A Multiple Model-Based Approach for Fault Diagnosis of Jet Engines

Fault detection and isolation of a dual spool gas turbine engine using dynamic neural networks and multiple model approach

“…The dynamic neural network-based multiple model idea is derived and motivated from that of multiple model-based FDI schemes in the literature [11,10,8], where the mathematical models corresponding to multiple operating conditions are replaced by a parallel bank of dynamic neural network identifiers. The basic structure of the FDI scheme that uses dynamic neural networks is illustrated in Fig.…”

“…Therefore, as compared to our approach it is more reliable and yields significant improvement to a single dynamic neural network-based approach that may not remain valid and representative of the system given the unexpected changes and various operating conditions that the gas turbine system may be required to operate under. The aircraft jet engine component faults considered in this paper correspond to changes in eight (8) health parameters which are the efficiencies and the flow capacities of the low pressure compressor, the high pressure compressor, the low pressure turbine, and the high pressure turbine. Therefore, eight (8) component faults, as shown in Table 1, are investigated in this work for being detected and isolated.…”

Computationally intelligent strategies for robust fault detection, isolation, and identification of mobile robots

“…By proper adjustment of the network parameters: weights, biases, functions, number of neurons and layers, it has been shown that neural networks are general (universal) function approximator. Various neural network-based approaches have been developed in the literature to perform system identification or fault diagnosis of nonlinear systems, as in [8][9][10][11][12][13][14], to name a few. (ii) Fuzzy logic applications: In recent years, fuzzy logic has been successfully applied to different fault detection and diagnosis technical processes.…”

“…4. Development of a fault isolation/identification (FI) methodology through the use of the multiple model approach [11][12][13][14][15] that is augmented with our two proposed methods of system modeling and adaptive threshold bands generation. 5.…”

A kernel principal component analysis–based degradation model and remaining useful life estimation for the turbofan engine

“…Figure 2 shows a flowchart of the engine that includes the main modules and describes the relevant detail of all model information. [17][18][19] For the thermodynamic turbofan engine models, rotor and volume dynamics are involved in the nonlinear system. The engine model considered the volume dynamics and damage factors and added in an unbalanced mass flow rate.…”