Document Type : Research Paper
Authors
1 M.S. Student, Department of Instrumentation & Automation Engineering, Petroleum University of Technology, Ahwaz, Iran
2 Associate Professor, Department of Instrumentation & Automation Engineering, Petroleum University of Technology, Ahwaz, Iran
Abstract
Auto-associative neural network (AANN) has been recently used in sensor fault diagnosis. This paper introduces a new AANN based algorithm named improved AANN (I-AANN) for sensor single-fault diagnosis. An algorithm is a two-aimed approach that estimates the correct value of the faulty sensor by isolating the source of the fault. The performance of the algorithm is compared with the so-called enhanced AANN (E-AANN) in terms of computational time and fault reconstruction accuracy. The I-AANN has high performance, and it can isolate the source of fault quickly and accurately. A dimerization process model is used as a case study to examine and compare the performance of the algorithms. The results demonstrate that the I-AANN has superior performance.
Highlights
- An algorithm named improved auto-associative neural network (I-AANN) is presented for sensor fault diagnosis;
- The algorithm uses a calibration model based on auto-associative neural network (AANN);
- The I-AANN performance is compared with enhanced auto-associative neural network (E-AANN);
- The algorithm is a kind of nonlinear principal component analysis (NLPCA);
- The algorithm can detect and isolate faulty sensors via reconstruction;
- Due to the low computational time, the algorithm is capable of online application.
Keywords
Main Subjects