On‐line Statistical Process Monitoring and Fault Diagnosis in Batch Baker's Yeast Fermentation

Abstract

This study involves real-time monitoring and fault diagnosis in batch baker's yeast fermentation. A specific Real Time Statistical Process Analysis and Control (RT-SPAC) program was developed to monitor instantaneous reaction conditions. The air flow rate fed to the reactor, temperature, pH, and dissolved oxygen concentration in a laboratory-size fermenter were monitored and recorded by means of on-line sensors. Under control of the RT-SPAC program, 22 batch baker's yeast fermentation operations were carried out. In the first 20 operations, an ordinary process was followed under previously defined nominal operating conditions. Historical data collected from these batches were then used for online Dynamic Principal Component Analysis (DPCA) in the course of the following two batches. The last two batches were implemented such that some deliberate faults (in temperature and pH) were introduced during the operation. The results indicated that the software was capable of capturing the process faults, and furthermore the possible causes of these faults were identified by contribution plots.

Review of Recent Research on Data-Based Process Monitoring

“…So far, ongoing research studies for all of the above three types of batch process monitoring methods have being carried out. More recent related works include those by Gunther et al, Faggian et al, Berber et al., Alvarez et al, Chen and Jiang, He and Wang, Ge and Song, and so on. To examine the advantages and disadvantages of different types of batch process monitoring methods, please refer to the recent critical evaluation and survey papers. ,, …”

An efficient FDIR strategy on nonlinear processes of self-validating multifunctional sensors

“…To locate the faulty sensitive units, a fault isolation algorithm should be carried out once a fault is detected. As a popular method, contribution plots (Bezergianni and Kalogianni, 2008; Berber et al , 2009) were commonly utilized to diagnosis fault details by evaluating the contribution of each variable. However, Westerhuis et al (2000) reported that contribution plots method suffers from fault smearing effect, i.e.…”

Stationäre Siebklassierung

“…Therefore, designing an intelligent fault diagnosis method has attracted considerable attention. Various intelligent techniques have been put forward, such as expert system 1, principal component analysis (PCA) 2–5, wavelet transform 6, 7, rough set theory 8 etc. Artificial neural network (ANN) can approximate the nonlinear relations for continuous or discrete systems 9–11 and has been widely applied in fault diagnosis 12–16 in recent years.…”