Proposed Prediction Method Research Articles

GPR-based prediction and uncertainty quantification for bearing capacity of steel tubular members considering semi-rigid connections in transmission towers

In this paper, the effect of semi-rigid connections on the bearing capacity of steel tubular members in transmission towers is investigated by the numerical analysis based on experimental validation and the metamodel-based prediction method. Especially, for the stability bearing capacity of steel tubular members considering semi-rigid connections (STM-SRC), a prediction method based on the Gaussian process regression (GPR) model is proposed to accurately predict its value and to efficiently quantify its uncertainty. Firstly, on the basis of the development of mechanical model of STM-SRC in transmission towers, the experimental and numerical studies on STM-SRC are conducted. Then, a dataset of 1125 samples generated by the validated finite element model is used to train and test the GPR model, and the accuracy of the proposed method based on the GPR model is evaluated. Finally, based on the proposed prediction method and the Monte Carlo simulation, the uncertainty for the stability bearing capacity of STM-SRC is quantified under the probabilistic framework. The results show that the proposed method has high accuracy in predicting the stability bearing capacity of STM-SRC. Meanwhile, the stability bearing capacity of steel tubular members is enhanced and their reliability exhibits the linear increase after considering semi-rigid connections.

Multi-Section Traffic Flow Prediction Based on MLR-LSTM Neural Network.

As the aggravation of road congestion leads to frequent traffic crashes, it is necessary to relieve traffic pressure through traffic flow prediction. As well, the traffic flow of the target road section to be predicted is also closely related to the adjacent road sections. Therefore, in this paper, a prediction method based on the combination of multiple linear regression and Long-Short-Term Memory (MLR-LSTM) is proposed, which uses the incomplete traffic flow data in the past period of time of the target prediction section and the continuous and complete traffic flow data in the past period of time of each adjacent section to jointly predict the traffic flow changes of the target section in a short time. The accurate prediction of future traffic flow changes can be solved based on the model supposed when the traffic flow data of the target road section is partially missing in the past period of time. The accuracy of the prediction results is the same as that of the current mainstream prediction results based on continuous and non-missing target link flow data. Meanwhile, there is a small-scale improvement when the data time interval is short enough. In the case of frequent maintenance of cameras in actual traffic sections, the proposed prediction method is more feasible and can be widely used.

An Improved Energy Detection Scheme Based on Channel Prediction In CR Networks

Cognitive radio is considered as an intelligent wireless communication system proposed to improve the utilization of the radio electromagnetic spectrum. In CR technology the secondary users take the responsibility of dynamically sensing and accessing any unused channels in the spectrum allocated to the licensed users. As spectrum sensing consumes considerable energy, predictive methods for inferring the availability of spectrum holes can reduce energy consumption of the unlicensed users to only sense those channels which are likely to be idle. It also helps to improve the spectrum utilizations. Several prediction techniques have been used to predict spectrum utilization. However, most of current approaches do not consider seasonality in spectrum workload, for example most of the channels are busy during business hours in mobile phone bands. This paper; proposes a channel status predictor based on the multiplicative seasonal model called Holt-Winters’ method. The proposed prediction method has the ability to adapt with changes in trends and seasonal patterns of the sensing observations. Performance analysis and the accuracy of the channel status prediction schemes are investigated.

Research on noise source separation and sound quality prediction for electric powertrain

The overall noise of the electric powertrain (EP) features the characteristics of high-frequency discreteness, abundant orders of harmonics, and serious howling. The consequent poor sound quality problems in the EP are frequently inevitable. In this paper, a complete set of sound quality evaluation system for EP noise signals is established, which closely combines the time-domain separation and sound quality evaluation. The EP noise source separation method in the time domain based on computational auditory scene analysis (CASA) and Robust-independent component analysis (ICA) is proposed to separate and identify EP independent noise sources. Five independent noise source signals in the time domain are then obtained, which could be played back for further psychoacoustic evaluation. The EP sound quality prediction method based on kernel principal component analysis (KPCA) and Lasso regression is proposed to develop the relationship between the subjective and objective quality for EP noise signals. Besides, the dimensionality of the objective evaluation parameters can be significantly reduced from nine to five. The experimental results indicate the superiority of the proposed prediction method to the traditional multiple linear regression approach on predicting the sound quality. A further deduction is made that the harmonic noise (HN) and switching noise (SN) can contribute more to sound quality of the EP overall noise and optimization on them can be a good choice.

A machine learning-based fatigue loads and power prediction method for wind turbines under yaw control

Yaw control is one of the most promising active wake control strategies to maximize the total power generation of wind farms. Meanwhile, structural performance needs to be considered in yaw misalignment in case the adverse structural performance offsets the benefit of yaw control in power enhancement. However, an efficient and accurate prediction method for fatigue loads under yaw control is still lacking. In this study, a machine learning-based prediction method is proposed to accurately estimate the fatigue loads and power of wind turbines under yaw control. Fatigue loads at critical turbine components and corresponding power yields are selected as outputs to reflect the performance of yawed wind turbines. Since most wind turbines (WTs) are sunk into the wake flow of their upstream counterparts, the wake effects are considered with the combination of active yaw control. Besides, the full range of inflow and yaw conditions are taken into account to ensure the accuracy and practicability of the proposed model. A machine learning algorithm, support vector regression (SVR), is tuned and trained to learn the relationships between outputs and inputs. The superiority of the proposed method is verified by comparing it with another machine learning-based model in several metrics. The results show that the proposed prediction method can return high regression coefficients and low deviation, proving its accuracy and robustness. Large yaw angles and high wind speeds are found to be beneficial for further improving the prediction accuracy. The proposed fatigue loads and power prediction method is expected to make contributions to the yaw optimization and therefore benefit the wind farms.

A novel prediction method for protein DNA-binding residues based on neighboring residue correlations

Accurately identifying the protein DNA-binding residues is important for understanding the protein–DNA recognition mechanism and protein function annotation. Many computational methods have been proposed to predict protein–DNA binding residues using protein sequence information; however, for severe imbalanced data like the protein–DNA binding dataset, the under-sampling technique which is applied by most previous methods cannot achieve satisfactory performance. In this study, an adjustment algorithm is proposed to offset the biased prediction results from the classifier. The proposed adjustment algorithm uses the binding probability between the target residue and its neighboring residues to identify more true binding residues which are wrongly predicted as non-binding. The proposed prediction method with adjustment algorithm achieves an area under the ROC curve (AUC) of 0.926 and 0.866 on two benchmark datasets and 0.882 on the independent testing set, which demonstrates that the proposed method can efficiently predict specific residues for protein–DNA interactions.

Time-Series-Based Personalized Lane-Changing Decision-Making Model.

In recent years, autonomous driving technology has been changing from “human adapting to vehicle” to “vehicle adapting to human”. To improve the adaptability of autonomous driving systems to human drivers, a time-series-based personalized lane change decision (LCD) model is proposed. Firstly, according to the characteristics of the subject vehicle (SV) with respect to speed, acceleration and headway, an unsupervised clustering algorithm, namely, a Gaussian mixture model (GMM), is used to identify its three different driving styles. Secondly, considering the interaction between the SV and the surrounding vehicles, the lane change (LC) gain value is produced by developing a gain function to characterize their interaction. On the basis of the recognition of the driving style, this gain value and LC feature parameters are employed as model inputs to develop a personalized LCD model on the basis of a long short-term memory (LSTM) recurrent neural network model (RNN). The proposed method is tested using the US Open Driving Dataset NGSIM. The results show that the accuracy, F1 score, and macro-average area under the curve (macro-AUC) value of the proposed method for LC behavior prediction are 0.965, 0.951 and 0.983, respectively, and the performance is significantly better than that of other mainstream models. At the same time, the method is able to capture the LCD behavior of different human drivers, enabling personalized driving.

A Data-Driven Method for Prediction of Post-Fault Voltage Stability in Hybrid AC/DC Microgrids

Faults are extreme events that canadversely affect the voltages in islanded microgrids. This paper provides a new data-driven methodology for timely prediction of the post-fault voltage stability in hybrid AC/DC microgrids. The proposed method performs a binary classification with delay constraints by processing sequences of the short-time mean squared deviations using a deep learning system. The deep learning system consists of a bidirectional long short-term memory network whose output is a probabilistic voltage instability indicator. When the value of the indicator is non-zero, persistent voltage disturbances are most likely to occur even after the fault clearance. The proposed method enables the microgrid to carry out remedial or preventive actions, such as event-triggered protection and control of distributed energy resources (DERs), which are advantageous to the resilient operation of the microgrids. Extensive and detailed electromagnetic transient (EMT) simulations of a low-voltage hybrid AC/DC microgrid benchmark are analyzed, and the results confirm the effectiveness of the proposed method for online prediction and fast voltage regulation.

A new method for transformer hot-spot temperature prediction based on dynamic mode decomposition

The Accurate prediction of a hot spot temperature (HST) is critical for ensuring the reliable operation of transformers. The existing HST prediction methods are based on the black-box model. They cannot take into account both the real-time prediction and the acquisition of the winding temperature field, and the prediction results are unexplained. Therefore, a new HST prediction method based on dynamic mode decomposition (DMD) is proposed in this study. First, the electromagnetic-thermal-flow coupling model of a transformer winding temperature field was established for a transient calculation. A simulation snapshot set of the winding temperature field was obtained. DMD and DMD dominant modes selection were then performed on the snapshot set. Finally, the HST and winding temperature field distributions at the subsequent times were predicted by the DMD dominant modes and their revolution laws. By comparing the prediction results of the HST and winding temperature field distribution with the simulation and experimental measurement results, the speed and accuracy of the proposed prediction method were verified. The DMD-based prediction method can predict the HST and winding temperature field distribution in a few seconds and has a clear physical meaning. • Transformer model for analysing electromagnetic-thermal-flow coupling is proposed. • Prediction method based on dynamic mode decomposition is proposed. • Hot-spot temperatures and winding temperature fields of transformers are predicted. • An experimental platform is built to verify the validation of the proposed method.

Data-driven fuel cell performance prediction by transfer learning and dynamic time warping

The increase of world energy demand contributes to the development of renewable energy sources. Fuel cells, which use hydrogen to deliver energy, have seen a promising future. Fuel cells have been investigated since the last 50 years but they are still relatively absent for the commercial use due to the large exploitation cost and poor durability. One of the reasons is that the health state of a running fuel cell is hard to evaluate due to the system complexity and insufficient data. To tackle this problem, this paper proposes a data-driven fuel cell performance prediction method based on transfer learning and dynamic time warping. Historical data is trained in the source domain to build a model that can be transferred to the target domain and can be fine-tuned with only a small volume of online measurement. To improve the model recognition, dynamic time warping technology is applied to quantify the similarity between two different time series so that similar instances can be selected to build the neural network prediction model. Results show that, compared to traditional prediction method, the proposed prediction method has improved the prediction accuracy by almost 50%.

An Intelligent Trajectory Prediction Algorithm for Hypersonic Glide Targets Based on Maneuver Mode Identification

Trajectory prediction for hypersonic glide targets is a difficult task that needs to be solved. To improve the prediction precision for hypersonic glide targets, based on the analysis of the target’s maneuver characteristic, an intelligent trajectory prediction algorithm based on the maneuver mode identification is proposed in this paper. Firstly, according to the typical maneuver modes of the target, a group of parameter suitable for maneuver mode identification and parameter estimation is proposed. The proposed maneuver parameters can reflect the maneuvering characteristics of the target than the other control parameters. Then, the rationality of parameters is analyzed. Secondly, using the long-short-term memory network (LSTM), the structure of intelligent trajectory prediction based on maneuver mode identification is proposed. The proposed prediction method is designed to improve the prediction accuracy by combining the target dynamic model with the flight data. Finally, the maneuver trajectory data set is established to train and test the method. For the test data set, when the observation time for the target is 200 s and the prediction time is 150 s, with a fast prediction speed, our method’s average error of spatial distance (AESD) is less than 2.9 km, and the maximum error of spatial distance (MESD) is less than 6.9 km. The result is better than other compared mainstream methods. And it is also proved valid with some observational error.

A Method for Detecting Anomalies in an Electromagnetic Environment Situation Using a Dual-Branch Prediction Network

Electromagnetic environment situation anomaly detection is a prerequisite for electromagnetic threat level assessment, and its research is of great practical value. However, because of the complexity of the electromagnetic environment, electromagnetic environment situation anomaly detection is not efficient. Therefore, we propose a dual-branch prediction network-based electromagnetic environment situation anomaly detection method to predict the future and achieve anomaly detection by fusing different development characteristics of electromagnetic environment situations learned by other branches. We extract the electromagnetic environment situation state and trend features using the manual feature extraction module and mine the electromagnetic environment situation in-depth data distribution features using ConvLSTM, improve the dynamic time regularization model according to the physical characteristics of electromagnetic space, and then provide the anomaly detection method. We experimentally demonstrate the effectiveness of the proposed method in electromagnetic environment situation prediction and anomaly detection accuracy.

Initialization of smooth adaptive neural network weights with a cultural algorithm for SET index prediction

In the business sector, predicting the movement of the Stock Exchange of Thailand (SET) index is challenging. Due to worldwide stock market fluctuations, investors commonly invest in price-changing businesses solely in the long term. Therefore, an accurate SET index movement prediction method is significant for investment purposes and has been the goal of many previous studies. Some studies have indicated that neural network (NN) models perform more effectively and accurately than traditional statistical models; accordingly, NNs employing backpropagation (BP) with sigmoid and smooth adaptive activation functions (SAAFs) and 10 metaheuristic algorithms to determine the initial prediction weights were developed in this study. An experiment was conducted using a Thailand SET50 index dataset, and the results revealed that the model utilizing SAAFs with a cultural algorithm (CA) for weight initialization yielded more precise and efficient predictions than those of other competing models. This finding indicated the possibility of applying the proposed method for SET index movement prediction in the future.

Remaining useful life prediction of rolling bearings based on Pearson correlation-KPCA multi-feature fusion

In the feature selection process, a subset of features is selected from the original set of features based on the feature redundancy and importance. However, most of the existing methods for fusing multiple features ignore the connection between original features which leads to increased redundancy and affects the final classification results. To address this issue, in this study, an effective feature fusion method is proposed for predicting the remaining useful life (RUL) of rolling bearings based on Pearson correlation coefficient and kernel principal component analysis (KPCA). Firstly, the multi-domain features reflecting the bearing degradation state are extracted, and the correlation between the multi-domain features is obtained by Pearson correlation analysis before the feature fusion by KPCA. The features are grouped in such a way that that the correlation between the fused features is higher and the redundancy is lower. Secondly, a RUL prediction model of bearings is established based on the long short-term memory (LSTM) neural network and the Cox proportional-hazards model. In this model, the fused feature set is input into the LSTM neural network to predict the bearing performance degradation trend, which is then used as a multi-dimensional covariate in the Cox proportional-hazards model to assess the reliability of the bearing over time, thereby predicting the bearing RUL. Finally, based on experimental verification, the bearing failure prediction error for two different bearings is obtained to be 1.6 % and 3.4 %, which indicates the feasibility and efficacy of the proposed method for RUL prediction of mechanical equipment.

Evolutionary quantile regression gated recurrent unit network based on variational mode decomposition, improved whale optimization algorithm for probabilistic short-term wind speed prediction

Wind energy, as clean energy, has attracted more and more attention. Wind power generation is easily threatened by the irregular fluctuation of wind speed, which interferes with the safety and stability of power system. In this study, a wind speed interval prediction method based on variational mode decomposition (VMD), phase space reconstruction (PSR), whale optimization algorithm (WOA), quantile regression (QR) and gated recurrent unit (GRU) is proposed. Firstly, the wind speed time series is decomposed into a variety of intrinsic mode functions (IMFs) through VMD to reduce the stochasticity. Secondly, all IMFs are then reconstructed using PSR to get the optimal input variables of the model. Then, the QRGRU model is optimized by the improved WOA to get the optimal QRGRU model parameters. Then, the wind speed interval prediction model of PSR-IWOA-QRGRU is established for each intrinsic mode function. Finally, the prediction results of each component are superimposed to realize the wind speed interval prediction. By checking on three different data sets, the effectiveness of the proposed method in wind speed interval prediction is proved.

Deep-Reinforcement Learning-Based Architecture for Multi-Objective Optimization of Stock Prediction

Artificial Intelligence has been established to predict the future performance of the trading in modern era including Statistics, Computer Science, and economics, especially the stack market. By analyzing the big data, making the financial decision is important for investors in the stock market. As records, several techniques like Back Propagation Neural Network (BPNN) Recurrent Neural Network (RNN) are used to predict the stock price but due to its computation complexity is major challenging of time serious financial data in the decision-making process. In this paper, we have proposed the Recurrent Q Network Learning (RQNL) to make the right decision according to movements of stock prices as reliable attention. To overcome the computational complexity shortcoming, the forgotten memory is developed in a neural network. In this way, the error arousal is pruned in a significant manner. In addition, Enhancing the prediction ability is outstanding, and reinforcement learning is demonstrated to reduce the correlations in time series data. Discussion and evaluation were based on the NSE dataset are experimented with three different learning approaches, with the proposed method for stock prediction of financial markets. The experiment result carried out that our proposed Recurrent Q Network Learning (RQNL) performs the perfect prediction compared with other existing learning.

Analysis of hydro-abrasive erosion in Pelton buckets using a Eulerian-Lagrangian approach

One major concern in developing high-head water resources, which usually uses Pelton turbines, especially in geologically young and fragile mountains, is hydro-abrasive erosion. However, the physical mechanism of hydro-abrasive erosion in Pelton turbine buckets is still not well understood as the cumulative erosion is changing with the transient flow in rotating buckets. In this work, a new approach to predict the cumulative erosion on a rotating surface is proposed and applied to Pelton turbine buckets. This method is based on the Eulerian-Lagaraigian approach previously developed by authors and a novel algorithm introduced to predict the impact behavior of particles hitting rotating surfaces. The numerically obtained erosion is validated with 3D-scanned erosion profiles of buckets measured in a prototype plant. Further, a detailed analysis of the flow and hydro-abrasive erosion characteristics with bucket rotation is conducted. The good agreement with field values demonstrates the promising ability of the proposed method for quantitative erosion prediction. Interestingly, the flow interferences between the jet and the water sheet are found to produce a shield layer to prevent particles from directly impacting surfaces and consequently reduce hydro-abrasive erosion. The current work may provide important engineering insights for geometry optimization to reduce hydro-abrasive erosion.

STTG-net: a Spatio-temporal network for human motion prediction based on transformer and graph convolution network

In recent years, human motion prediction has become an active research topic in computer vision. However, owing to the complexity and stochastic nature of human motion, it remains a challenging problem. In previous works, human motion prediction has always been treated as a typical inter-sequence problem, and most works have aimed to capture the temporal dependence between successive frames. However, although these approaches focused on the effects of the temporal dimension, they rarely considered the correlation between different joints in space. Thus, the spatio-temporal coupling of human joints is considered, to propose a novel spatio-temporal network based on a transformer and a gragh convolutional network (GCN) (STTG-Net). The temporal transformer is used to capture the global temporal dependencies, and the spatial GCN module is used to establish local spatial correlations between the joints for each frame. To overcome the problems of error accumulation and discontinuity in the motion prediction, a revision method based on fusion strategy is also proposed, in which the current prediction frame is fused with the previous frame. The experimental results show that the proposed prediction method has less prediction error and the prediction motion is smoother than previous prediction methods. The effectiveness of the proposed method is also demonstrated comparing it with the state-of-the-art method on the Human3.6 M dataset.

The impact of correlated colour temperature variation from a tuneable LED lamp on colour sample appearance shift in CIELAB colour space

Variation of correlated colour temperature (Tc) of tuneable LED lamps are thought to have a significant effect on red-yellow and blue colour shades, compared to the green one. The phenomenon is expected to be better explained by observing lightness, hue, and chroma (L*C*h°). However, attempts to map the impact of Tc variation on the shift in colour sample appearance are relatively scarce. Therefore, this study aims to map the relation of Tc variation of a tuneable LED lamp with respect to shift in appearance of theoretical colour samples, using L*C*h° parameters in the CIELAB colour space, and to determine their sensitivity. Interaction between SPD of the tuneable LED lamp and ρ(λ) of each colour sample is observed. Analysis is conducted for 210 colour samples derived from the Burns ρ(λ) model. In most cases, as Tc increases, the colour difference tends to become closer to the reference D65. Relation that can be best explained with regression model is the one between the sensitivity of ΔL* and the h° values. The proposed prediction method of colour samples chromaticity under tuneable LED lamps can therefore be implemented in interior lighting scenes with coloured objects and surfaces.

Short-term wind power prediction with harmony search algorithm: Belen region

Wind power is the fastest-growing technology among alternative energy production sources. Reliable forecasting of short-term wind power plays a critical role in the acquisition of most of the generated energy. In this study, short-term wind power forecast is performed using radial-based artificial neural networks, forecast error and cost to be minimized with the harmony search algorithm. Experimented results show that, we can predict wind power with fewer features and less error by using harmony search algorithm. A %7 percent improvement in RMSE rate has been achieved with the proposed method for short-term wind power prediction.