State estimation of nonlinear dynamical systems has long aimed to balance accuracy, computational efficiency, robustness, and reliability. The rapid evolution of various industries has amplified the demand for estimation frameworks that satisfy all these factors. This study introduces a neuromorphic approach for robust filtering of nonlinear dynamical systems: SNN-EMSIF (spiking neural network-extended modified sliding innovation filter). SNN-EMSIF combines the computational efficiency and scalability of SNNs with the robustness of EMSIF, an estimation framework designed for nonlinear systems with zero-mean Gaussian noise. Notably, the weight matrices are designed according to the system model, eliminating the need for a learning process. The framework's efficacy is evaluated through comprehensive Monte Carlo simulations, comparing SNN-EMSIF with EKF and EMSIF. Additionally, it is compared with SNN-EKF in the presence of modeling uncertainties and neuron loss, using RMSEs as a metric. The results demonstrate the superior accuracy and robustness of SNN-EMSIF. Further analysis of runtimes and spiking patterns reveals an impressive reduction of 85% in emitted spikes compared to possible spikes, highlighting the computational efficiency of SNN-EMSIF. This framework offers a promising solution for robust estimation in nonlinear dynamical systems, opening new avenues for efficient and reliable estimation in various industries that can benefit from neuromorphic computing.

翻译：非线性动力系统的状态估计长期致力于平衡精度、计算效率、鲁棒性与可靠性。各行业的快速发展进一步放大了对同时满足这些因素的估计框架的需求。本研究提出一种基于神经形态方法的非线性动力系统鲁棒滤波框架：SNN-EMSIF（脉冲神经网络-扩展修正滑动创新滤波）。该框架将脉冲神经网络的计算效率与可扩展性，同针对零均值高斯噪声非线性系统设计的估计框架EMSIF的鲁棒性相结合。值得注意的是，其权重矩阵依据系统模型直接设计，无需学习过程。通过全面的蒙特卡洛仿真，将SNN-EMSIF与EKF及EMSIF进行对比评估；同时，在存在模型不确定性与神经元缺失条件下，以均方根误差（RMSE）为指标，将其与SNN-EKF进行比较。结果表明SNN-EMSIF在精度与鲁棒性方面表现卓越。对运行时间与脉冲模式的进一步分析显示，其实际发射脉冲数相较于理论可能脉冲数减少85%，凸显了SNN-EMSIF的计算效率。该框架为非线性动力系统的鲁棒估计提供了有前景的解决方案，为受益于神经形态计算的多行业高效可靠估计开辟了新路径。