为提高采煤工作面涌水量预测准确度,收集大量工作面涌水量观测数据进行整理、统计、分析,将涌水量稳定性、周期性和季节性特征考虑在内,提出1种基于数据驱动的完全自适应模态分解算法(CEEMDAN)和改进的混合时间序列模型工作面涌水量预...为提高采煤工作面涌水量预测准确度,收集大量工作面涌水量观测数据进行整理、统计、分析,将涌水量稳定性、周期性和季节性特征考虑在内,提出1种基于数据驱动的完全自适应模态分解算法(CEEMDAN)和改进的混合时间序列模型工作面涌水量预测方法。该方法利用CEEMDAN处理涌水量数据,构建麻雀搜索算法(SSA)优化的长短期记忆网络(LSTM)和自回归移动平均模型(ARIMA)并行级联而成的混合时间序列模型对工作面涌水量进行预测。研究结果表明:该模型预测结果与真实数据相差更小,平均绝对误差为6.36 m 3/h,均方根误差为10.6 m 3/h,模型拟合系数为0.95,更适用于工作面涌水量预测。研究结果可为矿井工作面涌水量预测及防控提供参考。展开更多
In the acoustic detection process of buried non-metallic pipelines,the echo signal is often interfered by a large amount of noise,which makes it extremely difficult to effectively extract useful signals.An denoising a...In the acoustic detection process of buried non-metallic pipelines,the echo signal is often interfered by a large amount of noise,which makes it extremely difficult to effectively extract useful signals.An denoising algorithm based on empirical mode decomposition(EMD)and wavelet thresholding was proposed.This method fully considered the nonlinear and non-stationary characteristics of the echo signal,making the denoising effect more significant.Its feasibility and effectiveness were verified through numerical simulation.When the input SNR(SNRin)is between-10 dB and 10 dB,the output SNR(SNRout)of the combined denoising algorithm increases by 12.0%-34.1%compared to the wavelet thresholding method and by 19.60%-56.8%compared to the EMD denoising method.Additionally,the RMSE of the combined denoising algorithm decreases by 18.1%-48.0%compared to the wavelet thresholding method and by 22.1%-48.8%compared to the EMD denoising method.These results indicated that this joint denoising algorithm could not only effectively reduce noise interference,but also significantly improve the positioning accuracy of acoustic detection.The research results could provide technical support for denoising the echo signals of buried non-metallic pipelines,which was conducive to improving the acoustic detection and positioning accuracy of underground non-metallic pipelines.展开更多
文摘为提高采煤工作面涌水量预测准确度,收集大量工作面涌水量观测数据进行整理、统计、分析,将涌水量稳定性、周期性和季节性特征考虑在内,提出1种基于数据驱动的完全自适应模态分解算法(CEEMDAN)和改进的混合时间序列模型工作面涌水量预测方法。该方法利用CEEMDAN处理涌水量数据,构建麻雀搜索算法(SSA)优化的长短期记忆网络(LSTM)和自回归移动平均模型(ARIMA)并行级联而成的混合时间序列模型对工作面涌水量进行预测。研究结果表明:该模型预测结果与真实数据相差更小,平均绝对误差为6.36 m 3/h,均方根误差为10.6 m 3/h,模型拟合系数为0.95,更适用于工作面涌水量预测。研究结果可为矿井工作面涌水量预测及防控提供参考。
基金supported by Nanchong Southwest Petroleum University Science and Technology Strategic Cooperation Project(Nos.23XNSYSX0022,23XNSYSX0026)Provincial Science and Technology Plan Project(No.2023ZHCG0020)Southwest Petroleum University Natural Science“Sailing Plan”Project(No.2023QHZ003)。
文摘In the acoustic detection process of buried non-metallic pipelines,the echo signal is often interfered by a large amount of noise,which makes it extremely difficult to effectively extract useful signals.An denoising algorithm based on empirical mode decomposition(EMD)and wavelet thresholding was proposed.This method fully considered the nonlinear and non-stationary characteristics of the echo signal,making the denoising effect more significant.Its feasibility and effectiveness were verified through numerical simulation.When the input SNR(SNRin)is between-10 dB and 10 dB,the output SNR(SNRout)of the combined denoising algorithm increases by 12.0%-34.1%compared to the wavelet thresholding method and by 19.60%-56.8%compared to the EMD denoising method.Additionally,the RMSE of the combined denoising algorithm decreases by 18.1%-48.0%compared to the wavelet thresholding method and by 22.1%-48.8%compared to the EMD denoising method.These results indicated that this joint denoising algorithm could not only effectively reduce noise interference,but also significantly improve the positioning accuracy of acoustic detection.The research results could provide technical support for denoising the echo signals of buried non-metallic pipelines,which was conducive to improving the acoustic detection and positioning accuracy of underground non-metallic pipelines.
