Tool Health Condition Recognition Method for High Speed Milling of Titanium Alloy Based on Principal Component Analysis (PCA) and Long Short Term Memory (LSTM)

The healthy condition of the milling tool has a very high impact on the machining quality of the titanium components.Therefore,it is important to recognize the healthy condition of the tool and replace the damaged cutter at the right time.In order to recognize the health condition of the milling cutter,a method based on the long short term memory(LSTM)was proposed to recognize tool health state in this paper.The various signals collected in the tool wear experiments were analyzed by time-domain statistics,and then the extracted data were generated by principal component analysis(PCA)method.The preprocessed data extracted by PCA is transmitted to the LSTM model for recognition.Compared with back propagation neural network(BPNN)and support vector machine(SVM),the proposed method can effectively utilize the time-domain regulation in the data to achieve higher recognition speed and accuracy.

LW-AFC and its active components ameliorate corticosterone-induced long-term potentiation impairment in mice

OBJECTIVE LW-AFC is extracted from the classical traditional Chinese medicinal prescription-Liuwei Dihuang Decoction.Previous studies have showed that LW-AFC could improve learning&memory ability in amny animal models.In this study,we focused on evaluating the effect of several main active components fromLW-AFC(B-B;loganin,LOG;morroniside,MOR;paeoniflorin,PF and stachyose,STA)on LTP.METHODS In vivo recording of LTP was used in this study to evaluate the effects of LW-AFC and it′s active components on coticorsterone(Cort)induced LTP impairment.RESULTS The results showed that LW-AFC could ameliorate Cort-induced LTP impairment.The effect of LW-AFC was abolished when the immune function was inhibited.Single administration(ig,ip,icv)of any of the components had no effect on Cort-induced LTP impairment.Consecutively intragastric administration or intraperitoneal injections(chronic administration)of B-B,LOG,MOR or PF for 7 d showed protective effect on Cort-induced LTP impairment.Intragastric administration of STA for 7 d protected LTP from impairment induced by Cort,while there was little improving effect when STA was administrated via intraperitoneal injection.In addition,when the intestinal microbiota was disrupted by applying the antibiotic cocktail,STA showed little protective effect against Cort.CONCLUSION In conclusion,LW-AFC and it′s components showed positive effects against cort induced LTP impairment,it seems that all displayed protective effects via indirectly,immune modulation might be the common pathway for all components;the exact pathways are different in each component,B-B,LOG,MOR and PF could be absorbed into the bloods tream and then modulate the peripheral immune function,while STA could not be absorbed and modulates the immune function via modulating intestinal microbiota.Further studies are needed to invesgate the underlying mechanisms and the synergetic effects of all components.

Text Detection in Natural Scene Images Using Morphological Component Analysis and Laplacian Dictionary

Text in natural scene images usually carries abundant semantic information. However, due to variations of text and complexity of background, detecting text in scene images becomes a critical and challenging task. In this paper, we present a novel method to detect text from scene images. Firstly, we decompose scene images into background and text components using morphological component analysis(MCA), which will reduce the adverse effects of complex backgrounds on the detection results.In order to improve the performance of image decomposition,two discriminative dictionaries of background and text are learned from the training samples. Moreover, Laplacian sparse regularization is introduced into our proposed dictionary learning method which improves discrimination of dictionary. Based on the text dictionary and the sparse-representation coefficients of text, we can construct the text component. After that, the text in the query image can be detected by applying certain heuristic rules. The results of experiments show the effectiveness of the proposed method.

A NEW METHOD OF COMPUTING MULTI-COMPONENT E-pH DIAGRAMS

Aqueous E pH Diagram is an essential tool for analyzing hydrometallurgical and corrosion processes. Due to the requirements for environmental protection and energy saving in recent years, waste water processing and hydrometallurgical process of concentrate have been greatly developed. The construction of E pH diagrams has turned to multi component systems. However, there are some limits in plotting such diagrams. There is only one diagram for one multi component system, which can not reflect the truth of the aqueous reaction. In the paper, a new computation method is proposed to construct E pH diagrams. Component activity term is used to determine the boundary of stable areas. For the multi component systems, different atom ratios of elements have been taken into account. M S H 2O system is chosen to study since it is of importance in metallurgical solution. Compared with conventional methods, the algorithm is simple and conforms to real conditions.

A delay-constrained energy-efficient component carrier adjusting scheme for LTE-Advanced systems

The energy efficiency and packet delay tradeoffs in long term evolution-advanced(LTE-A) systems are investigated.Analytical expressions are derived to explain the relation of energy efficiency to mean packet delay,arrival rate and component carrier(CC) configurations,from the theoretical respective which reveals that the energy efficiency of multiple CC systems is closely related to the frequency of CCs and the number of active CCs.Based on the theoretical analysis,a CC adjusting scheme for LTE-A systems is proposed to maximize energy efficiency subject to delay constraint by dynamically altering the on/off state of CCs according to traffic variations.Numerical and simulation results show that for CCs in different frequency bands with equal transmit power,the proposed scheme could significantly improve the energy efficiency of users in all aggregation levels within the constraint of mean packet delay.

Efficient Fast Independent Component Analysis Algorithm with Fifth-Order Convergence

Independent component analysis （ICA） is the primary statistical method for solving the problems of blind source separation. The fast ICA is a famous and excellent algorithm and its contrast function is optimized by the quadratic convergence of Newton iteration method. In order to improve the convergence speed and the separation precision of the fast ICA, an improved fast ICA algorithm is presented. The algorithm introduces an efficient Newton＇s iterative method with fifth-order convergence for optimizing the contrast function and gives the detail derivation process and the corresponding condition. The experimental results demonstrate that the convergence speed and the separation precision of the improved algorithm are better than that of the fast ICA.

Impact of Long-Term Fertilization on Cropland Soil Fauna Community at Loess Soil, Shannxi, China

The relationship between long-term fertilization and cropland network for soil fertility and fertilizers in Loess soil of Shannxi soil fauna was studied at the station＇s experiment research Provincefrom Jul. 2001 to Oct. 2002. Six types of long-term fertilizer were carried out for this study including non-fertilizer （CK）, abandonment （ABAND）, nitrogenous and phosphors and potassium fertilizers combined （NPK）, straw and NPK （SNPK）, organic material and NPK （MNPK） and 1.5 times MNPK （1.5MNPK）. 72 soil samples were collected and 5 495 species of cropland soil fauna obtained by handsorting and Cobb methods at 4 times, belonging to 6 Phyla, 11 Classes, 22 Orders, 2 Superfamilies, 61 Families and 35 Genera. The result showed that different fertilizer had significantly impacted on the cropland soil fauna （F = 2.24, P〈0.007）. The number of the cropland soil fauna was related to the soil physicochemical properties caused by long-term fertilization. The result by principal component analysis, focusing on the number of 15 key soil fauna species group＇s diversity, evenness of community and the total soil fauna individuals indicated that the effects of SNPK, NPK, MNPK and 1.5MNPK were significantly different from that of the cropland soil fauna, in which, SNPK and NPK had the positive effect on cropland soil fauna, and MNPK and 1.5 MNPK had the negative affect, others could not be explained. By principal component I, the synthetic effect of different fertilization on the total soil fauna individuals and the group was most significant, and the effect was little on evenness and diversity. By value of eigenvectors, the maximum one was 9.6248, and the minimum one was - 1.0904, that means the 6 types of fertilization did not affect evenly the cropland soil fauna.

Estimation of unloading relaxation depth of Baihetan Arch Dam foundation using long-short term memory network

The unloading relaxation caused by excavation for construction of high arch dams is an important factor influencing the foundation’s integrity and strength.To evaluate the degree of unloading relaxation,the long-short term memory(LSTM)network was used to estimate the depth of unloading relaxation zones on the left bank foundation of the Baihetan Arch Dam.Principal component analysis indicates that rock charac-teristics,the structural plane,the protection layer,lithology,and time are the main factors.The LSTM network results demonstrate the unloading relaxation characteristics of the left bank,and the relationships with the factors were also analyzed.The structural plane has the most significant influence on the distribution of unloading relaxation zones.Compared with massive basalt,the columnar jointed basalt experiences a more significant unloading relaxation phenomenon with a clear time effect,with the average unloading relaxation period being 50 d.The protection layer can effectively reduce the unloading relaxation depth by approximately 20%.

The quantum thermodynamic functions of plasma in terms of the Green’s function

The objective of this paper is to calculate the third virial coefficient in Hartree approximation, Hartree-Fock approximation and the MontrollWard contribution of plasma byusing the Green’s function technique in terms of the interaction parameter , and used the result to calculate the quantum thermodynamic functions for one and two component plasma in the case of , where is the thermal De Broglie wave-length. We compared our results with others.

Short Term Traffic Flow Prediction Using Hybrid Deep Learning

Traffic flow prediction in urban areas is essential in the IntelligentTransportation System (ITS). Short Term Traffic Flow (STTF) predictionimpacts traffic flow series, where an estimation of the number of vehicleswill appear during the next instance of time per hour. Precise STTF iscritical in Intelligent Transportation System. Various extinct systems aim forshort-term traffic forecasts, ensuring a good precision outcome which was asignificant task over the past few years. The main objective of this paper is topropose a new model to predict STTF for every hour of a day. In this paper,we have proposed a novel hybrid algorithm utilizing Principal ComponentAnalysis (PCA), Stacked Auto-Encoder (SAE), Long Short Term Memory(LSTM), and K-Nearest Neighbors (KNN) named PALKNN. Firstly, PCAremoves unwanted information from the dataset and selects essential features.Secondly, SAE is used to reduce the dimension of input data using onehotencoding so the model can be trained with better speed. Thirdly, LSTMtakes the input from SAE, where the data is sorted in ascending orderbased on the important features and generates the derived value. Finally,KNN Regressor takes information from LSTM to predict traffic flow. Theforecasting performance of the PALKNN model is investigated with OpenRoad Traffic Statistics dataset, Great Britain, UK. This paper enhanced thetraffic flow prediction for every hour of a day with a minimal error value.An extensive experimental analysis was performed on the benchmark dataset.The evaluated results indicate the significant improvement of the proposedPALKNN model over the recent approaches such as KNN, SARIMA, LogisticRegression, RNN, and LSTM in terms of root mean square error (RMSE)of 2.07%, mean square error (MSE) of 4.1%, and mean absolute error (MAE)of 2.04%.

Short Term Electric Load Prediction by Incorporation of Kernel into Features Extraction Regression Technique

Accurate load prediction plays an important role in smart power management system, either for planning, facing the increasing of load demand, maintenance issues, or power distribution system. In order to achieve a reasonable prediction, authors have applied and compared two features extraction technique presented by kernel partial least square regression and kernel principal component regression, and both of them are carried out by polynomial and Gaussian kernels to map the original features’ to high dimension features’ space, and then draw new predictor variables known as scores and loadings, while kernel principal component regression draws the predictor features to construct new predictor variables without any consideration to response vector. In contrast, kernel partial least square regression does take the response vector into consideration. Models are simulated by three different cities’ electric load data, which used historical load data in addition to weekends and holidays as common predictor features for all models. On the other hand temperature has been used for only one data as a comparative study to measure its effect. Models’ results evaluated by three statistic measurements, show that Gaussian Kernel Partial Least Square Regression offers the more powerful features and significantly can improve the load prediction performance than other presented models.

基于VMD-SE的电力负荷分量的多特征短期预测

为提高电力负荷的预测精度,提出一种基于VMD-SE的电力负荷分量的多特征短期预测方法。首先采用变分模态分解(VMD)将原始负荷分解为一系列模态分量与残差,VMD的分解层数由样本熵值(sample entropy,SE)确定;然后对比原始负荷与模态分量的SE值,重构为平稳分量和波动分量,来降低运算规模;同时利用皮尔逊相关系数来筛选特征变量,删除特征冗余,建立灰狼算法优化后的支持向量回归模型(GWO-SVR)和长短期记忆神经网络(LSTM)分别对平稳分量和波动分量预测;最后以某地区2018—2020年用电负荷为例进行实验。实验证明:此模型精准度高达94.7%,平均绝对百分误差降低到2.98%,具有更好的精准性和适用性。

基于LSTM的机场飞行区活动目标潜在冲突预测

针对机场飞行区冲突不断的问题,提出一种基于长短期记忆(LSTM)网络预测机场飞行区活动目标潜在冲突的方法。根据复杂网络理论,以航空器和车辆2类活动目标为研究对象,建立飞行区活动目标网络,设置网络动态演化模型,输入运行数据计算多个网络特征指标,对指标时间序列进行主成分分析,拟合成潜在冲突指数;利用Keras框架搭建LSTM网络模型,将指标时间序列输入LSTM网络进行训练和预测,并与其他预测方法对比;用西安咸阳机场实际运行数据进行实验,将预测值与真实值进行对比,各项指标预测均方误差分别为1.608%、13.126%、0.072%、0.004%、0.014%。结果表明:通过建立飞行区活动目标网络模型,可以用网络特征指标从不同角度刻画潜在冲突;LSTM网络可以有效预测飞行区活动目标网络的潜在冲突,提醒相关人员预防冲突发生,降低冲突概率。

基于ikPCA-FABAS-KELM的短期风电功率预测

为了增强在短期风电功率预测领域中传统数据驱动机器学习模型的精度,提出基于ikPCA-FABAS-KELM的短期风电功率预测模型.首先,对主成分分析进行改进,提出可逆核主成分分析(ikPCA),在保证数据特征的同时,降低输入数据的复杂度,以提升模型运行速度;其次,引入萤火虫个体吸引策略对天牛须算法(BAS)进行改进,提出FABAS算法;最后,利用FABAS算法对核极限学习机(KELM)的正则化参数C和核参数γ进行寻优,降低人为因素对模型盲目训练的影响,提高模型预测精度.仿真结果显示,提出的预测模型有效提高了传统模型的预测精度.

基于经验模态分解和深度学习的短期风电功率预测

精准的风电功率预测有利于全网电力平衡、系统安全稳定运行和节能减耗。提出一种基于经验模态分解(empirical mode decomposition, EMD)、核主成分分析(kernel principal component analysis, KPCA)和长短期记忆(long short-term memory, LSTM)神经网络的短期风功率预测模型。采用EMD技术将多维气象序列分解为多个固有模态分量,以挖掘原始数据的主要特征并消除噪声;引入KPCA进行降维处理,提取数据的非线性特征;使用LSTM神经网络对特征提取的序列进行学习并完成预测,获得风电功率预测的最终结果。使用所提出的模型对新疆某一风电场风电功率进行预测,将预测结果与其他模型对比。结果表明,该预测模型能改善预测性能,降低风电功率预测误差。

基于EMD-PCA-LSTM的短期风电功率预测研究

精准的风电功率预测有利于全网电力平衡、系统安全稳定运行和节能减耗,提出一种基于EMD-PCA-LSTM的短期风电功率预测模型。先采用经验模态分解技术将多维气象序列分解为多个固有模态分量,以挖掘原始数据的主要特征并消除噪声。再引入主成分分析进行降维处理,提取数据的非线性特征,最后使用长短期记忆神经网络进行预测。通过与多种预测模型进行比较,证明了该模型在预测精度方面的卓越表现。

基于优化LSTM模型的风力机叶片剩余使用寿命预测

针对传统寿命预测方法计算复杂、耗时且不具普适性等问题,提出一种基于优化长短期记忆网络(LSTM)的风力机叶片剩余使用寿命(RUL)预测模型。首先,将多维传感器监测数据可视化,以观察数据特征并进行初次特征筛选。然后,对筛选后的数据进行归一化处理,并使用主成分分析法(PCA)进行数据融合,以去除冗余信息和降低特征维度。其次,使用自适应矩估计(AME)算法为不同网络参数提供独立的自适应性学习率;使用平滑平均绝对误差(SMAE)损失函数来综合两种传统回归损失函数的特点。最后,经过多次试验选定合适的LSTM层数及神经元数,并以复杂系统的多尺度时序监测数据为算例对模型进行试验验证。试验结果表明,在一种故障模式下,优化LSTM预测模型相较于其他传统机器学习模型在评价指标及预测误差分布情况上占优,表明该文所提模型具有更高的准确性及稳定性。

时间特征与空间特征融合的轻量网络故障诊断方法

为了解决多传感器数据间存在信息交叉、特征重复,导致模型训练精度低的问题,对滚动轴承在声辐射信号下的故障诊断进行了研究,提出了一种时间特征与空间特征融合的轻量网络故障诊断(SF-TFNet)方法。首先,利用卷积神经网络提取了原始轴承声阵列信号的空间特征(SFs),使用长短时记忆网络(LSTM)提取了声阵列信号中的时域特征(TFs),并对提取的SFs和TFs进行了特征融合,生成了新的特征矩阵;然后,为了消除融合特征带来的重叠特征和信息冗余问题,引入了基于核的主成分分析(KPCA)方法对新生成的特征矩阵进行了非线性降维,去除了特征中的冗余成分,构建了滚动轴承新的时空特征数据集;最后,采用AdaBoost算法对新生成的数据集进行了故障分类,并得到了滚动轴承的最终故障诊断结果。研究结果表明:在半消声室滚动轴承故障实验台测试中,SF-TFNet方法的故障分类精度可以达到99.75%,其分类精度较高、聚类效果明显。在强背景噪声环境下与ResNet、ICNN和AlexNet三种方法进行比较,SF-TFNet方法不仅收敛速度快,而且故障识别精度高,诊断精度最高可达99.25%。为基于多通道的滚动轴承声辐射信号故障诊断提供了理论依据。

基于多源数据融合的分布式光伏聚合超短期预测方法

分布式光伏聚合发电的超短期预测是支撑其功率快速调节的前提保障,由于规模化接入的分布式光伏容量小、分布广,其发电时序特性差异性大、非平稳性强,导致其超短期预测精度难以保证。为此,文章提出基于多源数据融合的分布式光伏聚合超短期预测方法。该方法基于变分模态分解法,充分挖掘分布式光伏聚合发电非平稳性特性,并采用核主成分分析法对引发光伏发电非平稳性的影响因素即温度、湿度、光照、云量等多源数据进行量化解析,同时结合改进的长短期记忆神经网络,创建了多源数据融合方法,实现了分布式光伏聚合发电超短期预测。仿真结果表明,该方法有效提升了模型的预测精度。与传统方法相比,提出的预测方法对随机性波动严重的光伏超短期预测具有显著优势。

考虑上游来水影响的中长期径流预报

雅砻江流域地面气象站点不足、分布不均,难以获得精确的流域面降雨资料,加之传统中长期径流预报模型泛化能力有限,中长期径流预报存在较大瓶颈。充分考虑流域水库间的物理联系,基于上下游水库流量变化在时空上的相似性,对1957年~2020年锦屏一级水库和二滩水库的历史月径流数据进行主成分分析,使用BP人工神经网络、随机森林和支持向量回归3种机器学习方法建立3种径流预报模型,通过决定系数R^(2),合格率Q R以及平均相对误差MRE三项指标构成的评价体系对预测结果进行评估。结果表明,上游水库对于下游水库的入库流量具有显著影响,且3种模型在二滩水库中长期径流预报上均具有较好的预报效果(R^(2)>0.8、Q R>0.7、MRE<0.2)。随机森林模型模拟效果整体优于BP人工神经网络和支持向量回归模型,3种模型均具有较好的实用性,能为流域水资源精细化调度及科学管理提供数据基础。