Instrumentation & Automation in Oil Industries
Hamidreza Mousavi; Mehdi Shahbazian
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 ...
Read More
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.
Hamidreza Mousavi; Mehdi Shahbazian; Nosrat Moradi
Abstract
Recently different approaches have been developed in the field of sensor fault diagnostics based on Auto-Associative Neural Network (AANN). In this paper we present a novel algorithm called Self reconstructing Auto-Associative Neural Network (S-AANN) which is able to detect and isolate single faulty ...
Read More
Recently different approaches have been developed in the field of sensor fault diagnostics based on Auto-Associative Neural Network (AANN). In this paper we present a novel algorithm called Self reconstructing Auto-Associative Neural Network (S-AANN) which is able to detect and isolate single faulty sensor via reconstruction. We have also extended the algorithm to be applicable in multiple fault conditions. The algorithm uses a calibration model based on AANN. AANN can reconstruct the faulty sensor using non-faulty sensors due to correlation between the process variables, and mean of the difference between reconstructed and original data determines which sensors are faulty. The algorithms are tested on a Dimerization process. The simulation results show that the S-AANN can isolate multiple faulty sensors with low computational time that make the algorithm appropriate candidate for online applications.