Prediction of industrial debutanizer column compositions using data-driven ANFIS- and ANN-based approaches

Neural Computing and Applications - The work in this paper is based on an industrial debutanizer column in a petroleum refinery located in Malaysia, which produces LPG (liquefied petroleum gas) as...     

Neural network applications in fault diagnosis and detection: an overview of implementations in engineering-related systems

The use of artificial neural networks (ANN) in fault detection analysis is widespread. This paper aims to provide an overview on its application in the field of fault identification and diagnosis (FID), as well as the guiding elements behind their successful implementations in engineering-related applications. In most of the reviewed studies, the ANN architecture of choice for FID problem-solving is the multilayer perceptron (MLP). This is likely due to its simplicity, flexibility, and established usage. Its use managed to find footing in a variety of fields in engineering very early on, even before the technology was as polished as it is today. Recurrent neural networks, while having overall stronger potential for solving dynamic problems, are only suggested for use after a simpler implementation in MLP was attempted. Across various ANN applications in FID, it is observed that preprocessing of the inputs is extremely important in obtaining the proper features for use in training the network, particularly when signal analysis is involved. Normalization is practically a standard for ANN use, and likely many other decision-based learning methods due to its ease of use and high impact on speed of convergence. A simple demonstration of ANN’s ease of use in solving a unique FID problem was also shown.

     

Zn(II) ions removal from aqueous solution by Karachi beach sand, a mixed crystal systems

The aim of this research work is to investigate sorption characteristic of beach sand for the removal of Zn(II) ions from aqueous solutions. The sorption of Zn(II) ions by batch dynamic method is carried out using dilute solutions (10⁻⁴ M) of nitric, hydrochloric and perchloric acids along with deionized water and from buffers of pH 2–10. Maximum sorption is noticed from deionized water (88.3%) using 30 min shaking time. Two equations, i.e. Morris–Weber and Lagergren have been tested to track the kinetics of removal process. The Langmuir, Freundlich and Dubinin–Radushkevich (D–R) model are subjected to sorption data to estimate sorption capacity, intensity and energy. The thermodynamic parameters ΔH, ΔS and ΔG are evaluated. The influence of common ions on the sorption of Zn(II) ions is also examined. Some ions reduce the sorption while most of the ions tested have very little effect. It can be concluded that beach sand has potential to remove Zn(II) ions from aqueous solutions at very low concentrations and for the treatment of industrial effluent carrying Zn(II) ions.     

Improved process monitoring using the CUSUM and EWMA-based multiscale PCA fault detection framework

Process monitoring techniques are of paramount importance in the chemical industry to improve both the product quality and plant safety. Small or incipient irregularities may lead to severe degradation in complex chemical processes, and the conventional process monitoring techniques cannot detect these irregularities. In this study to improve the performance of monitoring, an online multiscale fault detection approach is proposed by integrating multiscale principal component analysis (MSPCA) with cumulative sum (CUSUM) and exponentially weighted moving average (EWMA) control charts. The new Hotelling's T² and square prediction error (SPE) based fault detection indices are proposed to detect the incipient irregularities in the process data. The performance of the proposed fault detection methods was tested for simulated data obtained from the CSTR system and compared to that of conventional PCA and MSPCA based methods. The results demonstrate that the proposed EWMA based MSPCA fault detection method was successful in detecting the faults. Moreover, a comparative study shows that the SPE-EWMA monitoring index exhibits a better performance with lower values of missed detections ranging from 0% to 0.80% and false alarms ranging from 0% to 21.20%.     

Preparation of polyaniline montmorillonite clay composites for the removal of diethyl hexyl phthalate from aqueous solutions

The work presents the synthesis of polyaniline functionalized montmorillonite (PANI/MMT) clay composites and evaluation of their performance as an adsorbent for the mitigation of toxic diethyl hexyl phthalate (DEHP) from water. The formation of composite was confirmed by different analytical techniques such as FTIR, zeta potential analysis, XRD, SEM, and AFM. The adsorption capacity of PANI/MMT was superior to MMT. DEHP followed partition mechanism on PANI/MMT whereas MMT favored surface adsorption mechanism. The performance of PANI/MMT for DEHP removal was unaffected by the change in pH of solution, change in salinity, and hardness contents in aqueous system and consecutive adsorption desorption cycles compared to MMT. Furthermore, both PANI/MMT and MMT exhibited greater adsorption capacities as compared to the previously published work and showed satisfactory performance in real water samples.     

Sorption profile of Cd(II) ions onto beach sand from aqueous solutions

Sorption of traces of Cd(II) ions onto beach sand is investigated as a function of nature and concentration of electrolyte (10(-4) to 10(-2)M nitric, hydrochloric and perchloric acids, pH 2-10 buffers and deionized water), shaking time 5-40min, shaking speed 50-200strokes/min, dosage of sand (50-1000mg/15cm(3)), concentration of sorbate (1.04x10(-6) to 1.9x10(-4)M) and temperature (293-323K). Maximum sorption of Cd(II) ions (approximately 66%) is achieved from deionized water using 300mg/15cm(3) sand in 20min. The data are successfully tested by Langmuir, Freundlich and Dubinin-Redushkevich (D-R) sorption isotherms. The values for characteristic Langmuir constants Q=13.31+/-0.20micromol/g and of b=(6.56+/-0.53)x10(3)dm(3)/mol, Freundlich constants A=2.23+/-1.16mmol/g and 1/n=0.70+/-0.05 of (D-R) constants beta=-0.005068+/-0.000328kJ(2)/mol(2), X(m)=46.91+/-11.91micromol/g and energy E=9.92+/-0.32kJ/mol have been estimated. Kinetics of sorption has been studied by applying Morris-Weber, Richenberg and Lagergren equations. The sorption follows first order rate equation resulting 0.182+/-0.004min(-1) The thermodynamic parameters DeltaH=32.09+/-2.92kJ/mol, DeltaS=111.0+/-9.5J/molK and DeltaG=-1.68+/-0.02kJ/mol are evaluated. The influence of common ions on the sorption of Cd(II) ions is also examined. Some common ions reduce the sorption while most of the ions have very little effect. It can be concluded that beach sand may be used as an alternative for the expensive synthetic sorbents.