The performance of a chemical process plant can gradually degrade due to deterioration of the process equipment and unpermitted deviation of the characteristic variables of the system. Hence, advanced supervision is required for early detection, isolation and correction of abnormal conditions. This work presents the use of an adaptive neuro-fuzzy inference system (ANFIS) for online fault diagnosis of a gas-phase polypropylene production process with emphasis on fast and accurate diagnosis, multiple fault identification and adaptability. The most influential inputs are selected from the raw measured data sets and fed to multiple ANFIS classifiers to identify faults occurring in the process, eliminating the requirement of a detailed process model. Simulation results illustrated that the proposed method effectively diagnosed different fault types and severities, and that it has a better performance compared to a conventional multivariate statistical approach based on principal component analysis (PCA). The proposed method is shown to be simple to apply, robust to measurement noise and able to rapidly discriminate between multiple faults occurring simultaneously. This method is applicable for plant-wide monitoring and can serve as an early warning system to identify process upsets that could threaten the process operation ahead of time.
Matched MeSH terms: Chemical Industry/statistics & numerical data*
Chemical classification and labelling systems may be roughly similar from one country to another but there are significant differences too. In order to harmonize various chemical classification systems and ultimately provide consistent chemical hazard communication tools worldwide, the Globally Harmonized System of Classification and Labelling of Chemicals (GHS) was endorsed by the United Nations Economic and Social Council (ECOSOC). Several countries, including Japan, Taiwan, Korea and Malaysia, are now in the process of implementing GHS. It is essential to ascertain the comprehensibility of chemical hazard communication tools that are described in the GHS documents, namely the chemical labels and Safety Data Sheets (SDS). Comprehensibility Testing (CT) was carried out with a mixed group of industrial workers in Malaysia (n=150) and factors that influence the comprehensibility were analysed using one-way ANOVA. The ability of the respondents to retrieve information from the SDS was also tested in this study. The findings show that almost all the GHS pictograms meet the ISO comprehension criteria and it is concluded that the underlying core elements that enhance comprehension of GHS pictograms and which are also essential in developing competent persons in the use of SDS are training and education.
Matched MeSH terms: Chemical Industry/statistics & numerical data*