This paper presents an innovative algebraic sensor fault detection approach fo r surge avoidance in turbo compressors (TC) in the natural gas compressor stations (GCS). The main objective is surge avoidance in the presence o f sensor faults in TC. In this way, the robust parity space approach fo r fault detection is extended to highly nonlinear dynamic o fT C based on Groebner basis and elimination technique. No work has been previously reported on the use o f this technique fo r nonlinear dynamic systems with parametric uncertainties. This algebraic approach is simulated on the Moore-Greitzer control ori ented model in the presence o f parametric uncertainties, disturbances, and sensor faults. Simulation results are presented to demonstrate the effectiveness o f the proposed fault detection approach.

No abstract

In this paper, a dynamic neural network (DNN) based on robust identification scheme is presented to determine compressor surge point accurately using sensor fault detection (FD). The main innovation of this paper is to present different and complementary technique for surge suppressing studies within sensor FD. The proposed method aims to utilize the embedded analytical redundancies for sensor FD, even in the presence of uncertainty in the compressor and sensor noise. The robust dynamic neural network is developed to learn the input–output map of the compressor for residual generation and the required data is obtained from the compressor Moore–Greitzer simulated model. Generally, the main drawback of DNN method is the lack of systematic law for selecting of initial Hurwitz matrix. Therefore, the subspace identification method is proposed for selecting this matrix. A number of simulation studies are carried out to demonstrate the advantages, capabilities, and performance of our proposed FD scheme and a worthwhile direction for future research is also presented.

This paper investigates the application of fault diagnosis (FD) approach for improving performance of compressors within exact operating point determination. Detecting of sensor fault or failure status is more important in the compressor for safety-critical appli cation. No work has previously been reported on the use of the FD system within a com pressor surge-suppressing system. Therefore, the main contribution of this paper is presenting different and complementary techniques for surge-suppressing studies via sen sor FD. By data acquisition from a nonlinear Moore-Greitzer model, a neural network (NN) and innovation complex decision logic provide residual generation and evaluation blocks in an analytical redundancy FD system, respectively. The proposed FD deals with the most-common sensor faults and failures in seven different scenarios according to their nature, such as bias, cutoff, loss of efficiency, and freeze.