To monitor the dynamic behavior of degrading systems over time, a flexible hierarchical discrete-time state-space model (SSM) is introduced that can mathematically characterize the stochastic evolution of the latent states (discrete, continuous, or hybrid) of degrading systems, dynamic measurements collected from condition monitoring sources (e.g., sensors with mixed-type out-puts), and the failure process. This flexible SSM is inspired by Bayesian hierarchical modeling and recurrent neural networks without imposing prior knowledge regarding the stochastic structure of the system dynamics and its variables. The temporal behavior of degrading systems and the relationship between variables of the corresponding system dynamics are fully characterized by stochastic neural networks without having to define parametric relationships/distributions between deterministic and stochastic variables. A Bayesian filtering-based learning method is introduced to train the structure of the proposed framework with historical data. Also, the steps to utilize the proposed framework for inference and prediction of the latent states and sensor outputs are dis-cussed. Numerical experiments are provided to demonstrate the application of the proposed framework for degradation system modeling and monitoring.
more »
« less
This content will become publicly available on August 1, 2024
A Risk-Based Approach to Prognostics and Health Management Combining Bayesian Networks and Continuous-Time Bayesian Networks
Performing general prognostics and health management (PHM), especially in electronic systems, continues to present significant challenges. The low availability of failure data makes learning generalized models difficult and constructing generalized models during the design phase often requires a level of understanding of the failure mechanisms that elude the designers. In this paper, we present a generalized approach to PHM based on two types of probabilistic models, Bayesian Networks (BNs) and Continuous-Time Bayesian Networks (CTBNs), and we pose the PHM problem from the perspective of risk mitigation rather than failure prediction. This paper also constitutes an extension of previous work where we proposed this framework initially [1]. In this extended version, we also provide a comparison of exact and approximate sample-based inference for CTBNs to provide practical guidance on conducting inference using the proposed framework.
more »
« less
- Award ID(s):
- 1664858
- NSF-PAR ID:
- 10493694
- Publisher / Repository:
- IEEE
- Date Published:
- Journal Name:
- IEEE Instrumentation & Measurement Magazine
- Volume:
- 26
- Issue:
- 5
- ISSN:
- 1094-6969
- Page Range / eLocation ID:
- 3 to 11
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
more » « less
Abstract This paper presents a Bayesian network model to assess the vulnerability of the flood control infrastructure and to simulate failure cascade based on the topological structure of flood control networks along with hydrological information gathered from sensors. Two measures are proposed to characterize the flood control network vulnerability and failure cascade: (a) node failure probability (NFP), which determines the failure likelihood of each network component under each scenario of rainfall event, and (b) failure cascade susceptibility, which captures the susceptibility of a network component to failure due to failure of other links. The proposed model was tested in both single watershed and multiple watershed scenarios in Harris County, Texas using historical data from three different flooding events, including Hurricane Harvey in 2017. The proposed model was able to identify the most vulnerable flood control network segments prone to flooding in the face of extreme rainfall. The framework and results furnish a new tool and insights to help decision‐makers to prioritize infrastructure enhancement investments and actions. The proposed Bayesian network modeling framework also enables simulation of failure cascades in flood control infrastructures, and thus could be used for scenario planning as well as near‐real‐time inundation forecasting to inform emergency response planning and operation, and hence improve the flood resilience of urban areas.
-
null (Ed.)Abstract Deep neural networks (DNNs) have achieved state-of-the-art performance in many important domains, including medical diagnosis, security, and autonomous driving. In domains where safety is highly critical, an erroneous decision can result in serious consequences. While a perfect prediction accuracy is not always achievable, recent work on Bayesian deep networks shows that it is possible to know when DNNs are more likely to make mistakes. Knowing what DNNs do not know is desirable to increase the safety of deep learning technology in sensitive applications; Bayesian neural networks attempt to address this challenge. Traditional approaches are computationally intractable and do not scale well to large, complex neural network architectures. In this paper, we develop a theoretical framework to approximate Bayesian inference for DNNs by imposing a Bernoulli distribution on the model weights. This method called Monte Carlo DropConnect (MC-DropConnect) gives us a tool to represent the model uncertainty with little change in the overall model structure or computational cost. We extensively validate the proposed algorithm on multiple network architectures and datasets for classification and semantic segmentation tasks. We also propose new metrics to quantify uncertainty estimates. This enables an objective comparison between MC-DropConnect and prior approaches. Our empirical results demonstrate that the proposed framework yields significant improvement in both prediction accuracy and uncertainty estimation quality compared to the state of the art.more » « less
-
There has been growing interest in the AI community for precise uncertainty quantification. Conditional density models f(y|x), where x represents potentially high-dimensional features, are an integral part of uncertainty quantification in prediction and Bayesian inference. However, it is challenging to assess conditional density estimates and gain insight into modes of failure. While existing diagnostic tools can determine whether an approximated conditional density is compatible overall with a data sample, they lack a principled framework for identifying, locating, and interpreting the nature of statistically significant discrepancies over the entire feature space. In this paper, we present rigorous and easy-to-interpret diagnostics such as (i) the “Local Coverage Test” (LCT), which distinguishes an arbitrarily misspecified model from the true conditional density of the sample, and (ii) “Amortized Local P-P plots” (ALP) which can quickly provide interpretable graphical summaries of distributional differences at any location x in the feature space. Our validation procedures scale to high dimensions and can potentially adapt to any type of data at hand. We demonstrate the effectiveness of LCT and ALP through a simulated experiment and applications to prediction and parameter inference for image data.more » « less
-
Bayesian neural networks are powerful inference methods by accounting for randomness in the data and the network model. Uncertainty quantification at the output of neural networks is critical, especially for applications such as autonomous driving and hazardous weather forecasting. However, approaches for theoretical analysis of Bayesian neural networks remain limited. This paper makes a step forward towards mathematical quantification of uncertainty in neural network models and proposes a cubature-rule-based computationally efficient uncertainty quantification approach that captures layerwise uncertainties of Bayesian neural networks. The proposed approach approximates the first two moments of the posterior distribution of the parameters by propagating cubature points across the network nonlinearities. Simulation results show that the proposed approach can achieve more diverse layer-wise uncertainty quantification results of neural networks with a fast convergence rate.more » « less
