Early detection of agglomeration in a polyethylene fluidized bed at high temperature and pressure by vibration signature analysis

Alamolhoda, Fatemeh; Shamiri, Ahmad; Hussain, Mohd Azlan; Sotudeh‐Gharebagh, Rahmat; Mostoufi, Navid

doi:10.1016/j.cherd.2015.08.003

Cited by 15 publications

(4 citation statements)

References 29 publications

(39 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Having a wide range of tabulated ΔMIT values would help, but unless these can be measured online this method is probably also limited given the complexity of what actually determines its value. Producers therefore sought other methods, and since the early 2000s, the use of acoustic spectroscopy has been discussed as a means of adding predictive capacity to the monitoring of agglomeration and flow in FBRs for the production of PE (alone, and in combination with static probes).…”

Section: Fundamentals Of Condensed Mode Cooling In Modern Pe Plantsmentioning

confidence: 99%

Condensed Mode Cooling of Ethylene Polymerization in Fluidized Bed Reactors

McKenna

2018

Macro Reaction Engineering

View full text Add to dashboard Cite

This review gives an overview of the evolution of the technology of condensed mode cooling, primarily for the case of ethylene polymerization on supported catalysts in fluidized bed reactors. It is well known that this mode of heat removal is quite effective in allowing polyolefin manufacturers to increase significantly production rates. What is perhaps less well understood are all of the issues that, in addition to the effect of the latent heat of vaporization of injected liquid components, also have an impact on the rate of production and behavior of the reactor. However, the liquid components injected into the reactor can vaporize rapidly under full‐scale conditions, leaving behind several heavy components (with respect to ethylene) that have numerous effects on how the particles behave, on the reaction rate, and on fluidization, fouling, and other parameters related to reactor and process performance.

show abstract

Section: Fundamentals Of Condensed Mode Cooling In Modern Pe Plantsmentioning

confidence: 99%

Condensed Mode Cooling of Ethylene Polymerization in Fluidized Bed Reactors

McKenna

2018

Macro Reaction Engineering

View full text Add to dashboard Cite

show abstract

“…This method has excellent Acc; however, it is susceptible to interference from the experimental environment. The temperature difference method detects faults according to temperature changes in the fluidized bed but has a large hysteresis, which will reduce the timeliness of fault detection. , Acoustic sensing technology is a type of nondestructive testing that collects the vibration signals inside the fluidized bed. The random impact of particles on the reactor walls, friction among particles, and air turbulence are white noise excitation sources of wall vibration energy.…”

Section: Resultsmentioning

confidence: 99%

Fault Detection with Data Imbalance Conditions Based on the Improved Bilayer Convolutional Neural Network

Jing

Zhang

Zhou

2020

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

Fault detection is considered a significant and urgent issue in industrial processes. However, faults rarely occur, resulting in an imbalance between normal data and fault data. This paper presents a novel fault-detection model based on wavelet packet decomposition and a bilayer convolutional neural network (WPD-biCNN) within imbalanced data conditions. WPD helps eliminate the adverse impact of data scarcity by mining information in multiple frequency domains rather than generating new data. More rich information in various time and frequency scales is obtained from collected fault samples, which increases the fault information and can help address the imbalance. The improved bilayer convolutional neural network combining local and full convolution stages is employed to extract features and detect fault. The experimental results of an actual polyethylene production process reveal that the proposed method achieves effective performance in the fault detection of agglomeration. In particular, the proposed method exhibits an excellent classification ability for imbalanced data sets with less fault data and more normal data.

show abstract

“…Azizpour et al [17] and Shiea et al [18] used this method for determining regime transition. Azizpour et al [19] used analysis of vibration signature of a lab-scale two-dimensional fluidized bed to detect sudden changes in fluidization state and Alamolhoda et al [20] detected agglomeration of inactive polyethylene particles by this method in early stages in a fluidized bed operating at moderately high temperature and pressure.…”

Section: Introductionmentioning

confidence: 99%