Statistical process monitoring of a multiphase flow facility

Abstract

a b s t r a c tIndustrial needs are evolving fast towards more flexible manufacture schemes. As a consequence, it is often required to adapt the plant production to the demand, which can be volatile depending on the application. This is why it is important to develop tools that can monitor the condition of the process working under varying operational conditions. Canonical Variate Analysis (CVA) is a multivariate data driven methodology which has been demonstrated to be superior to other methods, particularly under dynamically changing operational conditions. These comparative studies normally use computer simulated data in benchmark case studies such as the Tennessee Eastman Process Plant (Ricker, N.L. Tennessee Eastman Challenge Archive, Available at 〈http://depts.washington.edu/control/LARRY/TE/down load.html〉 Accessed 21.03.2014).The aim of this work is to provide a benchmark case to demonstrate the ability of different monitoring techniques to detect and diagnose artificially seeded faults in an industrial scale multiphase flow experimental rig. The changing operational conditions, the size and complexity of the test rig make this case study an ideal candidate for a benchmark case that provides a test bed for the evaluation of novel multivariate process monitoring techniques performance using real experimental data. In this paper, the capabilities of CVA to detect and diagnose faults in a real system working under changing operating conditions are assessed and compared with other methodologies. The results obtained demonstrate that CVA can be effectively applied for the detection and diagnosis of faults in real complex systems, and reinforce the idea that the performance of CVA is superior to other algorithms.

Canonical variate analysis for performance degradation under faulty conditions

“…The results presented in [15] demonstrated that CVA can effectively detect and diagnose faults in real complex systems working under varying operating conditions. The methodology presented in this investigation goes one step further to demonstrate that CVA can also be used for system identification in a large and complex real facility.…”

“…These data are also necessary to build a dynamic model of the healthy process (2.2). The procedure used in this investigation to apply the CVA for fault detection and diagnosis is similar to the methodology used in [15], where CVA was used to detect and diagnose process faults in the same test rig used here. Three training data sets (T1, T2 and T3) were acquired from the system.…”

“…Fault detection and diagnosis in real complex systems using CVA was introduced in [15]. Although it is not the main objective of the application shown here, fault detection and diagnosis is the starting point of estimation of degradation in a faulty system.…”

“…In [15] it was demonstrated that CVA can effectively detect and diagnose faults in a complex system working under dynamically varying operating conditions. In this paper CVA is used to estimate how the detected faults affect the variables measured in the system compared with normal operation, and also to model the behaviour of a faulty system.…”

“…This method has been applied in the past for detection and diagnosis of process faults using computer simulated data [2-4; 9-12], data acquired from small test rigs [13], and data acquired from particular parts of a system [14]. Recently, the capabilities of CVA to detect and diagnose process faults were tested and compared with other monitoring techniques using experimental data [15]. This investigation proved the superior performance of CVA for the detection and diagnosis of faults in a real complex system working under varying operational conditions.…”