As the core component of inertial navigation systems, fiber optic gyroscope (FOG), with technical advantages such as low power consumption, long lifespan, fast startup speed, and flexible structural design, are widely...As the core component of inertial navigation systems, fiber optic gyroscope (FOG), with technical advantages such as low power consumption, long lifespan, fast startup speed, and flexible structural design, are widely used in aerospace, unmanned driving, and other fields. However, due to the temper-ature sensitivity of optical devices, the influence of environmen-tal temperature causes errors in FOG, thereby greatly limiting their output accuracy. This work researches on machine-learn-ing based temperature error compensation techniques for FOG. Specifically, it focuses on compensating for the bias errors gen-erated in the fiber ring due to the Shupe effect. This work pro-poses a composite model based on k-means clustering, sup-port vector regression, and particle swarm optimization algo-rithms. And it significantly reduced redundancy within the sam-ples by adopting the interval sequence sample. Moreover, met-rics such as root mean square error (RMSE), mean absolute error (MAE), bias stability, and Allan variance, are selected to evaluate the model’s performance and compensation effective-ness. This work effectively enhances the consistency between data and models across different temperature ranges and tem-perature gradients, improving the bias stability of the FOG from 0.022 °/h to 0.006 °/h. Compared to the existing methods utiliz-ing a single machine learning model, the proposed method increases the bias stability of the compensated FOG from 57.11% to 71.98%, and enhances the suppression of rate ramp noise coefficient from 2.29% to 14.83%. This work improves the accuracy of FOG after compensation, providing theoretical guid-ance and technical references for sensors error compensation work in other fields.展开更多
In this study,we examine the problem of sliced inverse regression(SIR),a widely used method for sufficient dimension reduction(SDR).It was designed to find reduced-dimensional versions of multivariate predictors by re...In this study,we examine the problem of sliced inverse regression(SIR),a widely used method for sufficient dimension reduction(SDR).It was designed to find reduced-dimensional versions of multivariate predictors by replacing them with a minimally adequate collection of their linear combinations without loss of information.Recently,regularization methods have been proposed in SIR to incorporate a sparse structure of predictors for better interpretability.However,existing methods consider convex relaxation to bypass the sparsity constraint,which may not lead to the best subset,and particularly tends to include irrelevant variables when predictors are correlated.In this study,we approach sparse SIR as a nonconvex optimization problem and directly tackle the sparsity constraint by establishing the optimal conditions and iteratively solving them by means of the splicing technique.Without employing convex relaxation on the sparsity constraint and the orthogonal constraint,our algorithm exhibits superior empirical merits,as evidenced by extensive numerical studies.Computationally,our algorithm is much faster than the relaxed approach for the natural sparse SIR estimator.Statistically,our algorithm surpasses existing methods in terms of accuracy for central subspace estimation and best subset selection and sustains high performance even with correlated predictors.展开更多
Piezo actuators are widely used in ultra-precision fields because of their high response and nano-scale step length.However,their hysteresis characteristics seriously affect the accuracy and stability of piezo actuato...Piezo actuators are widely used in ultra-precision fields because of their high response and nano-scale step length.However,their hysteresis characteristics seriously affect the accuracy and stability of piezo actuators.Existing methods for fitting hysteresis loops include operator class,differential equation class,and machine learning class.The modeling cost of operator class and differential equation class methods is high,the model complexity is high,and the process of machine learning,such as neural network calculation,is opaque.The physical model framework cannot be directly extracted.Therefore,the sparse identification of nonlinear dynamics(SINDy)algorithm is proposed to fit hysteresis loops.Furthermore,the SINDy algorithm is improved.While the SINDy algorithm builds an orthogonal candidate database for modeling,the sparse regression model is simplified,and the Relay operator is introduced for piecewise fitting to solve the distortion problem of the SINDy algorithm fitting singularities.The Relay-SINDy algorithm proposed in this paper is applied to fitting hysteresis loops.Good performance is obtained with the experimental results of open and closed loops.Compared with the existing methods,the modeling cost and model complexity are reduced,and the modeling accuracy of the hysteresis loop is improved.展开更多
为更好地描述光伏出力不确定性,该文提出了一种基于时序卷积网络(temporal convolutional network,简称TCN)和双向长短期记忆(bidirectional long short term memory,简称BiLSTM)的光伏功率概率预测模型.首先,基于数值天气预报中的云量...为更好地描述光伏出力不确定性,该文提出了一种基于时序卷积网络(temporal convolutional network,简称TCN)和双向长短期记忆(bidirectional long short term memory,简称BiLSTM)的光伏功率概率预测模型.首先,基于数值天气预报中的云量和降雨量将历史数据集划分为晴天、多云天和阴雨天3种场景,生成具有相似天气类型的测试集和训练样本集:然后,应用TCN进行集成特征维度提取,利用BiLSTM神经网络建模进行输出功率和天气数据时间序列的双向拟合.针对传统区间预测分位数损失函数不可微的缺陷,引入Huber范数近似替代原损失函数,并应用梯度下降进行优化,构建改进的可微分位数回归(quantile regression,简称QR)模型,生成置信区间.最后,采用核密度估计(kerneldensity estimation,简称KDE)给出概率密度预测结果。以我国华东某地区分布式光伏电站作为研究对象,与现有概率预测方法相比,该文所提出的短期预测算法的功率区间各评价指标都有所改进,验证了所提方法的可靠性。展开更多
基金supported by the National Natural Science Foundation of China(62375013).
文摘As the core component of inertial navigation systems, fiber optic gyroscope (FOG), with technical advantages such as low power consumption, long lifespan, fast startup speed, and flexible structural design, are widely used in aerospace, unmanned driving, and other fields. However, due to the temper-ature sensitivity of optical devices, the influence of environmen-tal temperature causes errors in FOG, thereby greatly limiting their output accuracy. This work researches on machine-learn-ing based temperature error compensation techniques for FOG. Specifically, it focuses on compensating for the bias errors gen-erated in the fiber ring due to the Shupe effect. This work pro-poses a composite model based on k-means clustering, sup-port vector regression, and particle swarm optimization algo-rithms. And it significantly reduced redundancy within the sam-ples by adopting the interval sequence sample. Moreover, met-rics such as root mean square error (RMSE), mean absolute error (MAE), bias stability, and Allan variance, are selected to evaluate the model’s performance and compensation effective-ness. This work effectively enhances the consistency between data and models across different temperature ranges and tem-perature gradients, improving the bias stability of the FOG from 0.022 °/h to 0.006 °/h. Compared to the existing methods utiliz-ing a single machine learning model, the proposed method increases the bias stability of the compensated FOG from 57.11% to 71.98%, and enhances the suppression of rate ramp noise coefficient from 2.29% to 14.83%. This work improves the accuracy of FOG after compensation, providing theoretical guid-ance and technical references for sensors error compensation work in other fields.
文摘In this study,we examine the problem of sliced inverse regression(SIR),a widely used method for sufficient dimension reduction(SDR).It was designed to find reduced-dimensional versions of multivariate predictors by replacing them with a minimally adequate collection of their linear combinations without loss of information.Recently,regularization methods have been proposed in SIR to incorporate a sparse structure of predictors for better interpretability.However,existing methods consider convex relaxation to bypass the sparsity constraint,which may not lead to the best subset,and particularly tends to include irrelevant variables when predictors are correlated.In this study,we approach sparse SIR as a nonconvex optimization problem and directly tackle the sparsity constraint by establishing the optimal conditions and iteratively solving them by means of the splicing technique.Without employing convex relaxation on the sparsity constraint and the orthogonal constraint,our algorithm exhibits superior empirical merits,as evidenced by extensive numerical studies.Computationally,our algorithm is much faster than the relaxed approach for the natural sparse SIR estimator.Statistically,our algorithm surpasses existing methods in terms of accuracy for central subspace estimation and best subset selection and sustains high performance even with correlated predictors.
基金National Natural Science Foundation of China(62203118)。
文摘Piezo actuators are widely used in ultra-precision fields because of their high response and nano-scale step length.However,their hysteresis characteristics seriously affect the accuracy and stability of piezo actuators.Existing methods for fitting hysteresis loops include operator class,differential equation class,and machine learning class.The modeling cost of operator class and differential equation class methods is high,the model complexity is high,and the process of machine learning,such as neural network calculation,is opaque.The physical model framework cannot be directly extracted.Therefore,the sparse identification of nonlinear dynamics(SINDy)algorithm is proposed to fit hysteresis loops.Furthermore,the SINDy algorithm is improved.While the SINDy algorithm builds an orthogonal candidate database for modeling,the sparse regression model is simplified,and the Relay operator is introduced for piecewise fitting to solve the distortion problem of the SINDy algorithm fitting singularities.The Relay-SINDy algorithm proposed in this paper is applied to fitting hysteresis loops.Good performance is obtained with the experimental results of open and closed loops.Compared with the existing methods,the modeling cost and model complexity are reduced,and the modeling accuracy of the hysteresis loop is improved.
文摘为更好地描述光伏出力不确定性,该文提出了一种基于时序卷积网络(temporal convolutional network,简称TCN)和双向长短期记忆(bidirectional long short term memory,简称BiLSTM)的光伏功率概率预测模型.首先,基于数值天气预报中的云量和降雨量将历史数据集划分为晴天、多云天和阴雨天3种场景,生成具有相似天气类型的测试集和训练样本集:然后,应用TCN进行集成特征维度提取,利用BiLSTM神经网络建模进行输出功率和天气数据时间序列的双向拟合.针对传统区间预测分位数损失函数不可微的缺陷,引入Huber范数近似替代原损失函数,并应用梯度下降进行优化,构建改进的可微分位数回归(quantile regression,简称QR)模型,生成置信区间.最后,采用核密度估计(kerneldensity estimation,简称KDE)给出概率密度预测结果。以我国华东某地区分布式光伏电站作为研究对象,与现有概率预测方法相比,该文所提出的短期预测算法的功率区间各评价指标都有所改进,验证了所提方法的可靠性。
