Search results

Accurate prediction of the structural condition of urban critical infrastructure is crucial for predictive maintenance. However, the existing prediction methods lack precision due to limitations in utilizing heterogeneous sensing data and domain knowledge as well as insufficient generalizability resulting from limited data samples. This paper integrates implicit and qualitative expert knowledge into quantifiable values in tunnel condition assessment and proposes a tunnel structure prediction algorithm that augments a state-of-the-art attention-based long short-term memory (LSTM) model with expert rating knowledge to achieve robust prediction results to reasonably allocate maintenance resources.

Through formalizing domain experts' knowledge into quantitative tunnel condition index (TCI) with analytic hierarchy process (AHP), a fusion approach using sequence smoothing and sliding time window techniques is applied to the TCI and time-series sensing data. By incorporating both sensing data and expert ratings, an attention-based LSTM model is developed to improve prediction accuracy and reduce the uncertainty of structural influencing factors.

The empirical experiment in Dalian Road Tunnel in Shanghai, China showcases the effectiveness of the proposed method, which can comprehensively evaluate the tunnel structure condition and significantly improve prediction performance.

This study proposes a novel structure condition prediction algorithm that augments a state-of-the-art attention-based LSTM model with expert rating knowledge for robust prediction of structure condition of complex projects.

With the rapid advancement in the automotive industry, the friction coefficient (FC), wear rate (WR) and weight loss (WL) have emerged as crucial parameters to measure the performance of automotive braking systems, so the FC, WR and WL of friction material are predicted and analyzed in this work, with an aim of achieving accurate prediction of friction material properties.

Genetic algorithm support vector machine (GA-SVM) model is obtained by applying GA to optimize the SVM in this work, thus establishing a prediction model for friction material properties and achieving the predictive and comparative analysis of friction material properties. The process parameters are analyzed by using response surface methodology (RSM) and GA-RSM to determine them for optimal friction performance.

The results indicate that the GA-SVM prediction model has the smallest error for FC, WR and WL, showing that it owns excellent prediction accuracy. The predicted values obtained by response surface analysis are closed to those of GA-SVM model, providing further evidence of the validity and the rationality of the established prediction model.

The relevant results can serve as a valuable theoretical foundation for the preparation of friction material in engineering practice.

Higher energy conversion efficiency of internal combustion engine can be achieved with optimal control of unsteady in-cylinder flow fields inside a direct-injection (DI) engine. However, it remains a daunting task to predict the nonlinear and transient in-cylinder flow motion because they are highly complex which change both in space and time. Recently, machine learning methods have demonstrated great promises to infer relatively simple temporal flow field development. This paper aims to feature a physics-guided machine learning approach to realize high accuracy and generalization prediction for complex swirl-induced flow field motions.

To achieve high-fidelity time-series prediction of unsteady engine flow fields, this work features an automated machine learning framework with the following objectives: (1) The spatiotemporal physical constraint of the flow field structure is transferred to machine learning structure. (2) The ML inputs and targets are efficiently designed that ensure high model convergence with limited sets of experiments. (3) The prediction results are optimized by ensemble learning mechanism within the automated machine learning framework.

The proposed data-driven framework is proven effective in different time periods and different extent of unsteadiness of the flow dynamics, and the predicted flow fields are highly similar to the target field under various complex flow patterns. Among the described framework designs, the utilization of spatial flow field structure is the featured improvement to the time-series flow field prediction process.

The proposed flow field prediction framework could be generalized to different crank angle periods, cycles and swirl ratio conditions, which could greatly promote real-time flow control and reduce experiments on in-cylinder flow field measurement and diagnostics.

Traditional multivariable grey prediction models define the background-value coefficients of the dependent and independent variables uniformly, ignoring the differences between their physical properties, which in turn affects the stability and reliability of the model performance.

A novel multivariable grey prediction model is constructed with different background-value coefficients of the dependent and independent variables, and a one-to-one correspondence between the variables and the background-value coefficients to improve the smoothing effect of the background-value coefficients on the sequences. Furthermore, the fractional order accumulating operator is introduced to the new model weaken the randomness of the raw sequence. The particle swarm optimization (PSO) algorithm is used to optimize the background-value coefficients and the order of the model to improve model performance.

The new model structure has good variability and compatibility, which can achieve compatibility with current mainstream grey prediction models. The performance of the new model is compared and analyzed with three typical cases, and the results show that the new model outperforms the other two similar grey prediction models.

This study has positive implications for enriching the method system of multivariable grey prediction model.

With the rise in wine consumption, accurate wine price forecasts have significantly impacted restaurant and hotel purchasing decisions and inventory management. This study aims to develop a precise and effective wine price point and interval forecasting model.

The proposed forecast model uses an improved hybrid kernel extreme learning machine with an attention mechanism and a multi-objective swarm intelligent optimization algorithm to produce more accurate price estimates. To the best of the authors’ knowledge, this is the first attempt at applying artificial intelligence techniques to improve wine price prediction. Additionally, an effective method for predicting price intervals was constructed by leveraging the characteristics of the error distribution. This approach facilitates quantifying the uncertainty of wine price fluctuations, thus rendering decision-making by relevant practitioners more reliable and controllable.

The empirical findings indicated that the proposed forecast model provides accurate wine price predictions and reliable uncertainty analysis results. Compared with the benchmark models, the proposed model exhibited superiority in both one-step- and multi-step-ahead forecasts. Meanwhile, the model provides new evidence from artificial intelligence to explain wine prices and understand their driving factors.

This study is a pioneering attempt to evaluate the applicability and effectiveness of advanced artificial intelligence techniques in wine price forecasts. The proposed forecast model not only provides useful options for wine price forecasting but also introduces an innovative addition to existing forecasting research methods and literature.

While the Chinese securities market is booming, the phenomenon of listed companies falling into financial distress is also emerging, which affects the operation and development of enterprises and also jeopardizes the interests of investors. Therefore, it is important to understand how to accurately and reasonably predict the financial distress of enterprises.

In the present study, ensemble feature selection (EFS) and improved stacking were used for financial distress prediction (FDP). Mutual information, analysis of variance (ANOVA), random forest (RF), genetic algorithms, and recursive feature elimination (RFE) were chosen for EFS to select features. Since there may be missing information when feeding the results of the base learner directly into the meta-learner, the features with high importance were fed into the meta-learner together. A screening layer was added to select the meta-learner with better performance. Finally, Optima hyperparameters were used for parameter tuning by the learners.

An empirical study was conducted with a sample of A-share listed companies in China. The F1-score of the model constructed using the features screened by EFS reached 84.55%, representing an improvement of 4.37% compared to the original features. To verify the effectiveness of improved stacking, benchmark model comparison experiments were conducted. Compared to the original stacking model, the accuracy of the improved stacking model was improved by 0.44%, and the F1-score was improved by 0.51%. In addition, the improved stacking model had the highest area under the curve (AUC) value (0.905) among all the compared models.

Compared to previous models, the proposed FDP model has better performance, thus bridging the research gap of feature selection. The present study provides new ideas for stacking improvement research and a reference for subsequent research in this field.

To improve the speed and accuracy of turbine blade film cooling design process, the most advanced deep learning models were introduced into this study to investigate the most suitable define for prediction work. This paper aims to create a generative surrogate model that can be applied on multi-objective optimization problems.

The latest backbone in the field of computer vision (Swin-Transformer, 2021) was introduced and improved as the surrogate function for prediction of the multi-physics field distribution (film cooling effectiveness, pressure, density and velocity). The basic samples were generated by Latin hypercube sampling method and the numerical method adopt for the calculation was validated experimentally at first. The training and testing samples were calculated at experimental conditions. At last, the surrogate model predicted results were verified by experiment in a linear cascade.

The results indicated that comparing with the Multi-Scale Pix2Pix Model, the Swin-Transformer U-Net model presented higher accuracy and computing speed on the prediction of contour results. The computation time for each step of the Swin-Transformer U-Net model is one-third of the original model, especially in the case of multi-physics field prediction. The correlation index reached more than 99.2% and the first-order error was lower than 0.3% for multi-physics field. The predictions of the data-driven surrogate model are consistent with the predictions of the computational fluid dynamics results, and both are very close to the experimental results. The application of the Swin-Transformer model on enlarging the different structure samples will reduce the cost of numerical calculations as well as experiments.

The number of U-Net layers and sample scales has a proper relationship according to equation (8). Too many layers of U-Net will lead to unnecessary nonlinear variation, whereas too few layers will lead to insufficient feature extraction. In the case of Swin-Transformer U-Net model, incorrect number of U-Net layer will reduce the prediction accuracy. The multi-scale Pix2Pix model owns higher accuracy in predicting a single physical field, but the calculation speed is too slow. The Swin-Transformer model is fast in prediction and training (nearly three times faster than multi Pix2Pix model), but the predicted contours have more noise. The neural network predicted results and numerical calculations are consistent with the experimental distribution.

This paper creates a generative surrogate model that can be applied on multi-objective optimization problems. The generative adversarial networks using new backbone is chosen to adjust the output from single contour to multi-physics fields, which will generate more results simultaneously than traditional surrogate models and reduce the time-cost. And it is more applicable to multi-objective spatial optimization algorithms. The Swin-Transformer surrogate model is three times faster to computation speed than the Multi Pix2Pix model. In the prediction results of multi-physics fields, the prediction results of the Swin-Transformer model are more accurate.

With the continuous growth of online education, the quality issue of online educational videos has become increasingly prominent, causing students in online learning to face the dilemma of knowledge confusion. The existing mechanisms for controlling the quality of online educational videos suffer from subjectivity and low timeliness. Monitoring the quality of online educational videos involves analyzing metadata features and log data, which is an important aspect. With the development of artificial intelligence technology, deep learning techniques with strong predictive capabilities can provide new methods for predicting the quality of online educational videos, effectively overcoming the shortcomings of existing methods. The purpose of this study is to find a deep neural network that can model the dynamic and static features of the video itself, as well as the relationships between videos, to achieve dynamic monitoring of the quality of online educational videos.

The quality of a video cannot be directly measured. According to previous research, the authors use engagement to represent the level of video quality. Engagement is the normalized participation time, which represents the degree to which learners tend to participate in the video. Based on existing public data sets, this study designs an online educational video engagement prediction model based on dynamic graph neural networks (DGNNs). The model is trained based on the video’s static features and dynamic features generated after its release by constructing dynamic graph data. The model includes a spatiotemporal feature extraction layer composed of DGNNs, which can effectively extract the time and space features contained in the video's dynamic graph data. The trained model is used to predict the engagement level of learners with the video on day T after its release, thereby achieving dynamic monitoring of video quality.

Models with spatiotemporal feature extraction layers consisting of four types of DGNNs can accurately predict the engagement level of online educational videos. Of these, the model using the temporal graph convolutional neural network has the smallest prediction error. In dynamic graph construction, using cosine similarity and Euclidean distance functions with reasonable threshold settings can construct a structurally appropriate dynamic graph. In the training of this model, the amount of historical time series data used will affect the model’s predictive performance. The more historical time series data used, the smaller the prediction error of the trained model.

A limitation of this study is that not all video data in the data set was used to construct the dynamic graph due to memory constraints. In addition, the DGNNs used in the spatiotemporal feature extraction layer are relatively conventional.

In this study, the authors propose an online educational video engagement prediction model based on DGNNs, which can achieve the dynamic monitoring of video quality. The model can be applied as part of a video quality monitoring mechanism for various online educational resource platforms.

In a boundary layer ingestion (BLI) propulsion system, the fan operates continuously under distorted inflow conditions, leading to an increment of aerodynamic loss and in turn impacting the potential fuel burn reduction of the aircraft. Usually, in the preliminary design stage of a BLI propulsion system, it is essential to assess the impact of fuselage boundary layer fluids on fan aerodynamic performances under various flight conditions. However, the hub region flow loss is one of the major loss sources in a fan and would greatly influence the fan performances. Moreover, the inflow distortion also results in a complex and highly nonlinear mapping relation between loss and local physical parameters. It will diminish the prediction accuracy of the commonly used low-fidelity computational approaches which often incorporate traditional physics-based loss models, reducing the reliability of these approaches in evaluating fan performances. Meanwhile, the high-fidelity full-annulus unsteady Reynolds-averaged Navier–Stokes (URANS) approach, even though it can give rather accurate loss predictions, is extremely time-consuming. This study aims to develop a fast and accurate hub loss prediction method for a BLI fan under distorted inflow conditions.

This paper develops a data-driven hub loss prediction method for a BLI fan under distorted inflows. To improve the prediction accuracy and applicability, physical understandings of hub flow features are integrated into the modeling process. Then, the key physical parameters related to flow loss are screened by conducting a sensitivity analysis of influencing parameters. Next, a quasi-steady assumption of flow is made to generate a training sample database, reducing the computational time by acquiring one single sample from the highly time-consuming full-annulus URANS approach to a cost-efficient single-blade-passage approach. Finally, a radial basis function neural network is used to establish a surrogate model that correlates the input parameters and the output loss.

The data-driven hub loss model shows higher prediction accuracy than the traditional physics-based loss models. It can accurately capture the circumferentially and radially nonuniform variation trends of the losses and the associated absolute magnitudes in a BLI fan under different blade load, inlet distortion intensity and rotating speed conditions. Compared with the high-fidelity full-annulus URANS results, the averaged relative prediction errors of the data-driven hub loss model are kept less than 10%.

The originality of this paper lies in developing a new method for predicting flow loss in a BLI fan rotor blade hub region. This method offers higher prediction accuracy than the traditional loss models and lower computational time cost than the full-annulus URANS approach, which could realize fast evaluations of fan aerodynamic performances and provide technical support for designing high-performance BLI fans.

The purpose of this paper is to develop an appropriate machine learning model for predicting soil compaction degree while also examining the contribution rates of three influential factors: moisture content, electrical conductivity and temperature, towards the prediction of soil compaction degree.

Taking fine-grained soil A and B as the research object, this paper utilized the laboratory test data, including compaction parameter (moisture content), electrical parameter (electrical conductivity) and temperature, to predict soil degree of compaction based on five types of commonly used machine learning models (19 models in total). According to the prediction results, these models were preliminarily compared and further evaluated.

The Gaussian process regression model has a good effect on the prediction of degree of compaction of the two kinds of soils: the error rates of the prediction of degree of compaction for fine-grained soil A and B are within 6 and 8%, respectively. As per the order, the contribution rates manifest as: moisture content > electrical conductivity >> temperature.

By using moisture content, electrical conductivity, temperature to predict the compaction degree directly, the predicted value of the compaction degree can be obtained with higher accuracy and the detection efficiency of the compaction degree can be improved.