。

基于CNN-GRU模型的USV运动姿态多步预测方法

针对单一模型在预测无人水面艇(Unmanned Surface Vessel,USV)运动姿态时精度不高的问题,提出一种基于卷积神经网络(CNN)和门控循环单元(GRU)的USV姿态多步预测模型。首先,使用滑动窗口法构造运动姿态数据集作为模型输入;然后,使用CNN模块挖掘时序数据的局部特征;最后,使用GRU模型进行多步预测。使用实测USV运动姿态数据进行预测实验,实验结果表明,该模型比XGBoost模型、单一LSTM模型和单一GRU模型具有更高的预测精度,各项评价指标表现更佳,具有重要的应用价值。

Banach空间中Mann-Ishikawa迭代和Multi-Step迭代的等价性问题

本文研究了一致光滑Banach空间中迭代算法等价性的问题.利用泛函分析的方法,获得了广义强连接Φ伪压缩算子在具误差的修正的Mann-Ishikawa迭代和具误差的修正的multi-step迭代下收敛等价性的结果,推广了目前的相关结果.

DPCA-POA-RF-Informer在多情景光伏多步预测中的应用

针对光伏发电波动性与不确定性对电力系统稳定产生的影响,对多情景光伏发电功率的多步预测进行研究。首先通过密度峰值算法根据太阳辐射量、温度、湿度等气象数据对天气状况进行精确分类。其次,为了使模型表现出更好的性能,建立了鹈鹕算法优化随机森林(POA-RF)的因素筛选特征变量,模型用鹈鹕算法对随机森林的决策树数目和深度两个参数进行寻优,加强了因素筛选的有效性。最后,基于Informer模型对不同天气状况的光伏功率进行多步预测。实例计算结果验证了所提模型预测精准度的有效性与精准性。

基于同步ADMM算法含P2G-CCS的多园区综合能源系统优化调度

多园区综合能源微电网系统交互需要解决每个微电网之间的协调优化调度的问题,文中通过引入交互耦合功率变量解耦的方法,来求解园区内微电网之间交互的电功率,将集中求解的复杂问题转换为各微电网之间相互合作而且可以内部管理的优化问题,于是文中考虑采用同步式交替向乘子法(alternating direction method of multipliers,ADMM)分布式求解方法来实现各个园区微电网系统的成本关系分配,系统只需要求解分布式优化方案所需的信息,可以最大限度地降低运行成本,同时为了保证多园区微电网系统的低碳运行和降低环境成本,在考虑单个电热冷综合能源微电网系统的基础上,采用碳捕集设备和电转气装置以及配合阶梯碳交易机制的方法,更进一步降低系统碳排放;最后,通过仿真算例来验证所提方法和模型的有效性。

Real-time multi-step prediction control for BP network with delay

Real time multi step prediction of BP network based on dynamical compensation of system characteristics is suggested by introducing the first and second derivatives of the system and network outputs into the network input layer, and real time multi step prediction control is proposed for the BP network with delay on the basis of the results of real time multi step prediction, to achieve the simulation of real time fuzzy control of the delayed time system.

Multi-step-prediction of chaotic time series based on co-evolutionary recurrent neural network

This paper proposes a co-evolutionary recurrent neural network （CERNN） for the multi-step-prediction of chaotic time series, it estimates the proper parameters of phase space reconstruction and optimizes the structure of recurrent neural networks by coevolutionary strategy. The searching space was separated into two subspaces and the individuals are trained in a parallel computational procedure. It can dynamically combine the embedding method with the capability of recurrent neural network to incorporate past experience due to internal recurrence. The effectiveness of CERNN is evaluated by using three benchmark chaotic time series data sets： the Lorenz series, Mackey-Glass series and real-world sun spot series. The simulation results show that CERNN improves the performances of multi-step-prediction of chaotic time series.

Nonlinear system PID-type multi-step predictive control

A compound neural network was constructed during the process of identification and multi-step prediction. Under the PID-type long-range predictive cost function, the control signal was calculated based on gradient algorithm. The nonlinear controller’s structure was similar to the conventional PID controller. The parameters of this controller were tuned by using a local recurrent neural network on-line. The controller has a better effect than the conventional PID controller. Simulation study shows the effectiveness and good performance.

Strategies for multi-step-ahead available parking spaces forecasting based on wavelet transform

A new methodology for multi-step-ahead forecasting was proposed herein which combined the wavelet transform(WT), artificial neural network(ANN) and forecasting strategies based on the changing characteristics of available parking spaces(APS). First, several APS time series were decomposed and reconstituted by the wavelet transform. Then, using an artificial neural network, the following five strategies for multi-step-ahead time series forecasting were used to forecast the reconstructed time series: recursive strategy, direct strategy, multi-input multi-output(MIMO) strategy, DIRMO strategy(a combination of the direct and MIMO strategies), and newly proposed recursive multi-input multi-output(RECMO) strategy which is a combination of the recursive and MIMO strategies. Finally, integrating the predicted results with the reconstructed time series produced the final forecasted available parking spaces. Three findings appear to be consistently supported by the experimental results. First, applying the wavelet transform to multi-step ahead available parking spaces forecasting can effectively improve the forecasting accuracy. Second, the forecasting resulted from the DIRMO and RECMO strategies is more accurate than that of the other strategies. Finally, the RECMO strategy requires less model training time than the DIRMO strategy and consumes the least amount of training time among five forecasting strategies.

基于MIC-EEMD-改进Informer的含高比例清洁能源与储能的电力市场短期电价多步预测

随着电力现货市场的开展,短期电价预测对于各市场主体的决策有着重要意义,而高比例清洁能源与储能的不断接入给短期电价预测带来很大挑战。提出一种基于最大信息系数法(maximum information coefficient,MIC)、集成经验模态分解(ensemble empirical mode decomposition,EEMD)和改进Informer的短期电价多步预测模型。首先,采用MIC分析出与电价相关性较高的几类因素作为模型原始输入序列;然后,将上述原始序列进行EEMD分解后得到多条本征模函数(intrinsic mode function,IMF)和一个残余项后输入改进Informer分别得到翌日24点多步预测结果,再对预测结果进行滤波;最后,将滤波后序列的预测结果叠加得到最终的预测值。以西班牙电力市场数据进行验证,实验结果证明该模型可以有效提高电力市场短期电价多步预测精度。

面向STEP-NC数控加工的Multi-agent工艺协同设计研究

提出了一个基于特征的Multi-agent工艺协同设计系统,简要介绍了Multi-agent技术、该系统的体系结构和特征技术及特征继承关系,详细描述了系统中各代理的功能及系统工作流程。

Chaotic time series multi-step direct prediction with partial least squares regression

Considering chaotic time series multi-step prediction, multi-step direct prediction model based on partial least squares （PLS） is proposed in this article, where PLS, the method for predicting a set of dependent variables forming a large set of predictors, is used to model the dynamic evolution between the space points and the corresponding future points. The model can eliminate error accumulation with the common single-step local model algorithm~ and refrain from the high multi-collinearity problem in the reconstructed state space with the increase of embedding dimension. Simulation predictions are done on the Mackey-Glass chaotic time series with the model. The satisfying prediction accuracy is obtained and the model efficiency verified. In the experiments, the number of extracted components in PLS is set with cross-validation procedure.

Application of Multi-Step Differential Transform Method on Flow of a Second-Grade Fluid over a Stretching or Shrinking Sheet

In this study, a reliable algorithm to develop approximate solutions for the problem of fluid flow over a stretching or shrinking sheet is proposed. It is depicted that the differential transform method (DTM) solutions are only valid for small values of the independent variable. The DTM solutions diverge for some differential equations that extremely have nonlinear behaviors or have boundary-conditions at infinity. For this reason the governing boundary-layer equations are solved by the Multi-step Differential Transform Method (MDTM). The main advantage of this method is that it can be applied directly to nonlinear differential equations without requiring linearization, discretization, or perturbation. It is a semi analytical-numerical technique that formulizes Taylor series in a very different manner. By applying the MDTM the interval of convergence for the series solution is increased. The MDTM is treated as an algorithm in a sequence of intervals for finding accurate approximate solutions for systems of differential equations. It is predicted that the MDTM can be applied to a wide range of engineering applications.

Reproducing fling-step and forward directivity at near source site using of multi-objective particle swarm optimization and multi taper

This paper presents a technique to reproduce compatible seismogran3s involving permanent displacen3ent effects at sites close to the fault source. A multi-objective evolutionary algorithm is used to minimize the differences between the response spectra and multi-tapered power spectral delsilies corresponding to the recorded and simulated wavelbrms. The multi-taper method is used to reduce the spectral leakage that is inherent in the Fourier rams formed form ofwavelbrms, ieading to a reduction of variance in power spectral amplitudes, thus permitting the calibration of the two sets of data. The technique is implemented using the 1998-Fandoqa （lran） earthquake data and the results are compared with the actual observed data. Additionally, a comparison is made with a SAR interfcrometry study leading to fair agreement with the reported dislocation along the main fault. The simulation procedure and results are discussed and assessed concluding that, although the technique may be associated with uncertainties, it can still be used to reproduce wavelbnns at near source sites that include permanent dislocation, and can be used for seismic pertbrmance evaluation of structures in the region under study.

Finite element analysis and experiment on multi-wedge cross wedge rolling for asymmetric stepped shaft of C45

A rigid-plastic finite element method(FEM) simulation model for a multi-wedge cross wedge rolling(MCWR) was developed to analyze an asymmetric stepped shaft. To evaluate the MCWR process and better understand its deformation characteristics, the material flowing mechanisms, temperature distributions, strain and rolling force were analyzed. The correctness of the finite element simulation is experimentally verified. Numerical simulations and experiments led to the following conclusions: when α=36° and β=7.5°, the quality of the work piece can be significantly improved. Finally, the development of the asymmetric stepped shaft is applied to industrial production.

A novel methodology for constructing a multi-wing chaotic and hyperchaotic system with a unified step function switching control

This paper aims at developing a novel method of constructing a class of multi-wing chaotic and hyperchaotic system by introducing a unified step function. In order to overcome the essential difficulties in iteratively adjusting multiple parameters of conventional multi-parameter control, this paper introduces a unified step function controlled by a single parameter for constructing various multi-wing chaotic and hyperchaotic systems. In particular, to the best of the authors＇ knowledge, this is also the first time to find a non-equilibrium multi-wing hyperchaotic system by means of the unified step function control. According to the heteroclinic loop Shilnikov theorem, some properties for multi-wing attractors and its chaos mechanism are further discussed and analyzed. A circuit for multi-wing systems is designed and implemented for demonstration, which verifies the effectiveness of the proposed approach.

基于多步句子选择-重写模型生成科技文献创新点

近年来科技文献数量的显著增加,使得研究人员难以跟上自己所在领域的最新进展。为了保持对前沿研究的追踪,研究者通常依赖于阅读文献中的创新点,该部分简明扼要地概括了关键研究成果。然而,许多作者在文中并未充分地呈现文章的创新内容,这导致读者难以快速掌握研究的核心内容。为了解决这一问题,提出了一个全新的任务,即自动生成科技文献的创新点摘要。该任务的难点之一在于目前缺少相关数据集,于是构建了科技创新点摘要语料库(SCSC)。另一个难点在于目前现有的生成式或抽取式模型在生成创新点方面分别存在冗余度过高和句与句之前缺乏关联性的问题。为了满足生成简洁、高质量创新点的需求,提出了MSSRsum模型(一个多步句子选择-重写模型)。最终实验表明,所提模型在SCSC和arXiv数据集上优于基线模型。

基于机-岩状态识别和融合注意力的盾构姿态多步预测

为准确预测未来多个时刻的盾构姿态,帮助盾构操作人员提前识别盾构姿态变化趋势,以进行早期决策,提出基于机-岩状态识别和融合多尺度的特征-时域注意力机制的知识-数据双驱动盾构掘进姿态多步预测方法。引入实时反映机-岩工作状态关系的场切入指标FPI、单位贯入度的刀盘扭矩指标TPI、分区可掘性指标FPIR、螺旋机性能指标STP等复合参数指标,作为模型的输入特征参数,并构建以GRU为基础单元的Encoder-Decoder网络结构。在特征维度上,采用融合多尺度一维卷积的特征注意力机制,自适应捕捉不同层次、不同尺度的盾构掘进参数特征;时间维度上,在解码器中引入时域注意力机制,充分挖掘盾构掘进数据中的长期历史信息和短期输入输出序列的隐藏依赖关系。广州地铁12号线盾构掘进历史数据的模型测试结果分析表明,该预测方法在不增加网络复杂性的前提下,既缓解了算法自身在寻优、迭代和匹配时产生的可解释性差、效率低等问题,又大幅提升模型的特征提取、时间序列的相关性捕获及长期趋势挖掘的能力,实现盾构掘进姿态的精准多步预测,其性能明显优于门控循环神经网络LSTM、GRU及其经典组合模型GRU-SelfAttention、GRU-MultiheadAttention等。研究结果为进一步完善盾构掘进姿态预测方法、提升盾构掘进姿态优化控制水平提供参考。

Noise cancellation of a multi-reference full-wave magnetic resonance sounding signal based on a modified sigmoid variable step size least mean square algorithm

Nano-volt magnetic resonance sounding(MRS) signals are sufficiently weak so that during the actual measurement, they are affected by environmental electromagnetic noise, leading to inaccuracy of the extracted characteristic parameters and hindering effective inverse interpretation. Considering the complexity and non-homogeneous spatial distribution of environmental noise and based on the theory of adaptive noise cancellation, a model system for noise cancellation using multi-reference coils was constructed to receive MRS signals. The feasibility of this system with theoretical calculation and experiments was analyzed and a modified sigmoid variable step size least mean square(SVSLMS) algorithm for noise cancellation was presented. The simulation results show that, the multi-reference coil method performs better than the single one on both signal-to-noise ratio(SNR) improvement and signal waveform optimization after filtering, under the condition of different noise correlations in the reference coils and primary detecting coils and different SNRs. In particular, when the noise correlation is poor and the SNR<0, the SNR can be improved by more than 8 dB after filtering with multi-reference coils. And the average fitting errors for initial amplitude and relaxation time are within 5%. Compared with the normalized least mean square(NLMS) algorithm and multichannel Wiener filter and processing field test data, the effectiveness of the proposed method is verified.