Development of an Artificial Neural Network Utilizing Particle Swarm Optimization for Modeling the Spray Drying of Coconut Milk

Ming, Jesse Lee Kar; Anuar, M. S.; How, Muhammad Syahmeer; Noor, Samsul Bahari Mohd; Abdullah, Zulhamri; Taip, Farah Saleena

doi:10.3390/foods10112708

Cited by 16 publications

(6 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This analysis helps identify the most crucial input parameters, allowing for neglecting less important parameters to reduce the network's complexity. The Garson equation (Ming et al 2021) is utilized for sensitivity analysis, and the weight coefficients of input variables on the output variable are determined by Eq. ( 9).…”

Section: Sensitivity Analysismentioning

confidence: 99%

Moisture content prediction of municipal sludge drying process based on genetic algorithm optimized BP neural network

Zhang,

Wang

2024

Preprint

View full text Add to dashboard Cite

Municipal sludge drying process of internal moisture detection difficulties, and in order to predict the change rule of the internal moisture in the hot-air drying process of municipal sludge, the moisture change of municipal sludge under different drying conditions was monitored through experiments. The moisture prediction model of municipal sludge drying process was established by optimizing the BP neural network using mathematical model, back-propagation (BP) neural network and genetic algorithm (GA), and the performance analysis of the model was carried out. In addition, a sensitivity analysis of the GA-BP model was performed. The results showed that the temperature had the most significant effect on the drying process of municipal sludge, reducing the thickness of the mud layer could improve the drying rate of sludge, and the moisture reduction rate of municipal sludge showed a fast and then a slow trend during the whole drying process. Through the performance analysis, the coefficient of determination of the test set of GA-BP model is 0.9999, and the root mean square error is only 0.0039, which means that the GA-BP model has a better prediction effect and can predict the dynamic change of moisture in the drying process of municipal sludge more accurately. The sensitivity analysis shows that the drying time and drying temperature have the greatest influence on moisture ratio(MR), and the results of the study can provide a theoretical basis for the optimization of the sludge drying process and procedure, and provide a powerful reference for guiding the resource utilization of sludge.

show abstract

Section: Sensitivity Analysismentioning

confidence: 99%

Moisture content prediction of municipal sludge drying process based on genetic algorithm optimized BP neural network

Zhang,

Wang

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…This analysis helps identify the most crucial input parameters, allowing for neglecting less important parameters to reduce the network's complexity. The Garson equation [48] is utilized for sensitivity analysis, and the weight coefficients of input variables on the output variable are determined by Eq. ( 9).…”

Section: Sensitivity Analysismentioning

confidence: 99%

Moisture prediction of municipal sludge drying process using BP neural network modeling and genetic algorithm optimization

Zhang,

Wang,

Wang

2024

Preprint

View full text Add to dashboard Cite

The detection of internal moisture during the municipal sludge drying process is challenging. To explore the dynamic changes in internal moisture during the hot air drying process of municipal sludge and achieve accurate predictions of moisture content(MC) throughout the drying process, experiments were conducted to monitor the moisture variations of municipal sludge under different drying temperatures (50, 60, 70℃), sludge layer thicknesses (5, 10, 15mm), and flow pressure differentials (0.61, 0.85, 1Kpa). Drying time, drying temperature, sludge layer thickness, and flow pressure differential were employed as input variables, while moisture ratio served as the output variable. Predictive models for MC during the hot air drying of municipal sludge were established using both Back Propagation (BP) neural network and Genetic Algorithm-optimized BP (GA-BP) neural network algorithms. Additionally, the drying characteristic curves obtained from experiments were nonlinearly fitted to seven different mathematical models. The results revealed that temperature exerted the most significant influence on the drying process of municipal sludge. Reducing the sludge layer thickness enhanced the drying rate of municipal sludge. The moisture reduction rate of municipal sludge exhibited a trend of initially rapid reduction followed by a slower decline throughout the entire drying process. The Page model demonstrated greater accuracy in describing the hot air drying process of municipal sludge compared to other models. Validation and error analysis of the BP and GA-BP moisture prediction models were performed, with coefficient of determination for both models' test sets reaching 0.99978 and 0.99989, and root mean square errors at 0.49148 and 0.29468, respectively. This indicates that the predictive model established by the GA-BP algorithm exhibits superior performance in accurately predicting the dynamic changes in moisture during the drying process of municipal sludge. The research findings provide a theoretical basis for optimizing municipal sludge drying processes and guiding the efficient utilization of municipal sludge resources. Keywords: Municipal sludge, Drying characteristics, Genetic algorithm, Neural network, Moisture prediction, Sensitivity analysis

show abstract

“…[ 101 ] The main perspective uses of AI methods in spray‐drying are: Exploration of search space for optimized product design : Finding the right set of operation and material parameters for a desired product property is a multidimensional problem. Within the set of admissible solutions (parameter values), some may fulfill additional constraints, e.g., maximized sustainability of the process and product, or minimum production effort, as demonstrated by Przybyl and Kozela (e.g., deep and convolutional neural networks), [ 102 ] Ming et al (particle swarm optimization‐enhanced artificial neural network), [ 103 ] or Fiedler et al (efficient design of experiments using a multi‐step machine learning approach). [ 104 ] Elucidation of fundamental relationships between operational, material parameters and product properties : Utilizing spray‐drying data across different disciplines, e.g., material science, pharmaceuticals, or food and feed, AI methods may find fundamental relationships between the parameters and product properties, independent of the field of application.…”

Section: Spray‐drying As a Highly Versatile Tool For Materials Chemistsmentioning

confidence: 99%

Multifunctional, Hybrid Materials Design via Spray‐Drying: Much more than Just Drying

Wintzheimer,

Luthardt,

Cao

et al. 2023

Advanced Materials

View full text Add to dashboard Cite

Spray‐drying is a popular and well‐known “drying tool” for engineers. This perspective highlights that, beyond this application, spray‐drying is a very interesting and powerful tool for materials chemists to enable the design of multifunctional and hybrid materials. Upon spray‐drying, the confined space of a liquid droplet is narrowed down, and its ingredients are forced together upon “falling dry.” As detailed in this article, this enables the following material formation strategies either individually or even in combination: nanoparticles and/or molecules can be assembled; precipitation reactions as well as chemical syntheses can be performed; and templated materials can be designed. Beyond this, fragile moieties can be processed, or “precursor materials” be prepared. Post‐treatment of spray‐dried objects eventually enables the next level in the design of complex materials. Using spray‐drying to design (particulate) materials comes with many advantages—but also with many challenges—all of which are outlined here. It is believed that multifunctional, hybrid materials, made via spray‐drying, enable very unique property combinations that are particularly highly promising in myriad applications—of which catalysis, diagnostics, purification, storage, and information are highlighted.

show abstract

Development of an Artificial Neural Network Utilizing Particle Swarm Optimization for Modeling the Spray Drying of Coconut Milk

Cited by 16 publications

References 38 publications

Moisture content prediction of municipal sludge drying process based on genetic algorithm optimized BP neural network

Moisture content prediction of municipal sludge drying process based on genetic algorithm optimized BP neural network

Moisture prediction of municipal sludge drying process using BP neural network modeling and genetic algorithm optimization

Multifunctional, Hybrid Materials Design via Spray‐Drying: Much more than Just Drying

Contact Info

Product

Resources

About