Unmanned Underwater Vehicles Fault Identification and Fault-Tolerant Control Method Based on FCA-CMAC Neural Networks, Applied on an Actuated Vehicle

Abstract

A novel fault diagnosis and accommodation method for unmanned underwater vehicles thruster is presented in this paper. FCA-CMAC (Credit Assignment-based Fuzzy Cerebellar Model Articulation Controllers) neural network is used to realize the fault identification for thruster continuous and uncertain jammed fault situation. A reconstruction algorithm based on weighted pseudo-inverse is used to find the available solution of the control allocation problem. To illustrate effective of the proposed method, two simulation examples of multi-uncertain abrupt faults are given in the paper.

Least-Squares Based and Gradient Based Iterative Parameter Estimation Algorithms for a Class of Linear-in-Parameters Multiple-Input Single-Output Output Error Systems

“…The proposed methods can be extended to study the identification problems of linear multivariable systems [39,40] or multirate or nonuniformly sampled systems [41,42]. The methods in this paper can combine the multi-innovation identification methods [43][44][45][46][47][48][49][50], the iterative identification methods [51,52], and other identification methods [53][54][55][56] to present new identification algorithms for nonlinear systems [57][58][59] and can also be applied in other fields [60][61][62][63][64][65][66][67].…”

A Fault-tolerant Steering Prototype for X-rudder Underwater Vehicles

“…To achieve this, the four individual control surfaces need to coordinate well since every control surface contributes its own effect to the pitch and heading control. Actually, this manner is quite similar to dynamic positioning systems for ocean surface vessels in [23,24], motion control systems for over-actuated underwater vehicles in [25,26], flight control systems for tailless aircraft with strong interactions between control effectors as described in [27,28].…”

“…. n) using the system dynamics represented by Equation (25), then a prior probability p(χ i k y 1:k−1 ) (i = 1, 2, . .…”

Resilient control system execution agent (ReCoSEA)

“…In order to provide the appropriate response, the immediacy of the impact and type of response is necessary. A neural network can then be used to selectively align the response based upon this information that accompanies the anomaly statistic from the Rationalize aspect to perform a selection of this appropriate response [22] [23] [24] [25]. In what is rationalized in Figure 5, some sources of anomaly and the level of impact are mentioned.…”