scispace - formally typeset
Search or ask a question
Proceedings ArticleDOI

Bayesian inference for fault-tolerant control

TL;DR: This work uses an original method based on the Kalman-filter by which fault detection, diagnosis and accommodation is possible provided that an accurate model is available, and attempts to alleviate this necessity by means of accounting for uncertainty in both model as well as in the measurements used for fault diagnosis.
Abstract: In this contribution, we present initial developments in view of model-based fault-tolerant control (FTC). In this context, we use an original method based on the Kalman-filter by which fault detection, diagnosis and accommodation is possible provided that an accurate model is available. Since this is not generally true, we attempt to alleviate this necessity by means of accounting for uncertainty, in both model as well as in the measurements used for fault diagnosis. Our preliminary results are focused on the diagnosis step in the FTC scheme.
Citations
More filters
03 May 2010
TL;DR: The paper presents as an application how Bayesian networks could be applied to fault detection and diagnosis in an on-line estimation of a dynamic model for distributed parameter systems, with exemplification in the case of the city road traffic.
Abstract: This paper presents some considerations related to fault detection and diagnosis, using Bayesian networks, in the complex distributed parameter systems with time and space variables, where the intelligent wireless sensor networks are used as a distributed sensor. These miniaturized intelligent sensors may be placed in the area of multivariable distributed parameter systems and even with limited resources of energy, memory, computational power and bandwidth they may add to solve applications on a large space. Multivariable estimation techniques are easier to applied when a multi-sensor network is used. Bayesian networks bring their main characteristics as graphic models with a node topology and treating information by probabilistic inference. The usage of Bayesian networks is chosen considering the distributed parameter system as a system with continuous variable, but digitally surveyed in discrete time, the sensor placed to measure the time variation of system variables been affected by random noises. The paper presents as an application how Bayesian networks could be applied to fault detection and diagnosis in an on-line estimation of a dynamic model for distributed parameter systems, with exemplification in the case of the city road traffic.

2 citations


Cites background from "Bayesian inference for fault-tolera..."

  • ...In the paper [18] initial developments for modelbased fault-tolerant control are presented....

    [...]

References
More filters
Journal ArticleDOI
TL;DR: In this paper, a fault-tolerant control scheme (FTCS) is proposed by integrating a fault detection and identification (FDI) technique with conventional control, which allows online application of the FTCS without causing significant degradation in the closed-loop performance due to the occurrences of biases in sensors and actuators.
Abstract: Coventional control schemes are developed under the assumption that the sensors and actuators are free from faults. However, the occurrence of faults will cause degradation in the closed-loop performance and also will have an impact on safety, productivity, and plant economy. In the present work, we have proposed a fault-tolerant control scheme (FTCS) by integrating a fault detection and identification (FDI) technique with conventional control. The principal component of our proposed FTCS is a compensation strategy (supervisory system) which uses the information provided by the FDI to appropriately modify the controller as well as the model used in FDI. This allows online application of the FTCS without causing significant degradation in the closed-loop performance due to the occurrences of biases in sensors and actuators or due to changes in unmeasured disturbance variables and due to moderate change in process parameters. Through stochastic simulation studies of a continuous stirred tank reactor process...

82 citations


"Bayesian inference for fault-tolera..." refers methods in this paper

  • ...The classic Fault Tolerant Scheme In the original FTC method [1,2], monitoring and diagnosis tasks are performed by means of the analysis of residuals produced by the Kalman filter [3]....

    [...]

  • ...In the first milestones of the project, we aim at the implementation of the Fault-Tolerant Control (FTC) technique developed in [1,2]....

    [...]

Journal ArticleDOI
TL;DR: Soft faults such as biases or drifts in sensors or actuators are more frequently encountered in the process industry and can lead to degradation in the closed loop performance of the MPC controller.
Abstract: Model predictive control (MPC) schemes are typically developed under the assumption that the sensors and actuators are free from faults. Attempts to develop fault-tolerant MPC schemes have mainly focused on dealing with hard faults, such as sensor or actuator failures, process leaks, etc. However, soft faults such as biases or drifts in sensors or actuators are more frequently encountered in the process industry. Occurrences of such faults can lead to degradation in the closed loop performance of the MPC controller. Since MPC controllers are typically used to control key operations in a chemical plant, this can have an impact on safety and productivity of the entire plant. The conventional approach to dealing with such soft faults in MPC formulations is through the introduction of additional artificial states to the model. The main limitation of this approach is that number of artificial extra states introduced cannot exceed the number of measurements. This implies that it is necessary to have a priori kn...

60 citations


"Bayesian inference for fault-tolera..." refers methods in this paper

  • ...The classic Fault Tolerant Scheme In the original FTC method [1,2], monitoring and diagnosis tasks are performed by means of the analysis of residuals produced by the Kalman filter [3]....

    [...]

  • ...In the first milestones of the project, we aim at the implementation of the Fault-Tolerant Control (FTC) technique developed in [1,2]....

    [...]