Digital twin is a vital enabling technology for smart manufacturing in the era of Industry 4.0. Digital twin effectively replicates its physical asset enabling easy visualization, smart decision-making and cognitive capability in the system. In this paper, a framework of dynamic data driven digital twin for complex engineering products was proposed. To illustrate the proposed framework, an example of health management on aircraft engines was studied. This framework models the digital twin by extracting information from the various sensors and Industry Internet of Things (IIoT) monitoring the remaining useful life (RUL) of an engine in both cyber and physical domains. Then, with sensor measurements selected from linear degradation models, a long short-term memory (LSTM) neural network is proposed to dynamically update the digital twin, which can estimate the most up-to-date RUL of the physical aircraft engine. Through comparison with other machine learning algorithms, including similarity based linear regression and feed forward neural network, on RUL modelling, this LSTM based dynamical data driven digital twin provides a promising tool to accurately replicate the health status of aircraft engines. This digital twin based RUL technique can also be extended for health management and remote operation of manufacturing systems.
more »
« less
Physically Invertible System Identification for Monitoring System Edges with Unobservability
Nowadays, the data collected in physical/engineering systems allows various machine learning methods to conduct system monitoring and control, when the physical knowledge on the system edge is limited and challenging to recover completely. Solving such problems typically requires identifying forward system mapping rules, from system states to the output measurements. However, the forward system identification based on digital twin can hardly provide complete monitoring functions, such as state estimation, e.g., to infer the states from measurements. While one can directly learn the inverse mapping rule, it is more desirable to re-utilize the forward digital twin since it is relatively easy to embed physical law there to regularize the inverse process and avoid overfitting. For this purpose, this paper proposes an invertible learning structure based on designing parallel paths in structural neural networks with basis functionals and embedding virtual storage variables for information preservation. For such a two-way digital twin modeling, there is an additional challenge of multiple solutions for system inverse, which contradict the reality of one feasible solution for the current system. To avoid ambiguous inverse, the proposed model maximizes the physical likelihood to contract the original solution space, leading to the unique system operation status of interest. We validate the proposed method on various physical system monitoring tasks and scenarios, such as inverse kinematics problems, power system state estimation, etc. Furthermore, by building a perfect match of a forward-inverse pair, the proposed method obtains accurate and computation-efficient inverse predictions, given observations. Finally, the forward physical interpretation and small prediction errors guarantee the explainability of the invertible structure, compared to standard learning methods.
more »
« less
- Award ID(s):
- 1810537
- NSF-PAR ID:
- 10461960
- Date Published:
- Journal Name:
- Machine Learning and Knowledge Discovery in Databases: European Conference
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract We consider Bayesian inference for large-scale inverse problems, where computational challenges arise from the need for repeated evaluations of an expensive forward model. This renders most Markov chain Monte Carlo approaches infeasible, since they typically require O ( 1 0 4 ) model runs, or more. Moreover, the forward model is often given as a black box or is impractical to differentiate. Therefore derivative-free algorithms are highly desirable. We propose a framework, which is built on Kalman methodology, to efficiently perform Bayesian inference in such inverse problems. The basic method is based on an approximation of the filtering distribution of a novel mean-field dynamical system, into which the inverse problem is embedded as an observation operator. Theoretical properties are established for linear inverse problems, demonstrating that the desired Bayesian posterior is given by the steady state of the law of the filtering distribution of the mean-field dynamical system, and proving exponential convergence to it. This suggests that, for nonlinear problems which are close to Gaussian, sequentially computing this law provides the basis for efficient iterative methods to approximate the Bayesian posterior. Ensemble methods are applied to obtain interacting particle system approximations of the filtering distribution of the mean-field model; and practical strategies to further reduce the computational and memory cost of the methodology are presented, including low-rank approximation and a bi-fidelity approach. The effectiveness of the framework is demonstrated in several numerical experiments, including proof-of-concept linear/nonlinear examples and two large-scale applications: learning of permeability parameters in subsurface flow; and learning subgrid-scale parameters in a global climate model. Moreover, the stochastic ensemble Kalman filter and various ensemble square-root Kalman filters are all employed and are compared numerically. The results demonstrate that the proposed method, based on exponential convergence to the filtering distribution of a mean-field dynamical system, is competitive with pre-existing Kalman-based methods for inverse problems.more » « less
-
null (Ed.)Power system state estimation is an important component of the status and healthiness of the underlying electric power grid real-time monitoring. However, such a component is prone to cyber-physical attacks. The majority of research in cyber-physical power systems security focuses on detecting measurements False-Data Injection attacks. While this is important, measurement model parameters are also a most important part of the state estimation process. Measurement model parameters though, also known as static-data, are not monitored in real-life applications. Measurement model solutions ultimately provide estimated states. A state-of-the-art model presents a two-step process towards simultaneous false-data injection security: detection and correction. Detection steps are χ2 statistical hypothesis test based, while correction steps consider the augmented state vector approach. In addition, the correction step uses an iterative solution of a relaxed non-linear model with no guarantee of optimal solution. This paper presents a linear programming method to detect and correct cyber-attacks in the measurement model parameters. The presented bi-level model integrates the detection and correction steps. Temporal and spatio characteristics of the power grid are used to provide an online detection and correction tool for attacks pertaining the parameters of the measurement model. The presented model is implemented on the IEEE 118 bus system. Comparative test results with the state-of-the-art model highlight improved accuracy. An easy-to-implement model, built on the classical weighted least squares solution, without hard-to-derive parameters, highlights potential aspects towards real-life applications.more » « less
-
more » « less
Abstract There are two broad modeling paradigms in scientific applications: forward and inverse. While forward modeling estimates the observations based on known causes, inverse modeling attempts to infer the causes given the observations. Inverse problems are usually more critical as well as difficult in scientific applications as they seek to explore the causes that cannot be directly observed. Inverse problems are used extensively in various scientific fields, such as geophysics, health care and materials science. Exploring the relationships from properties to microstructures is one of the inverse problems in material science. It is challenging to solve the microstructure discovery inverse problem, because it usually needs to learn a one-to-many nonlinear mapping. Given a target property, there are multiple different microstructures that exhibit the target property, and their discovery also requires significant computing time. Further, microstructure discovery becomes even more difficult because the dimension of properties (input) is much lower than that of microstructures (output). In this work, we propose a framework consisting of generative adversarial networks and mixture density networks for inverse modeling of structure–property linkages in materials, i.e., microstructure discovery for a given property. The results demonstrate that compared to baseline methods, the proposed framework can overcome the above-mentioned challenges and discover multiple promising solutions in an efficient manner.
-
null (Ed.)Many inverse problems involve two or more sets of variables that represent different physical quantities but are tightly coupled with each other. For example, image super-resolution requires joint estimation of the image and motion parameters from noisy measurements. Exploiting this structure is key for efficiently solving these large-scale optimization problems, which are often ill-conditioned. In this paper, we present a new method called Linearize And Project (LAP) that offers a flexible framework for solving inverse problems with coupled variables. LAP is most promising for cases when the subproblem corresponding to one of the variables is considerably easier to solve than the other. LAP is based on a Gauss–Newton method, and thus after linearizing the residual, it eliminates one block of variables through projection. Due to the linearization, this block can be chosen freely. Further, LAP supports direct, iterative, and hybrid regularization as well as constraints. Therefore LAP is attractive, e.g., for ill-posed imaging problems. These traits differentiate LAP from common alternatives for this type of problem such as variable projection (VarPro) and block coordinate descent (BCD). Our numerical experiments compare the performance of LAP to BCD and VarPro using three coupled problems whose forward operators are linear with respect to one block and nonlinear for the other set of variables.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
