Research on Fault Early Warning of Wind Turbine Pitch System based on Long Short-Term Memory Neural Network

The prediction of land subsidence is a crucial step for early warning of urban infrastructure damage and timely remedy. However, the performance of most mathematical and empirical prediction models is often compromised by their large number of parameters, complex operational processes and sparsely measured values. Currently, the traditional neural network models are popular and effective, but they cannot accurately discover the characteristic changes of time series data. In this paper, a long short-term memory (LSTM) neural network was proposed to predict the land subsidence of time series Interferometric Synthetic Aperture Radar (InSAR). First, the Persistent Scatterer Interferometric Synthetic Aperture Radar (PS-InSAR) technique was utilized to monitor the time series land subsidence at Beijing Capital International Airport (BCIA) from 2005 to 2010 based on ENVISAT ASAR images with a descending orbit. The results were compared with the existing results to verify the reliability and then used to analyse the temporal and spatial characteristics of the time series land subsidence of the BCIA. Based on the time series InSAR deformation data, the LSTM neural network was used to establish the prediction model of time series InSAR, and the results were compared with those of the Multi-Layer Perceptron (MLP) and Recurrent Neural Network (RNN). The comparison results showed that the LSTM neural network was more accurate than the MLP and RNN on the point scale (the root mean square error was 4.60 mm and the mean absolute error was 3.18 mm), the correlation coefficients between the prediction results of the LSTM neural network and the real InSAR measurement results in 2007 and 2008 were 0.93 mm and 0.96 mm, respectively, indicating that LSTM neural network had better prediction performance. Eventually, based on the land subsidence data of time series InSAR from 2006 to 2010, the LSTM neural network was applied to predict the BCIA time series land subsidence in 2011. The results predicted that cumulative subsidence in September 2011 would reach a maximum of 350 mm. Therefore, the LSTM neural network is a potentially effective prediction method, which can replace numerical or empirical models in the absence of detailed hydrogeological data. Moreover, its prediction results can be used to assist decision-making, early warning and hazard relief.

Since it is one of the world's most significant financial markets, the foreign exchange (Forex) market has attracted a large number of investors. Accurately anticipating the forex trend has remained a popular but difficult issue to aid Forex traders' trading decisions. It is always a question of how precise a Forex prediction can be because of the market's tremendous complexity. The fast advancement of machine learning in recent decades has allowed artificial neural networks to be effectively adapted to several areas, including the Forex market. As a result, a slew of research articles aimed at improving the accuracy of currency forecasting has been released. The Long Short-Term Memory (LSTM) neural network, which is a special kind of artificial neural network developed exclusively for time series data analysis, is frequently used. Due to its high learning capacity, the LSTM neural network is increasingly being utilized to predict advanced Forex trading based on previous data. This model, on the other hand, can be improved by stacking it. The goal of this study is to choose a dataset using the Hurst exponent, then use a two-layer stacked Long Short-Term Memory (TLS-LSTM) neural network to forecast the trend and conduct a correlation analysis. The Hurst exponent (h) was used to determine the predictability of the Australian Dollar and United States Dollar (AUD/USD) dataset. TLS-LSTM algorithm is presented to improve the accuracy of Forex trend prediction of Australian Dollar and United States Dollar (AUD/USD). A correlation study was performed between the AUD/USD, the Euro and the Australian Dollar (EUR/AUD), and the Australian Dollar and the Japanese Yen (AUD/JPY) to see how AUD/USD movement affects EUR/AUD and AUD/JPY. The model was compared with Single-Layer Long Short-Term (SL-LSTM), Multilayer Perceptron (MLP), and Complete Ensemble Empirical Mode Decomposition with Adaptive Noise–Improved Firefly Algorithm Long Short-Term Memory. Based on the evaluation metrics Mean Square Error (MSE), Root Mean Square Error, and Mean Absolute Error, the suggested TLS-LSTM, whose data selection is based on the Hurst exponent (h) value of 0.6026, outperforms SL-LSTM, MLP, and CEEMDAN-IFALSTM. The correlation analysis conducted shows both positive and negative relations between AUD/USD, EUR/AUD, and AUD/JPY which means that a change in AUD/USD will affect EUR/AUD and AUD/JPY as recorded depending on the magnitude of the correlation coefficient (r).

This paper proposes a novel method for the real-time prediction of photovoltaic (PV) power output by integrating phase space reconstruction (PSR), improved grey wolf optimization (GWO), and long short-term memory (LSTM) neural networks. The proposed method consists of three main steps. First, historical data are denoised and features are extracted using singular spectrum analysis (SSA) and complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN). Second, improved grey wolf optimization (GWO) is employed to optimize the key parameters of phase space reconstruction (PSR) and long short-term memory (LSTM) neural networks. Third, real-time predictions are made using LSTM neural networks, with dynamic updates of training data and model parameters. Experimental results demonstrate that the proposed method has significant advantages in both prediction accuracy and speed. Specifically, the proposed method achieves a mean absolute percentage error (MAPE) of 3.45%, significantly outperforming traditional machine learning models and other neural network-based approaches. Compared with seven alternative methods, our method improves prediction accuracy by 15% to 25% and computational speed by 20% to 30%. Additionally, the proposed method exhibits excellent prediction stability and adaptability, effectively handling the nonlinear and chaotic characteristics of PV power.

Shared bicycles have strong liquidity and high randomness. In order to more accurately predict the short term demand for shared bicycles, the long short-term memory (LSTM) neural network model was used as the tool to predict, on the basis of crawling the weather characteristics data of bicycles shared by Citi Bike in New York City, and analyzing the influence of time factor and meteorological factors on the demand for bicycles. On the purpose of verify our method, the traditional RNN and back propagation (BP) neural network were compared with LSTM neural network. The experimental results show that the main factors affecting the demand for shared bicycles including temperature, holidays, seasons and morning and evening peak time periods. Compared with traditional BP neural network and cyclic neural network RNN algorithm, LSTM has high robustness and strong generalization ability. The prediction result curve is consistent with the real result curve, the prediction accuracy is the highest with 0.860 and the root mean square error is the smallest with 0.090. It can be seen that the LSTM model can be used to predict the short-term demand for shared bicycles.

The current study aims to develop a new technique for the precise identification of Escherichia coli strains, utilizing matrix-assisted laser desorption ionization time-of-flight mass spectrometry (MALDI-TOF MS) combined with a long short-term memory (LSTM) neural network. A total of 48 Escherichia coli strains were isolated and cultured on tryptic soy agar medium for 24 hours for the generation of MALDI-TOF MS spectra. Eight hundred MALDI-TOF MS spectra were obtained per strain, resulting in a database of 38,400 spectra. Fifty percent of the data was utilized for LSTM neural network training, with fine-tuned parameters for strain-level identification. The other half served as the test set to assess model performance. Traditional PCA dimension reduction of MALDI-TOF MS spectra indicated 47 out of 48 strains to be unclassifiable. In contrast, the LSTM neural network demonstrated remarkable efficacy. After 20 training epochs, the model achieved a loss value of 0.0524, an accuracy of 0.999, a precision of 0.985, and a recall of 0.982. When tested on the unseen data, the model attained an overall accuracy of 92.24%. The integration of MALDI-TOF MS and LSTM neural network markedly enhances the identification of Escherichia coli strains. This innovative approach offers an effective and accurate tool for MALDI-TOF MS-based strain-level identification, thus expanding the analytical capabilities of microbial diagnostics.

The use of an inertial measurement unit (IMU) to measure the motion data of the upper limb is a mature method, and the IMU has gradually become an important device for obtaining information sources to control assistive prosthetic hands. However, the control method of the assistive prosthetic hand based on the IMU often has problems with high delay. Therefore, this paper proposes a method for predicting the action intentions of upper limbs based on a long short-term memory (LSTM) neural network. First, the degree of correlation between palm movement and arm movement is compared, and the Pearson correlation coefficient is calculated. The correlation coefficients are all greater than 0.6, indicating that there is a strong correlation between palm movement and arm movement. Then, the motion state of the upper limb is divided into the acceleration state, deceleration state and rest state. The rest state of the upper limb is used as a sign to control the assistive prosthetic hand. Using the LSTM to identify the motion state of the upper limb, the accuracy rate is 99%. When predicting the action intention of the upper limb based on the angular velocity of the shoulder and forearm, the LSTM is used to predict the angular velocity of the palm, and the average prediction error of palm motion is 1.5 rad/s. Finally, the feasibility of the method is verified through experiments, in the form of holding an assistive prosthetic hand to imitate a disabled person wearing a prosthesis. The assistive prosthetic hand is used to reproduce foot actions, and the average delay time of foot action was 0.65 s, which was measured by using the method based on the LSTM neural network. However, the average delay time of the manipulator control method based on threshold analysis is 1.35 s. Our experiments show that the prediction method based on the LSTM can achieve low prediction error and delay.

As one of the four financial pillars, insurance has the functions of risk diversification, loss compensation, financing and social management. It is of great practical significance to predict the level of premium income in the new normal of economy. In this paper, long short-term memory (LSTM) neural network was innovatively applied to the study of premium income prediction. The monthly data of China's premium income from January 1999 to October 2019 was selected for prediction, and the prediction results were compared with BP neural network. The results show that LSTM model can accurately predict premium income, and its performance is better than BP neural network.

When forecasting ship movements, the random errors of the inertial navigation system (INS) seriously affect the accuracy of general prediction methods. In actual measurement, the main causes of the random errors are electrostatic bias and micro-electric disturbance. In response to this problem, a novel type of dual-pass Long Short-Term Memory (LSTM) neural network architecture is developed, on the basis of regular LSTM neural network. In the designed dual-pass LSTM neural network, the random drift and the noise residual of the INS are regarded as a autoregressive moving average (ARMA) and generalized autoregressive conditional heteroskedasticity (GARCH) model. Through dual-pass layers, the prediction of drift and the correction of residual errors are realized respectively in the same time. The simulation of ship heave motion was carried out on the ship motion simulation platform, and the real-time datas which are measured by the INS are inputted to the trained dual-pass LSTM netural network. The experiment proved that, when training the same source datas offline, the average Root Mean Squared Error (RMSE) percentage of conventional LSTM network was 3.94%, but when training different source datas or training online, the prediction accuracy obvious decline. In contrast, the average RMSE percentage of the dual-pass LSTM neural network was 1.05% when training offline and 1.12% when training online. Compared with conventional LSTM networks, the dual-pass LSTM network is more targeted and has better adaptability in the field of ship-motion prediction, and this network restores the motion prediction to the actual trajectory of a ship more accurately.

Abstract. This study investigates the ability of long short-term memory (LSTM) neural networks to perform streamflow prediction at ungauged basins. A set of state-of-the-art, hydrological model-dependent regionalization methods are applied to 148 catchments in northeast North America and compared to an LSTM model that uses the exact same available data as the hydrological models. While conceptual model-based methods attempt to derive parameterizations at ungauged sites from other similar or nearby catchments, the LSTM model uses all available data in the region to maximize the information content and increase its robustness. Furthermore, by design, the LSTM does not require explicit definition of hydrological processes and derives its own structure from the provided data. The LSTM networks were able to clearly outperform the hydrological models in a leave-one-out cross-validation regionalization setting on most catchments in the study area, with the LSTM model outperforming the hydrological models in 93 % to 97 % of catchments depending on the hydrological model. Furthermore, for up to 78 % of the catchments, the LSTM model was able to predict streamflow more accurately on pseudo-ungauged catchments than hydrological models calibrated on the target data, showing that the LSTM model's structure was better suited to convert the meteorological data and geophysical descriptors into streamflow than the hydrological models even calibrated to those sites in these cases. Furthermore, the LSTM model robustness was tested by varying its hyperparameters, and still outperformed hydrological models in regionalization in almost all cases. Overall, LSTM networks have the potential to change the regionalization research landscape by providing clear improvement pathways over traditional methods in the field of streamflow prediction in ungauged catchments.

To address the issues of increased pseudorange error fluctuations at reference stations and a sharp decline in the positioning accuracy of mobile stations in Global Navigation Satellite System (GNSS)-denied environments—caused by factors such as high-rise building obstructions and multipath effects in urban vehicle-mounted scenarios—this study proposes a pseudorange error prediction method that integrates a time polynomial and a Long Short-Term Memory (LSTM) neural network, and further achieves Precise Point Positioning (PPP) for mobile stations by incorporating the predicted errors. First, the sources and temporal characteristics of pseudorange errors at GNSS reference stations in urban denied environments are analyzed, confirming that ionospheric delay, tropospheric delay, and multipath effects are the primary sources of these errors. Second, a time polynomial model and an LSTM neural network model are constructed separately to predict the pseudorange errors of reference stations: for the time polynomial model, a sliding window is used to take pseudorange observation errors as input, and the model coefficients are solved via the recursive least squares method; a PPP equation for mobile stations is established, where the predicted pseudorange errors are substituted into the mobile station’s PPP observation equation to correct the observed values, and the recursive least squares method is then applied to solve for the mobile station’s coordinates; for the LSTM model, historical pseudorange error sequences serve as input, gating units are used to capture the long-term temporal dependencies of errors, and the model is trained and optimized using the Backpropagation Through Time (BPTT) algorithm. Finally, simulation experiments based on measured data from urban reference stations demonstrate that, compared with the time polynomial model, the Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) of the pseudorange observation errors predicted by the LSTM model are reduced by 38.72%–85.50% and 35.94%–84.60%, respectively. In GNSS-denied environments, the LSTM neural network prediction model can effectively ensure the positioning accuracy of mobile stations. The findings of this study can effectively mitigate the impact of GNSS-denied environments on positioning accuracy and provide technical support for high-precision urban vehicle-mounted navigation.

This study constructs a model suitable for studying the performance of a Japanese speech recognition translation system based on a long short-term memory (LSTM) neural network. The impact of the matrix on the accuracy and recognition ratio of the speech recognition system is considered. This study provides a general introduction to the LSTM neural network, gives an overview of a Japanese speech recognition translation system, and presents experimental data to evaluate its performance. Then, the LSTM neural network is recommended for studying the Japanese speech translation recognition system, and a suitable model is established to conduct experiments on the system. By comparing example analyses, the experimental results show that the optimized PLSTM (Part-Aware Long Short-Term Memory) achieved an 8.09% improvement over an unoptimized LSTM network while maintaining recognition accuracy.

Displacement predictions are essential to landslide early warning systems establishment. Most existing prediction methods are focused on finding an individual model that provides a better result. However, the limitation of generalization that is inherent in all models makes it difficult for an individual model to predict different cases accurately. In this study, a novel coupled method was proposed, combining the long short-term memory (LSTM) neural networks and support vector regression (SVR) algorithm with optimal weight. The Shengjibao landslide in the Three Gorges Reservoir area was taken as a case study. At first, the moving average method was used to decompose the cumulative displacement into two components: trend and periodic terms. Single-factor models based on LSTM neural networks and SVR algorithms were used to predict the trend terms of displacement, respectively. Multi-factors LSTM and SVR models were used to predict the periodic terms of displacement. Precipitation, reservoir water level, and previous displacement are considered as the candidate factors for inputs in the models. Additionally, ensemble models based on the SVR algorithm are used to predict the optimal weight to combine the results of the LSTM and SVR models. The results show that the LSTM models display better performance than SVR models; the ensemble model with optimal weight outperforms other models. The prediction accuracy can be further improved by also considering results from multiple models.

As construction technology and project management develop, structural monitoring systems become increasingly important for ensuring large-span spatial structure safety during construction and operation. However, most of the sensors and monitoring equipment in monitoring systems are poorly serviced, resulting in frequent abnormal monitoring data, which directly leads to challenges in data analysis and structural safety assessment. In this paper, a structural response recovery method based on a long short-term memory (LSTM) neural network is proposed by studying the autocorrelation of data and the spatial correlations among data at multiple measurement points. The effectiveness and robustness of the proposed method are verified using the monitored stress data for a grid structure jacking construction process, and the influence of different data loss rates on the recovery accuracy is analysed. The recovery models are compared using a support vector machine and a Multi-Layer Perception (MLP) neural network. The proposed method can effectively restore missing data; notably, the MSE index is 0.6, and the MAPE is below 15%. The data restoration method based on the LSTM neural network is more accurate than the traditional method. Finally, the repair applicability of various types of monitored data is verified using the monitoring data from Hall F of Qingdao Jiao-dong International Airport under typhoon conditions.

On-site earthquake early warning techniques, which issue alerts based on seismic waves measured at a single station, are promising, and have performed quite successfully during some damaging earthquakes. Conventionally, most existing techniques extract several P-wave features from the first few seconds of seismic waves after the trigger to predict the intensity or destructiveness of an incoming earthquake. This type of technique neglects the behavior of temporal varying features within P waves. In other words, the characteristics of data sequences are not considered. In this study, a long short-term memory (LSTM) neural network, which is capable of learning order dependence in seismic waves, is employed to predict the peak ground acceleration (PGA) of the coming earthquake. A dense LSTM architecture is proposed and a large data set of earthquakes is used to train the LSTM model. The general performance of the LSTM model indicated that the predicted PGA values are quite promising but are generally overestimated. However, the predicted PGA of the Chi-Chi earthquake data set, whose fault rupture is complex and long, using the proposed LSTM model is more accurate than the PGA predicted in a previous study using a support vector regression approach. In addition, an alternative alert criterion, which issues alerts when the predicted PGA exceeds the threshold in successive time windows, is presented, and the performance of the proposed LSTM model when different PGA thresholds are considered is also discussed.

To meet the demand of accurate water level prediction of the reservoir in Liuxihe River Basin, this paper proposes an improved long short-term memory (LSTM) neural network based on the Bayesian optimization algorithm and wavelet decomposition coupling. Based on the improved model, the water levels of Liuxihe Reservoir and Huanglongdai Reservoir are simulated and predicted by the 1 h prediction length, and the prediction accuracy of the improved model is verified separately by the 3, 6 and 12 h prediction lengths. The results show that: first, Bayesian optimization coupling can significantly reduce the average absolute error and root mean square error of the model and improve the overall prediction accuracy, but this algorithm is insufficient in the optimization of model extremum; Wavelet decomposition coupling can significantly reduce the outliers in model prediction and improve the accuracy of extremum, but it plays relatively weaker role in the overall optimization of the model. Second, by the prediction lengths of 1, 3, 6 and 12 h, the improved model based on the LSTM neural network and coupled with Bayesian optimization and wavelet decomposition is superior to Bayesian optimization and wavelet decomposition coupling model in overall prediction accuracy and prediction accuracy of extremum.