The combustion characteristic parameters of mining conveyor belts represent a crucial index for measuring the fire performance and hazard posed by combustible materials.An accurate prediction of its value provides imp...The combustion characteristic parameters of mining conveyor belts represent a crucial index for measuring the fire performance and hazard posed by combustible materials.An accurate prediction of its value provides important guidance on preventing conveyor belt fires.The critical parameters of a flame-retardant polyvinyl chloride gum elastic conveyor belt were measured under different radiative heat fluxes,including mass loss rate,heat release rate,effective heat of combustion and gas production rates for CO and CO_(2).The prediction method for the combustion characteristics of conveyor belts was proposed by combining a convolutional neural network with long short-term memory.Results indicated that the peak values of the mass loss,heat release,smoke production and gas production rates of CO and CO_(2) were positively correlated with radiative heat flux,whilst the time required to reach the peak value was negatively correlated with it.The peak time of the effective heat of combustion occurred earlier.Through deep learning modelling,mean absolute error,root mean square error and coefficient of determination were determined as 2.09,3.45 and 9.93×10^(-1),respectively.Compared with convolutional neural network,long short-term memory and multilayer perceptron,mean absolute error decreased by 26.92%,24.82%and 25.09%,root mean square error declined by 27.82%,29.59%and 29.59%and coefficient of determination increased by 0.05×10^(-1),0.06×10^(-1) and 0.06×10^(-1),respectively.The findings provide a quantitative reference benchmark for the development of conveyor belt fires and offer new technical support for the construction of early warning systems for conveyor belt fires in coal mines.展开更多
The global growth of the Internet and the rapid expansion of social networks such as Facebook make multilingual sentiment analysis of social media content very necessary. This paper performs the first sentiment analys...The global growth of the Internet and the rapid expansion of social networks such as Facebook make multilingual sentiment analysis of social media content very necessary. This paper performs the first sentiment analysis on code-mixed Bambara-French Facebook comments. We develop four Long Short-term Memory（LSTM）-based models and two Convolutional Neural Network（CNN）-based models, and use these six models, Na？ve Bayes, and Support Vector Machines（SVM） to conduct experiments on a constituted dataset. Social media text written in Bambara is scarce. To mitigate this weakness, this paper uses dictionaries of character and word indexes to produce character and word embedding in place of pre-trained word vectors. We investigate the effect of comment length on the models and perform a comparison among them. The best performing model is a one-layer CNN deep learning model with an accuracy of 83.23 %.展开更多
Numerical weather prediction(NWP)models,widely applied in mesoscale offshore wind resource assessment,face inherent limitations in accuracy.This study explores the potential of machine learning(ML)techniques to enhanc...Numerical weather prediction(NWP)models,widely applied in mesoscale offshore wind resource assessment,face inherent limitations in accuracy.This study explores the potential of machine learning(ML)techniques to enhance the NWP model performance for offshore wind resource assessment.Three ML models are proposed to correct biases in wind field simulations generated by the Weather Research and Forecasting(WRF)model,utilizing in-situ observations as references.The findings reveal systematic biases in seasonal wind field simulations over the Yellow Sea in China,with overestimation in winter and underestimation in summer.Initial WRF simulations result in a mean root mean square error(RMSE)of 3.15 m s^(-1)and a Pearson correlation coefficient(PCC)of 0.76.After ML correction,all three models show significant forecasting improvements.Specifically,the hybrid model incorporating convolutional neural networks(CNN)with long short-term memory networks(LSTM)and Attention mechanisms(CNNLSTM-Attention)achieves the greatest enhancement,reducing RMSE to 1.48 m s^(-1)and increasing PCC to 0.95,representing improvements of 53.1%and 25.3%(p<0.05),respectively,compared to the original WRF model.Similarly,the extreme gradient boosting(XGBoost)and deep neural network(DNN)models demonstrate substantial improvements,achieving RMSE reductions of 45.4%and 51.3%,and PCC increases of 22.7%and 24.6%(p<0.05),respectively.Notably,XGBoost performs well under stable wind conditions,whereas the CNN-LSTM-Attention model excels at capturing dynamic wind speed variations and processing long-sequence datasets,showcasing superior generalization on independent test sets.This study highlights the significant potential of ML in improving NWP-based wind field simulations,providing a robust scientific foundation for precise offshore wind resource assessments.展开更多
基金supported by the Natural Science Foundation of Shaanxi Province(No.2024JC-YBQN-0458)National Natural Science Foundation of China(No.5217-4204)+1 种基金Innovation Capacity Improve-ment Project for Small and Medium-Sized Scientific and Technological Enterprises of Shandong Province(No.2023TSGC0952)Luzhou Science and Technology Planning Project of China(No.2024JYJ057).
文摘The combustion characteristic parameters of mining conveyor belts represent a crucial index for measuring the fire performance and hazard posed by combustible materials.An accurate prediction of its value provides important guidance on preventing conveyor belt fires.The critical parameters of a flame-retardant polyvinyl chloride gum elastic conveyor belt were measured under different radiative heat fluxes,including mass loss rate,heat release rate,effective heat of combustion and gas production rates for CO and CO_(2).The prediction method for the combustion characteristics of conveyor belts was proposed by combining a convolutional neural network with long short-term memory.Results indicated that the peak values of the mass loss,heat release,smoke production and gas production rates of CO and CO_(2) were positively correlated with radiative heat flux,whilst the time required to reach the peak value was negatively correlated with it.The peak time of the effective heat of combustion occurred earlier.Through deep learning modelling,mean absolute error,root mean square error and coefficient of determination were determined as 2.09,3.45 and 9.93×10^(-1),respectively.Compared with convolutional neural network,long short-term memory and multilayer perceptron,mean absolute error decreased by 26.92%,24.82%and 25.09%,root mean square error declined by 27.82%,29.59%and 29.59%and coefficient of determination increased by 0.05×10^(-1),0.06×10^(-1) and 0.06×10^(-1),respectively.The findings provide a quantitative reference benchmark for the development of conveyor belt fires and offer new technical support for the construction of early warning systems for conveyor belt fires in coal mines.
基金Supported by the National Natural Science Foundation of China(61272451,61572380,61772383 and 61702379)the Major State Basic Research Development Program of China(2014CB340600)
文摘The global growth of the Internet and the rapid expansion of social networks such as Facebook make multilingual sentiment analysis of social media content very necessary. This paper performs the first sentiment analysis on code-mixed Bambara-French Facebook comments. We develop four Long Short-term Memory（LSTM）-based models and two Convolutional Neural Network（CNN）-based models, and use these six models, Na？ve Bayes, and Support Vector Machines（SVM） to conduct experiments on a constituted dataset. Social media text written in Bambara is scarce. To mitigate this weakness, this paper uses dictionaries of character and word indexes to produce character and word embedding in place of pre-trained word vectors. We investigate the effect of comment length on the models and perform a comparison among them. The best performing model is a one-layer CNN deep learning model with an accuracy of 83.23 %.
基金Supported by the Scientific Research Project of China Three Gorges Corporation(NBZZ202300197)。
文摘Numerical weather prediction(NWP)models,widely applied in mesoscale offshore wind resource assessment,face inherent limitations in accuracy.This study explores the potential of machine learning(ML)techniques to enhance the NWP model performance for offshore wind resource assessment.Three ML models are proposed to correct biases in wind field simulations generated by the Weather Research and Forecasting(WRF)model,utilizing in-situ observations as references.The findings reveal systematic biases in seasonal wind field simulations over the Yellow Sea in China,with overestimation in winter and underestimation in summer.Initial WRF simulations result in a mean root mean square error(RMSE)of 3.15 m s^(-1)and a Pearson correlation coefficient(PCC)of 0.76.After ML correction,all three models show significant forecasting improvements.Specifically,the hybrid model incorporating convolutional neural networks(CNN)with long short-term memory networks(LSTM)and Attention mechanisms(CNNLSTM-Attention)achieves the greatest enhancement,reducing RMSE to 1.48 m s^(-1)and increasing PCC to 0.95,representing improvements of 53.1%and 25.3%(p<0.05),respectively,compared to the original WRF model.Similarly,the extreme gradient boosting(XGBoost)and deep neural network(DNN)models demonstrate substantial improvements,achieving RMSE reductions of 45.4%and 51.3%,and PCC increases of 22.7%and 24.6%(p<0.05),respectively.Notably,XGBoost performs well under stable wind conditions,whereas the CNN-LSTM-Attention model excels at capturing dynamic wind speed variations and processing long-sequence datasets,showcasing superior generalization on independent test sets.This study highlights the significant potential of ML in improving NWP-based wind field simulations,providing a robust scientific foundation for precise offshore wind resource assessments.
