The Bayesian paradigm provides a rigorous framework for estimating the whole probability distribution over unknown parameters, but due to high computational costs, its online application can be difficult. We propose the Adaptive Recursive Markov Chain Monte Carlo (ARMCMC) method, which calculates the complete probability density function of model parameters while alleviating the drawbacks of traditional online methods. These flaws include being limited to Gaussian noise, being solely applicable to linear in the parameters (LIP) systems, and having persisting excitation requirements (PE). A variable jump distribution based on a temporal forgetting factor (TFF) is proposed in ARMCMC. The TFF can be utilized in many dynamical systems as an effective way to adaptively present the forgetting factor instead of a constant hyperparameter. The particular jump distribution has tailored towards hybrid/multi-modal systems that enables inferences among modes by providing a trade-off between exploitation and exploration. These trade-off are adjusted based on parameter evolution rate. In comparison to traditional MCMC techniques, we show that ARMCMC requires fewer samples to obtain the same accuracy and reliability. We show our method on two challenging benchmarks: parameter estimation in a soft bending actuator and the Hunt-Crossley dynamic model. We also compare our method with recursive least squares and the particle filter, and show that our technique has significantly more accurate point estimates as well as a decrease in tracking error of the value of interest.
翻译:Bayesian 范式为估计整个概率分布的未知参数提供了严格的框架来估计整个概率分布,但由于计算成本高,其在线应用可能很困难。我们建议采用适应性再稳定马克夫链链的蒙特卡洛(ARMC)方法,该方法计算模型参数的完全概率密度功能,同时减轻传统在线方法的缺陷。这些缺陷包括限于Gausian噪音,仅适用于参数(LIP)系统中的线性噪音,并且具有持续的刺激要求。在ARMCMCMC中提议根据时间遗忘系数(TFF)进行价值跳动分配。TFF可以在许多动态系统中使用,作为适应性地呈现遗忘系数而不是恒定的超参数的有效方法。特别跳动分布针对混合/多模式系统,通过提供开采和勘探之间的交易,使各种模式之间的推理。这些交易根据参数的演变率进行调整。与传统的MCMC技术相比,我们表明ARMCMC技术需要较少的样本才能获得同样的准确性和可靠性。我们用两种动态系统的方法来有效地利用TARMSL,我们用一种最不具有挑战性的标准来比较,即以软的汇率的汇率来测量我们的汇率的汇率的汇率。我们的行为是比较。