Data-driven fault detection and isolation of nonlinear systems using deep learning for Koopman operator.
Mohammadhosein Bakhtiaridoust1, Meysam Yadegar1, Nader Meskin2
1Department of Electrical Engineering, Qom University of Technology, Qom, Iran.
ISA Transactions
|September 20, 2022
Summary
This study introduces a novel data-driven method for detecting and isolating actuator faults in nonlinear systems using deep neural networks and Koopman operator theory. The approach ensures global validity across operating regions without needing prior system knowledge.
Area of Science:
- Control Systems Engineering
- Machine Learning Applications
- Nonlinear System Analysis
Background:
- Actuator faults pose significant risks in nonlinear systems, necessitating reliable detection and isolation methods.
- Traditional approaches often require detailed system models, limiting their applicability.
- Data-driven techniques offer a promising alternative for complex systems.
Purpose of the Study:
- To develop a data-driven actuator fault detection and isolation (FDI) approach for general nonlinear systems.
- To leverage deep neural networks and Koopman operator theory for FDI.
- To achieve global validity of the FDI method across the system's operating range.
Main Methods:
- Utilized a deep neural network to derive an invariant set of basis functions for the Koopman operator.
- Formulated a linear Koopman predictor from the nonlinear system dynamics.
- Developed a recursive, data-driven FDI algorithm based on the linear Koopman model.
- Ensured global validity by exploiting the Koopman operator's inherent properties.
Main Results:
- Successfully demonstrated a data-driven FDI approach for nonlinear systems.
- The method effectively detects and isolates actuator faults without prior system knowledge.
- Validated the approach's global validity and efficacy through simulations on benchmark nonlinear systems.
Conclusions:
- The proposed data-driven FDI method offers a robust and model-free solution for nonlinear systems.
- Koopman operator theory combined with deep learning provides a powerful framework for fault diagnosis.
- The recursive algorithm ensures reliable performance across diverse operating conditions.
Related Concept Videos
01:23Linear time-invariant Systems
357
A system is linear if it displays the characteristics of homogeneity and additivity, together termed the superposition property. This principle is fundamental in all linear systems. Linear time-invariant (LTI) systems include systems with linear elements and constant parameters.
The input-output behavior of an LTI system can be fully defined by its response to an impulsive excitation at its input. Once this impulse response is known, the system's reaction to any other input can be...
The input-output behavior of an LTI system can be fully defined by its response to an impulsive excitation at its input. Once this impulse response is known, the system's reaction to any other input can be...
357
01:21Distributed Loads: Problem Solving
701
Beams are structural elements commonly employed in engineering applications requiring different load-carrying capacities. The first step in analyzing a beam under a distributed load is to simplify the problem by dividing the load into smaller regions, which allows one to consider each region separately and calculate the magnitude of the equivalent resultant load acting on each portion of the beam. The magnitude of the equivalent resultant load for each region can be determined by calculating...
701
01:22Multi-input and Multi-variable systems
143
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence...
In the absence...
143
01:26Linear Approximation in Frequency Domain
128
Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
128
01:26Classification of Systems-I
281
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
281
01:17Open and closed-loop control systems
938
Control systems are foundational elements in automation and engineering. They are broadly categorized into open-loop and closed-loop systems. These classifications hinge on the presence or absence of feedback mechanisms, significantly influencing the system's performance, complexity, and application.
An open-loop control system operates without feedback from the output. It consists of two primary elements: the controller and the controlled process. The controller receives an input signal...
An open-loop control system operates without feedback from the output. It consists of two primary elements: the controller and the controlled process. The controller receives an input signal...
938