The bias of micro-electro-mechanical system(MEMS)gyroscopes is sensitive to temperature variations,which limits their accuracy in complex thermal environments.To address this issue,this paper proposes a Gaussian proce...The bias of micro-electro-mechanical system(MEMS)gyroscopes is sensitive to temperature variations,which limits their accuracy in complex thermal environments.To address this issue,this paper proposes a Gaussian process regression(GPR)model that uses resonant frequency and quadrature output as inputs to predict and compensate for the full-temperature bias of MEMS gyroscopes in real-time.Without relying on external sensors,the resonant frequency and quadrature output serve as virtual sensors that directly reflect bias variations.To suppress noise and improve modeling accuracy,the bias is preprocessed using particle swarm optimization-optimized variational mode decomposition before training.In addition,a fast computation strategy is developed to improve the computational efficiency of the GPR model.Experimental results demonstrate the effectiveness and superiority of the proposed method.In three repeated trials,the bias instability of the compensated bias is reduced by 46.18%,60.18%,and 63.68%,respectively,compared to the uncompensated bias.展开更多
High-precision filtering estimation is one of the key techniques for strapdown inertial navigation system/global navigation satellite system(SINS/GNSS)integrated navigation system,and its estimation plays an important...High-precision filtering estimation is one of the key techniques for strapdown inertial navigation system/global navigation satellite system(SINS/GNSS)integrated navigation system,and its estimation plays an important role in the performance evaluation of the navigation system.Traditional filter estimation methods usually assume that the measurement noise conforms to the Gaussian distribution,without considering the influence of the pollution introduced by the GNSS signal,which is susceptible to external interference.To address this problem,a high-precision filter estimation method using Gaussian process regression(GPR)is proposed to enhance the prediction and estimation capability of the unscented quaternion estimator(USQUE)to improve the navigation accuracy.Based on the advantage of the GPR machine learning function,the estimation performance of the sliding window for model training is measured.This method estimates the output of the observation information source through the measurement window and realizes the robust measurement update of the filter.The combination of GPR and the USQUE algorithm establishes a robust mechanism framework,which enhances the robustness and stability of traditional methods.The results of the trajectory simulation experiment and SINS/GNSS car-mounted tests indicate that the strategy has strong robustness and high estimation accuracy,which demonstrates the effectiveness of the proposed method.展开更多
Gaussian process(GP)has fewer parameters,simple model and output of probabilistic sense,when compared with the methods such as support vector machines.Selection of the hyper-parameters is critical to the performance o...Gaussian process(GP)has fewer parameters,simple model and output of probabilistic sense,when compared with the methods such as support vector machines.Selection of the hyper-parameters is critical to the performance of Gaussian process model.However,the common-used algorithm has the disadvantages of difficult determination of iteration steps,over-dependence of optimization effect on initial values,and easily falling into local optimum.To solve this problem,a method combining the Gaussian process with memetic algorithm was proposed.Based on this method,memetic algorithm was used to search the optimal hyper parameters of Gaussian process regression(GPR)model in the training process and form MA-GPR algorithms,and then the model was used to predict and test the results.When used in the marine long-range precision strike system(LPSS)battle effectiveness evaluation,the proposed MA-GPR model significantly improved the prediction accuracy,compared with the conjugate gradient method and the genetic algorithm optimization process.展开更多
In order to meet the demand of online optimal running,a novel soft sensor modeling approach based on Gaussian processes was proposed.The approach is moderately simple to implement and use without loss of performance.I...In order to meet the demand of online optimal running,a novel soft sensor modeling approach based on Gaussian processes was proposed.The approach is moderately simple to implement and use without loss of performance.It is trained by optimizing the hyperparameters using the scaled conjugate gradient algorithm with the squared exponential covariance function employed.Experimental simulations show that the soft sensor modeling approach has the advantage via a real-world example in a refinery.Meanwhile,the method opens new possibilities for application of kernel methods to potential fields.展开更多
In order to reduce the computation of complex problems, a new surrogate-assisted estimation of distribution algorithm with Gaussian process was proposed. Coevolution was used in dual populations which evolved in paral...In order to reduce the computation of complex problems, a new surrogate-assisted estimation of distribution algorithm with Gaussian process was proposed. Coevolution was used in dual populations which evolved in parallel. The search space was projected into multiple subspaces and searched by sub-populations. Also, the whole space was exploited by the other population which exchanges information with the sub-populations. In order to make the evolutionary course efficient, multivariate Gaussian model and Gaussian mixture model were used in both populations separately to estimate the distribution of individuals and reproduce new generations. For the surrogate model, Gaussian process was combined with the algorithm which predicted variance of the predictions. The results on six benchmark functions show that the new algorithm performs better than other surrogate-model based algorithms and the computation complexity is only 10% of the original estimation of distribution algorithm.展开更多
An effective maintenance policy optimization model can reduce maintenance cost and system operation risk. For mission-oriented systems, the degradation process changes dynamically and is monotonous and irreversible. M...An effective maintenance policy optimization model can reduce maintenance cost and system operation risk. For mission-oriented systems, the degradation process changes dynamically and is monotonous and irreversible. Meanwhile, the risk of early failure is high. Therefore, this paper proposes a dynamic condition-based maintenance(CBM) optimization model for mission-oriented system based on inverse Gaussian(IG) degradation process. Firstly, the IG process with random drift coefficient is used to describe the degradation process and the relevant probability distributions are obtained. Secondly, the dynamic preventive maintenance threshold(DPMT) function is used to control the early failure risk of the mission-oriented system, and the influence of imperfect preventive maintenance(PM)on the degradation amount and degradation rate is analysed comprehensively. Thirdly, according to the mission availability requirement, the probability formulas of different types of renewal policies are obtained, and the CBM optimization model is constructed. Finally, a numerical example is presented to verify the proposed model. The comparison with the fixed PM threshold model and the sensitivity analysis show the effectiveness and application value of the optimization model.展开更多
针对海相黏土参数样本稀缺、分布稀疏及物理一致性缺失的问题,构建了一种融合领域物理知识的数据增强算法(physics-guided augmentation,简称PGA)与加权核函数策略的高斯过程回归(Gaussian process regression,简称GPR)模型PGA-GPR。该...针对海相黏土参数样本稀缺、分布稀疏及物理一致性缺失的问题,构建了一种融合领域物理知识的数据增强算法(physics-guided augmentation,简称PGA)与加权核函数策略的高斯过程回归(Gaussian process regression,简称GPR)模型PGA-GPR。该模型将有效应力原理、抗剪强度上限和超固结比约束等物理知识引入数据增强过程,结合多核加权机制提升非线性捕捉能力与物理一致性。采用TC304b数据库中挪威海相黏土实测数据验证了所建模型的参数预测能力。结果表明:稀疏样本条件下,PGA-GPR模型相较传统机器学习模型和海相黏土分层随机场模型,决定系数R^(2)提升17%~53%,预测精度高、结果更趋稳定,且能有效表征沿深度方向海相黏土超固结状态的变化规律。不少于84%的土性参数真实值落入该模型95%置信区间内,显示了所建PGA-GPR模型可靠的预测区间,为应对岩土工程稀缺数据问题提供了新途径。展开更多
在航空航天技术领域,代理模型发挥着关键作用。为平衡代理模型的训练成本与预测精度,需要发展能够有效挖掘多保真度数据间潜在相关性的建模方法。针对现有模型依赖预设核函数、缺乏数据自适应性的问题,提出了一种基于稀疏混合专家神经核...在航空航天技术领域,代理模型发挥着关键作用。为平衡代理模型的训练成本与预测精度,需要发展能够有效挖掘多保真度数据间潜在相关性的建模方法。针对现有模型依赖预设核函数、缺乏数据自适应性的问题,提出了一种基于稀疏混合专家神经核(mixture of experts neural kernel,MoENK)的多保真度代理模型。MoENK通过线性混合和乘积混合基本单元构造新核函数,选择性屏蔽中间结果以过滤噪声,并应用于多任务高斯过程中。将该方法应用于3个函数示例和2个翼型算例中,结果表明该方法的预测精度有较大提升,尤其在NACA0012翼型阻力系数的预测中,相较于次佳方法LR-MFS,RMSE和MAE分别降低了40.42%和44.70%。证实了所提出的MoENK核函数能够不依赖预设核函数进行自适应预测,具有良好的泛化能力和鲁棒性,为工程系统的代理模型构建提供了新的工具。展开更多
两反式光学系统广泛应用于空间遥感、探测制导等领域,其成像质量是光学系统的核心指标,不仅依赖光学器件的制造精度,而且很大程度上受装配精度的影响。在实际工程中,光学系统装配后的成像质量很容易受到界面条件、装配位姿偏差等多源不...两反式光学系统广泛应用于空间遥感、探测制导等领域,其成像质量是光学系统的核心指标,不仅依赖光学器件的制造精度,而且很大程度上受装配精度的影响。在实际工程中,光学系统装配后的成像质量很容易受到界面条件、装配位姿偏差等多源不确定性因素的影响,即使相同的装配工艺参数也可能导致成像质量出现偏差。为此,提出一种两反式光学系统装配与成像的联合仿真方法,以能量集中度作为成像质量定量评价指标,辨识光学系统装配过程中的不确定性参数并进行不确定性度量,根据参数特点选择合理的采样方法,通过联合仿真方法得到不同装配误差条件下的光学系统成像质量数据。建立基于Matern5/2核函数的高斯过程回归(Gaussian Process Regression, GPR)拧紧力矩指向性代理模型,以及结合贝叶斯优化和蒙特卡洛模拟(Bayesian Optimization-Monte Carlo Simulation, BO-MCS)的不确定性优化算法,基于构建的原始数据集,实现光学系统装配不确定性建模分析与装配工艺参数鲁棒性优化。研究结果表明:与其他代理模型相比,所建立的GPR代理模型具有最小的成像质量预测误差(平均预测误差仅有1.95%);优化后的光学系统成像质量平均提升6.13%,波动半径平均减少14.05%,有效提高了光学系统装配后的成像质量一致性。展开更多
基金supported by the National Natural Science Foundation of China(No.12172180).
文摘The bias of micro-electro-mechanical system(MEMS)gyroscopes is sensitive to temperature variations,which limits their accuracy in complex thermal environments.To address this issue,this paper proposes a Gaussian process regression(GPR)model that uses resonant frequency and quadrature output as inputs to predict and compensate for the full-temperature bias of MEMS gyroscopes in real-time.Without relying on external sensors,the resonant frequency and quadrature output serve as virtual sensors that directly reflect bias variations.To suppress noise and improve modeling accuracy,the bias is preprocessed using particle swarm optimization-optimized variational mode decomposition before training.In addition,a fast computation strategy is developed to improve the computational efficiency of the GPR model.Experimental results demonstrate the effectiveness and superiority of the proposed method.In three repeated trials,the bias instability of the compensated bias is reduced by 46.18%,60.18%,and 63.68%,respectively,compared to the uncompensated bias.
基金supported by the National Natural Science Foundation of China(61873275,61703419,425317829).
文摘High-precision filtering estimation is one of the key techniques for strapdown inertial navigation system/global navigation satellite system(SINS/GNSS)integrated navigation system,and its estimation plays an important role in the performance evaluation of the navigation system.Traditional filter estimation methods usually assume that the measurement noise conforms to the Gaussian distribution,without considering the influence of the pollution introduced by the GNSS signal,which is susceptible to external interference.To address this problem,a high-precision filter estimation method using Gaussian process regression(GPR)is proposed to enhance the prediction and estimation capability of the unscented quaternion estimator(USQUE)to improve the navigation accuracy.Based on the advantage of the GPR machine learning function,the estimation performance of the sliding window for model training is measured.This method estimates the output of the observation information source through the measurement window and realizes the robust measurement update of the filter.The combination of GPR and the USQUE algorithm establishes a robust mechanism framework,which enhances the robustness and stability of traditional methods.The results of the trajectory simulation experiment and SINS/GNSS car-mounted tests indicate that the strategy has strong robustness and high estimation accuracy,which demonstrates the effectiveness of the proposed method.
基金Project(513300303)supported by the General Armament Department,China
文摘Gaussian process(GP)has fewer parameters,simple model and output of probabilistic sense,when compared with the methods such as support vector machines.Selection of the hyper-parameters is critical to the performance of Gaussian process model.However,the common-used algorithm has the disadvantages of difficult determination of iteration steps,over-dependence of optimization effect on initial values,and easily falling into local optimum.To solve this problem,a method combining the Gaussian process with memetic algorithm was proposed.Based on this method,memetic algorithm was used to search the optimal hyper parameters of Gaussian process regression(GPR)model in the training process and form MA-GPR algorithms,and then the model was used to predict and test the results.When used in the marine long-range precision strike system(LPSS)battle effectiveness evaluation,the proposed MA-GPR model significantly improved the prediction accuracy,compared with the conjugate gradient method and the genetic algorithm optimization process.
基金Project(2002AA412010,2004AA412050)supported by the National High Technology Research and Development Program of China
文摘In order to meet the demand of online optimal running,a novel soft sensor modeling approach based on Gaussian processes was proposed.The approach is moderately simple to implement and use without loss of performance.It is trained by optimizing the hyperparameters using the scaled conjugate gradient algorithm with the squared exponential covariance function employed.Experimental simulations show that the soft sensor modeling approach has the advantage via a real-world example in a refinery.Meanwhile,the method opens new possibilities for application of kernel methods to potential fields.
基金Project(2009CB320603)supported by the National Basic Research Program of ChinaProject(IRT0712)supported by Program for Changjiang Scholars and Innovative Research Team in University+1 种基金Project(B504)supported by the Shanghai Leading Academic Discipline ProgramProject(61174118)supported by the National Natural Science Foundation of China
文摘In order to reduce the computation of complex problems, a new surrogate-assisted estimation of distribution algorithm with Gaussian process was proposed. Coevolution was used in dual populations which evolved in parallel. The search space was projected into multiple subspaces and searched by sub-populations. Also, the whole space was exploited by the other population which exchanges information with the sub-populations. In order to make the evolutionary course efficient, multivariate Gaussian model and Gaussian mixture model were used in both populations separately to estimate the distribution of individuals and reproduce new generations. For the surrogate model, Gaussian process was combined with the algorithm which predicted variance of the predictions. The results on six benchmark functions show that the new algorithm performs better than other surrogate-model based algorithms and the computation complexity is only 10% of the original estimation of distribution algorithm.
基金supported by the National Natural Science Foundation of China (71901216)。
文摘An effective maintenance policy optimization model can reduce maintenance cost and system operation risk. For mission-oriented systems, the degradation process changes dynamically and is monotonous and irreversible. Meanwhile, the risk of early failure is high. Therefore, this paper proposes a dynamic condition-based maintenance(CBM) optimization model for mission-oriented system based on inverse Gaussian(IG) degradation process. Firstly, the IG process with random drift coefficient is used to describe the degradation process and the relevant probability distributions are obtained. Secondly, the dynamic preventive maintenance threshold(DPMT) function is used to control the early failure risk of the mission-oriented system, and the influence of imperfect preventive maintenance(PM)on the degradation amount and degradation rate is analysed comprehensively. Thirdly, according to the mission availability requirement, the probability formulas of different types of renewal policies are obtained, and the CBM optimization model is constructed. Finally, a numerical example is presented to verify the proposed model. The comparison with the fixed PM threshold model and the sensitivity analysis show the effectiveness and application value of the optimization model.
文摘针对海相黏土参数样本稀缺、分布稀疏及物理一致性缺失的问题,构建了一种融合领域物理知识的数据增强算法(physics-guided augmentation,简称PGA)与加权核函数策略的高斯过程回归(Gaussian process regression,简称GPR)模型PGA-GPR。该模型将有效应力原理、抗剪强度上限和超固结比约束等物理知识引入数据增强过程,结合多核加权机制提升非线性捕捉能力与物理一致性。采用TC304b数据库中挪威海相黏土实测数据验证了所建模型的参数预测能力。结果表明:稀疏样本条件下,PGA-GPR模型相较传统机器学习模型和海相黏土分层随机场模型,决定系数R^(2)提升17%~53%,预测精度高、结果更趋稳定,且能有效表征沿深度方向海相黏土超固结状态的变化规律。不少于84%的土性参数真实值落入该模型95%置信区间内,显示了所建PGA-GPR模型可靠的预测区间,为应对岩土工程稀缺数据问题提供了新途径。
文摘在航空航天技术领域,代理模型发挥着关键作用。为平衡代理模型的训练成本与预测精度,需要发展能够有效挖掘多保真度数据间潜在相关性的建模方法。针对现有模型依赖预设核函数、缺乏数据自适应性的问题,提出了一种基于稀疏混合专家神经核(mixture of experts neural kernel,MoENK)的多保真度代理模型。MoENK通过线性混合和乘积混合基本单元构造新核函数,选择性屏蔽中间结果以过滤噪声,并应用于多任务高斯过程中。将该方法应用于3个函数示例和2个翼型算例中,结果表明该方法的预测精度有较大提升,尤其在NACA0012翼型阻力系数的预测中,相较于次佳方法LR-MFS,RMSE和MAE分别降低了40.42%和44.70%。证实了所提出的MoENK核函数能够不依赖预设核函数进行自适应预测,具有良好的泛化能力和鲁棒性,为工程系统的代理模型构建提供了新的工具。
文摘两反式光学系统广泛应用于空间遥感、探测制导等领域,其成像质量是光学系统的核心指标,不仅依赖光学器件的制造精度,而且很大程度上受装配精度的影响。在实际工程中,光学系统装配后的成像质量很容易受到界面条件、装配位姿偏差等多源不确定性因素的影响,即使相同的装配工艺参数也可能导致成像质量出现偏差。为此,提出一种两反式光学系统装配与成像的联合仿真方法,以能量集中度作为成像质量定量评价指标,辨识光学系统装配过程中的不确定性参数并进行不确定性度量,根据参数特点选择合理的采样方法,通过联合仿真方法得到不同装配误差条件下的光学系统成像质量数据。建立基于Matern5/2核函数的高斯过程回归(Gaussian Process Regression, GPR)拧紧力矩指向性代理模型,以及结合贝叶斯优化和蒙特卡洛模拟(Bayesian Optimization-Monte Carlo Simulation, BO-MCS)的不确定性优化算法,基于构建的原始数据集,实现光学系统装配不确定性建模分析与装配工艺参数鲁棒性优化。研究结果表明:与其他代理模型相比,所建立的GPR代理模型具有最小的成像质量预测误差(平均预测误差仅有1.95%);优化后的光学系统成像质量平均提升6.13%,波动半径平均减少14.05%,有效提高了光学系统装配后的成像质量一致性。
