Slope stability prediction based on a long short-term memory neural network:comparisons with convolutional neural networks,support vector machines and random forest models

The numerical simulation and slope stability prediction are the focus of slope disaster research.Recently,machine learning models are commonly used in the slope stability prediction.However,these machine learning models have some problems,such as poor nonlinear performance,local optimum and incomplete factors feature extraction.These issues can affect the accuracy of slope stability prediction.Therefore,a deep learning algorithm called Long short-term memory(LSTM)has been innovatively proposed to predict slope stability.Taking the Ganzhou City in China as the study area,the landslide inventory and their characteristics of geotechnical parameters,slope height and slope angle are analyzed.Based on these characteristics,typical soil slopes are constructed using the Geo-Studio software.Five control factors affecting slope stability,including slope height,slope angle,internal friction angle,cohesion and volumetric weight,are selected to form different slope and construct model input variables.Then,the limit equilibrium method is used to calculate the stability coefficients of these typical soil slopes under different control factors.Each slope stability coefficient and its corresponding control factors is a slope sample.As a result,a total of 2160 training samples and 450 testing samples are constructed.These sample sets are imported into LSTM for modelling and compared with the support vector machine(SVM),random forest(RF)and convo-lutional neural network(CNN).The results show that the LSTM overcomes the problem that the commonly used machine learning models have difficulty extracting global features.Furthermore,LSTM has a better prediction performance for slope stability compared to SVM,RF and CNN models.

Device Anomaly Detection Algorithm Based on Enhanced Long Short-Term Memory Network

The problems in equipment fault detection include data dimension explosion,computational complexity,low detection accuracy,etc.To solve these problems,a device anomaly detection algorithm based on enhanced long short-term memory(LSTM)is proposed.The algorithm first reduces the dimensionality of the device sensor data by principal component analysis(PCA),extracts the strongly correlated variable data among the multidimensional sensor data with the lowest possible information loss,and then uses the enhanced stacked LSTM to predict the extracted temporal data,thus improving the accuracy of anomaly detection.To improve the efficiency of the anomaly detection,a genetic algorithm(GA)is used to adjust the magnitude of the enhancements made by the LSTM model.The validation of the actual data from the pumps shows that the algorithm has significantly improved the recall rate and the detection speed of device anomaly detection,with the recall rate of 97.07%,which indicates that the algorithm is effective and efficient for device anomaly detection in the actual production environment.

Long Short-Term Memory Recurrent Neural Network-Based Acoustic Model Using Connectionist Temporal Classification on a Large-Scale Training Corpus

A Long Short-Term Memory(LSTM) Recurrent Neural Network(RNN) has driven tremendous improvements on an acoustic model based on Gaussian Mixture Model(GMM). However, these models based on a hybrid method require a forced aligned Hidden Markov Model(HMM) state sequence obtained from the GMM-based acoustic model. Therefore, it requires a long computation time for training both the GMM-based acoustic model and a deep learning-based acoustic model. In order to solve this problem, an acoustic model using CTC algorithm is proposed. CTC algorithm does not require the GMM-based acoustic model because it does not use the forced aligned HMM state sequence. However, previous works on a LSTM RNN-based acoustic model using CTC used a small-scale training corpus. In this paper, the LSTM RNN-based acoustic model using CTC is trained on a large-scale training corpus and its performance is evaluated. The implemented acoustic model has a performance of 6.18% and 15.01% in terms of Word Error Rate(WER) for clean speech and noisy speech, respectively. This is similar to a performance of the acoustic model based on the hybrid method.

基于Transformer-LSTM的闽南语唇语识别

针对端到端句子级闽南语唇语识别的问题,提出一种基于Transformer和长短时记忆网络(LSTM)的编解码模型.编码器采用时空卷积神经网络及Transformer编码器用于提取唇读序列时空特征,解码器采用长短时记忆网络并结合交叉注意力机制用于文本序列预测.最后,在自建闽南语唇语数据集上进行实验.实验结果表明:模型能有效地提高唇语识别的准确率.

Prophet-LSTM组合模型在运输航空征候预测中的应用

为准确预测中国运输航空征候万时率,提出了一种将时间序列模型和神经网络模型组合的预测方法。首先,利用2008年1月—2020年12月的运输航空征候万时率数据建立Prophet模型,使用RStudio软件进行模型拟合,获取运输航空征候万时率的线性部分;其次,利用长短期记忆网络(Long Short-Term Memory,LSTM)建模,获取运输航空征候万时率的非线性部分;最后,利用方差倒数法建立Prophet-LSTM组合模型,使用建立的组合模型对2021年1—12月运输航空征候万时率进行预测,将预测结果与实际值进行对比验证。结果表明,Prophet-LSTM组合模型的EMA、EMAP、ERMS分别为0.0973、16.1285%、0.1287。相较于已有的自回归移动平均(Auto Regression Integrated Moving Average,ARIMA)+反向传播神经网络(Back Propagation Neural Network,BPNN)组合模型和GM(1,1)+ARIMA+LSTM组合模型,Prophet-LSTM组合模型的EMA、EMAP、ERMS分别减小了0.0259、10.4874百分点、0.0143和0.0128、2.0599百分点、0.0086,验证了Prophet-LSTM组合模型的预测精度更高,性能更优良。

基于LSTM模型的船舶材料成本滚动预测

船舶建造周期长、材料成本占比大,易受大宗商品价格指数和汇率等多个因素的影响,造成实际完工成本与报价估算存在较大误差的情况。采用灰色关联分析(Grey Correlation Analysis,GCA)方法识别材料成本的影响因素,基于长短期记忆网络(Long Short-Term Memory,LSTM)模型构建船舶材料成本滚动预测模型,并使用某造船企业53艘64000 t散货船63个月的材料成本数据和对应的影响因素数据进行试验分析。结果表明,预测数据与实际数据误差在可接受范围内,可证明所选择方法和构建模型的有效性。研究结果对制造过程的成本实时预测和控制具有现实意义。

利用长短期记忆网络LSTM对赤道太平洋海表面温度短期预报

海表面温度作为海洋中一个最重要的变量,对全球气候、海洋生态等有很大的影响,因此十分有必要对海表面温度(SST)进行预报。深度学习具备高效的数据处理能力,但目前利用深度学习对整个赤道太平洋的SST短期预报及预报技巧的研究仍较少。本文基于最优插值海表面温度(OISST)的日平均SST数据,利用长短期记忆(LSTM)网络构建了未来10天赤道太平洋(10°S~10°N,120°E~80°W)SST的逐日预报模型。LSTM预报模型利用1982~2010年的观测数据进行训练,2011~2020年的观测数据作为初值进行预报和检验评估。结果表明:赤道太平洋东部地区预报均方根误差(RMSE)大于中、西部,东部预报第1天RMSE为0.6℃左右,而中、西部均小于0.3℃。在不同的年际变化位相,预报RMSE在拉尼娜出现时期最大,正常年份次之,厄尔尼诺时期最小,RMSE在拉尼娜时期比在厄尔尼诺时期可达20%。预报偏差整体表现为东正、西负。相关预报技巧上,中部最好,可预报天数基本为10天以上,赤道冷舌附近可预报天数为4~7天,赤道西边部分地区可预报天数为3天。预报模型在赤道太平洋东部地区各月份预报技巧普遍低于西部地区,相比较而言各区域10、11月份预报技巧最低。总的来说,基于LSTM构建的SST预报模型能很好地捕捉到SST在时序上的演变特征,在不同案例中预报表现良好。同时该预报模型依靠数据驱动,能迅速且较好地预报未来10天以内的日平均SST的短期变化。

Navigation jamming signal recognition based on long short-term memory neural networks

This paper introduces the time-frequency analyzed long short-term memory(TF-LSTM) neural network method for jamming signal recognition over the Global Navigation Satellite System(GNSS) receiver. The method introduces the long shortterm memory(LSTM) neural network into the recognition algorithm and combines the time-frequency(TF) analysis for signal preprocessing. Five kinds of navigation jamming signals including white Gaussian noise(WGN), pulse jamming, sweep jamming, audio jamming, and spread spectrum jamming are used as input for training and recognition. Since the signal parameters and quantity are unknown in the actual scenario, this work builds a data set containing multiple kinds and parameters jamming to train the TF-LSTM. The performance of this method is evaluated by simulations and experiments. The method has higher recognition accuracy and better robustness than the existing methods, such as LSTM and the convolutional neural network(CNN).

基于深度AttLSTM网络的脱硫过程建模

脱硫过程是具有高度动态非线性和较大延迟时间的复杂工业过程,为了解决烟气脱硫过程的建模问题,设计了注意力机制下的深度长短期记忆(attention mechanism-based long short-term memory,AttLSTM)网络,并基于该网络设计自动编码器,完成脱硫过程异常点的检测。该文首次提出使用AttLSTM网络自编码器对脱硫过程进行离群点检测,并且该网络模型同样首次应用于脱硫过程的辨识任务中。从更深的意义上讲,该文尝试使用深度学习模型对复杂系统进行辨识,所建立的AttLSTM网络之前未出现在系统辨识领域,该网络的出现可以丰富辨识模型的选择,同时为人工智能技术在系统辨识领域和控制领域的应用与推广提供参考。实验结果表明,相比于之前文献出现的脱硫过程建模方法,所提方法在不同性能指标上均具有更好的表现,由此可以证明深度AttLSTM网络在脱硫场景下的有效性。

基于SSA_(n)-SSA_(l)-LSTM的短期空调负荷预测模型

本文提出了一种奇异谱分析(SSA_(n))和麻雀搜索算法(SSA_(l))优化的长短期记忆网络(LSTM)的组合空调负荷预测模型。使用皮尔逊相关系数和主成分分析法对输入特征进行挑选和处理,以消除特征之间的冗余性和相关性。针对空调负荷的波动性和随机性,采用SSA_(n)将空调负荷分解为多个分量。同时针对LSTM超参数设置的问题,采用SSA_(l)对模型进行优化,使用优化后的LSTM对各个分量进行预测,对预测结果进行重构。利用办公建筑和医疗建筑的空调负荷数据对模型进行了验证和分析。研究发现,与其他模型相比,SSA_(n)-SSA_(l)-LSTM模型表现最好,在预测办公建筑空调负荷时决定系数(R^(2))高达0.996 7,平均绝对百分比误差(MAPE)、平均绝对误差(MAE)和均方根误差(RMSE)分别为0.62%、14.42 kW和18.82 kW,在预测医疗建筑空调负荷时R^(2)高达0.992 7,MAPE、MAE和RMSE分别为0.50%、19.40 kW和25.71 kW。

基于LSTM和ArcGIS的区域输电网污秽状态智能评估方法

为了提高电力系统的污闪预防水平,以北京市区域内架空输电线路绝缘子表面污秽状态的评估方法为研究对象,提出一种基于气象条件和盐密数据分布的区域污秽状态智能评估方法。首先,分析影响绝缘子表面积污的主要外部因素,并利用灰色关联分析法选取出6种关联度最大的影响因素。其次,建立一种基于长短期记忆神经网络的绝缘子污秽度预测模型,该模型的预测结果与实测数据吻合度较高,可以很好地反映电网绝缘子的污秽状态。最后,将气象条件与地理信息相结合,使用ArcGIS绘制北京地区的污区分布预测图,实现污秽度评估的动态表达,并在校园内搭建微型自然积污平台以验证文中方法。结果表明,所提方法可以实现区域输电网污秽度数据的周期动态监测,提前预判重度污区出现位置,有助于提升电网防污闪工作的预见性、精准性及智能化水平。

A multi-source information fusion layer counting method for penetration fuze based on TCN-LSTM

When employing penetration ammunition to strike multi-story buildings,the detection methods using acceleration sensors suffer from signal aliasing,while magnetic detection methods are susceptible to interference from ferromagnetic materials,thereby posing challenges in accurately determining the number of layers.To address this issue,this research proposes a layer counting method for penetration fuze that incorporates multi-source information fusion,utilizing both the temporal convolutional network(TCN)and the long short-term memory(LSTM)recurrent network.By leveraging the strengths of these two network structures,the method extracts temporal and high-dimensional features from the multi-source physical field during the penetration process,establishing a relationship between the multi-source physical field and the distance between the fuze and the target plate.A simulation model is developed to simulate the overload and magnetic field of a projectile penetrating multiple layers of target plates,capturing the multi-source physical field signals and their patterns during the penetration process.The analysis reveals that the proposed multi-source fusion layer counting method reduces errors by 60% and 50% compared to single overload layer counting and single magnetic anomaly signal layer counting,respectively.The model's predictive performance is evaluated under various operating conditions,including different ratios of added noise to random sample positions,penetration speeds,and spacing between target plates.The maximum errors in fuze penetration time predicted by the three modes are 0.08 ms,0.12 ms,and 0.16 ms,respectively,confirming the robustness of the proposed model.Moreover,the model's predictions indicate that the fitting degree for large interlayer spacings is superior to that for small interlayer spacings due to the influence of stress waves.

Real-time UAV path planning based on LSTM network

To address the shortcomings of single-step decision making in the existing deep reinforcement learning based unmanned aerial vehicle(UAV)real-time path planning problem,a real-time UAV path planning algorithm based on long shortterm memory(RPP-LSTM)network is proposed,which combines the memory characteristics of recurrent neural network(RNN)and the deep reinforcement learning algorithm.LSTM networks are used in this algorithm as Q-value networks for the deep Q network(DQN)algorithm,which makes the decision of the Q-value network has some memory.Thanks to LSTM network,the Q-value network can use the previous environmental information and action information which effectively avoids the problem of single-step decision considering only the current environment.Besides,the algorithm proposes a hierarchical reward and punishment function for the specific problem of UAV real-time path planning,so that the UAV can more reasonably perform path planning.Simulation verification shows that compared with the traditional feed-forward neural network(FNN)based UAV autonomous path planning algorithm,the RPP-LSTM proposed in this paper can adapt to more complex environments and has significantly improved robustness and accuracy when performing UAV real-time path planning.

DPAL-BERT:A Faster and Lighter Question Answering Model

Recent advancements in natural language processing have given rise to numerous pre-training language models in question-answering systems.However,with the constant evolution of algorithms,data,and computing power,the increasing size and complexity of these models have led to increased training costs and reduced efficiency.This study aims to minimize the inference time of such models while maintaining computational performance.It also proposes a novel Distillation model for PAL-BERT(DPAL-BERT),specifically,employs knowledge distillation,using the PAL-BERT model as the teacher model to train two student models:DPAL-BERT-Bi and DPAL-BERTC.This research enhances the dataset through techniques such as masking,replacement,and n-gram sampling to optimize knowledge transfer.The experimental results showed that the distilled models greatly outperform models trained from scratch.In addition,although the distilled models exhibit a slight decrease in performance compared to PAL-BERT,they significantly reduce inference time to just 0.25%of the original.This demonstrates the effectiveness of the proposed approach in balancing model performance and efficiency.

Track correlation algorithm based on CNN-LSTM for swarm targets

The rapid development of unmanned aerial vehicle(UAV) swarm, a new type of aerial threat target, has brought great pressure to the air defense early warning system. At present, most of the track correlation algorithms only use part of the target location, speed, and other information for correlation.In this paper, the artificial neural network method is used to establish the corresponding intelligent track correlation model and method according to the characteristics of swarm targets.Precisely, a route correlation method based on convolutional neural networks (CNN) and long short-term memory (LSTM)Neural network is designed. In this model, the CNN is used to extract the formation characteristics of UAV swarm and the spatial position characteristics of single UAV track in the formation,while the LSTM is used to extract the time characteristics of UAV swarm. Experimental results show that compared with the traditional algorithms, the algorithm based on CNN-LSTM neural network can make full use of multiple feature information of the target, and has better robustness and accuracy for swarm targets.

基于LSTM-AEKF算法的锂离子电池SOC估计

针对扩展卡尔曼滤波(Extended Kalman filter,EKF)算法与长短期记忆网络(Long Short-Term Memory,LSTM)不能准确估计锂离子电池荷电状态(State of Charge,SOC)的问题,本文提出了一种基于二阶戴维宁(Thevenin)的等效电路模型,采用自适应扩展卡尔曼滤波(Adaptve Extended Kalman filter,AEKF)与LSTM相结合的SOC估计算法,即LSTM-AEKF算法。在二阶RC等效电路模型的基础上建立整数阶模型,并采用EKF算法辨识模型参数,采用LSTM-AEKF算法估计SOC,与AEKF算法、LSTM算法进行比较。根据马里兰大学公开数据集进行测试,结果表明,与传统方法相比,LSTM-AEKF算法估计SOC的平均绝对误差(Mean Absolute Error,MAE)与均方根误差(Root Mean Square Error,RMSE)分别下降了1.23%、1.5%,基于二阶RC模型的LSTM-AEKF算法可以有效估计SOC。

基于GMM-KNN-LSTM的烧结矿化学指标预测

针对烧结矿化学指标检测频率低导致无标签样本无法被机器学习利用的问题,提出了一种充分利用样本中有用信息的烧结矿化学指标预测模型.首先,结合高斯混合模型(GMM)和K-近邻(KNN)算法,将无标签样本转化为有标签样本,然后与长短期记忆(LSTM)单元相结合,用于预测烧结矿的总铁质量分数、FeO质量分数和碱度3个化学指标.通过与反向传播神经网络(BPNN)、循环神经网络(RNN)和LSTM三种模型对比,结果表明所建模型具有较低的预测误差.总铁质量分数和FeO质量分数的预测命中率在允许误差±0.5%内时分别达到98.73%和95.33%,碱度的预测命中率在允许误差±0.05内为98.13%,展现了较高的预测精度.

基于GMM和GA-LSTM的稀土熔盐电解过程原料含量状态识别模型

在高温高风险的稀土熔盐电解工艺中,为了实现稀土熔盐电解过程原料含量状态的智能识别,提出了一种基于混合高斯背景建模(GMM)和遗传算法优化的长短期记忆神经网络(GA-LSTM)的分类模型。模型通过GMM算法、R通道自适应滤波和中值滤波准确提取图像的火焰前景和特征,以量化熔盐电解反应的剧烈程度,进而判断稀土熔盐电解处于原料含量过多或含量正常状态;然后利用GA-LSTM神经网络建立熔盐表面火焰特征和稀土熔盐电解过程原料含量状态的非线性映射关系。结果表明:模型的识别精度高达99.79%,具有较好的泛化性,为实现稀土熔盐电解工艺自动化提供了一定的参考价值。

基于LSTM神经网络模型分析预测钢材价格

钢价时间序列具有明显的长短记忆特征,故以施工企业安徽省的项目部实际采购规格型号为HRB400Eφ16螺纹钢的金额为例,科学合理的运用LSTM模型对其建模,并与传统的ARIMA模型进行对比,结果表明LSTM模型的预测相对误差为0.03,比ARIMA模型预测精度更好,适合用来预测建筑钢材价格。

基于K-means-LSTM模型的证券股价预测

鉴于股票数据具有非平稳、非线性等特征,传统的统计模型无法精准预测股票价格的未来趋势。针对这个问题,构建一种混合深度学习方法来提高股票预测性能。首先,通过将距离算法修改为DTW(动态时间归整),令K-means聚类算法拓展为更适用于时间序列数据的K-means-DTW,聚类出价格趋势相似的证券;然后,通过聚类数据来训练LSTM(长短时记忆网络)模型,以实现对单支股票价格的预测。实验结果表明,混合模型K-means-LSTM表现出更好的预测性能,其预测精度和稳定性均优于单一LSTM模型。