Modeling and optimization of sugarcane juice clarification process

Meng, Yanmei; Yu, Shuangshuang; Qiu, Zhenyong; Zhang, Jinlai; Jiekang, Wu; Tao, Yao; Qin, Johnny

doi:10.1016/j.jfoodeng.2020.110223

Cited by 20 publications

(9 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The production of sugar mainly consists of sugarcane milling, juice clarification, juice evaporation, sugar crystallization, sugar paste separation, and dry product packaging (Meng et al, 2021). Sugarcane milling is the first step of sugar production.…”

Section: Introductionmentioning

confidence: 99%

“…Problems such as poor generalization performance of the prediction model may occur if too many features are used as inputs (Zhao & Magoulès, 2012). The current widely used dimensionality reduction method PCA reduces the data dimensionality by transforming and combining the data into a new attribute combination (Meng et al, 2021;Song et al, 2012). However, the transformed features may not have physical meaning, and irrelevant features may cause overfitting of the training data, thereby reducing the accuracy of the model (Cunningham, 2007).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Soft sensor with deep feature extraction for a sugarcane milling system

Meng

Chen

et al. 2022

J Food Process Engineering

Self Cite

View full text Add to dashboard Cite

Extraction rate and energy consumption are two important indicators of the sugarcane milling system, which are calculated by offline experiments and inspection methods. Soft sensors are inferential models, which are enabling online prediction of these indicators. Selection of input variables is one of the most critical issues in soft sensors design. So a deep feature extraction method is proposed by combining mutual information theory and hybrid chicken swamp algorithm to determine the input and parameters of model. Then, input the obtained variables into the data‐driven model of deep kernal extreme learning machine (DK‐ELM) with optimized parameters to realize the prediction of extraction and hourly energy consumption. It combines the kernel method with the multi‐layer ELM. Experiments are conducted to verify the effectiveness and superiority of the modeling method. Comparing the proposed framework with the four experiments designed on a sugarcane milling system, the proposed framework for predicting extraction and energy consumption with better feasibility and effectiveness, and provided a good reference for end‐point control and judgment of quick direct tapping. Practical Applications Extraction and energy consumption are two important indicators of the milling process and whether they meet standards will affect the smooth operation and economic benefits of sugar production. This study presents a novel modeling method to predict these indicators based on the deep feature extraction and deep kernal extreme learning machine. These methods provided a good reference for end‐point control and judgment of quick direct tapping. In addition, it a new concept for the design of soft sensors for such complex industrial processes.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Soft sensor with deep feature extraction for a sugarcane milling system

Meng

Chen

et al. 2022

J Food Process Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…Apart from sucrose, the other constituents must be removed to obtain a refined juice with low turbidity [5]. The removal of suspended solids and non-sucrose impurities can be achieved by clarification [6][7]. Clarification can be conducted by adding lime milk (Ca(OH) 2 ) followed by passing SO 2 (sulfidation) or CO 2 gas (carbonation) through the juice to generate insoluble calcium phosphate flocs (Ca 3 (PO 4 ) 2 ), which can be readily separated by decantation.…”

Section: ■ Introductionmentioning

confidence: 99%

Flocculation Performance of Industrial Sugarcane Juice by Acrylamide-Based Anionic Flocculant

Ningrum

Subyakto²,

Ciptonugroho³

et al. 2023

Indones. J. Chem.

View full text Add to dashboard Cite

Despite the widespread use of ionic polymer flocculants in sugar refineries, there is still insufficient knowledge on the relationship between the polymer properties and the efficiency of flocculation. This paper describes the performance of poly(sodium acrylate-co-acrylamide) (poly(SA-co-AAm)) as an anionic flocculant in the flocculation–coagulation of sugarcane juice from the sugar factory Gempolkrep PTPN X Mojokerto. Poly(SA-co-AAm) was successfully prepared via free radical polymerization of sodium acrylate and acrylamide with respective molar ratios of 40:60, 50:50, and 60:40, and compared with the commercial flocculant Accofloc. It was found that the mud height of the sugarcane decreased with increasing SA:AAm ratio. However, mud height increase was observed with further increasing SA:AAm ratio. Furthermore, increasing the flocculant dosage did not induce any significant change in the mud height and pH. The total dissolved solids (TDS) significantly decreased when the ratio of sodium acrylate:acrylamide was changed from 40:60 to 50:50, whereas a further change to 60:40 increased the TDS value again. It is also noticed that the tendency of turbidity is consistent with the TDS value. These results demonstrate that poly(SA-co-AAm) is a feasible alternative to the commercial flocculant owing to its good flocculation–coagulation performance with an optimum SA:AAm ratio of 50:50.

show abstract

“…To fairly compare with the mainstream methods for sugar price forecasting, we build the deep neuron networks (DNNs) with multiple fully connected layers which is equal to models in [5][6][7] in the machine learning field and the ARIMA compared with [4]. e results are compared against other machine learning algorithms such as the support vector regression (SVR) machine [15,[26][27][28][29], the DNN, and traditional time series model ARIMA. e rest of this paper is organized as follows: Section 2 describes the theoretical background, such as the LSTM, EMD, and TPE.…”

Section: Introductionmentioning

confidence: 99%

A Novel Hybrid Deep Learning Model for Sugar Price Forecasting Based on Time Series Decomposition

Zhang

Meng

Jin

et al. 2021

Mathematical Problems in Engineering

Self Cite

View full text Add to dashboard Cite

Sugar price forecasting has attracted extensive attention from policymakers due to its significant impact on people’s daily lives and markets. In this paper, we present a novel hybrid deep learning model that utilizes the merit of a time series decomposition technology empirical mode decomposition (EMD) and a hyperparameter optimization algorithm Tree of Parzen Estimators (TPEs) for sugar price forecasting. The effectiveness of the proposed model was implemented in a case study with the price of London Sugar Futures. Two experiments are conducted to verify the superiority of the EMD and TPE. Moreover, the specific effects of EMD and TPE are analyzed by the DM test and improvement percentage. Finally, empirical results demonstrate that the proposed hybrid model outperforms other models.

show abstract

Modeling and optimization of sugarcane juice clarification process

Cited by 20 publications

References 25 publications

Soft sensor with deep feature extraction for a sugarcane milling system

Soft sensor with deep feature extraction for a sugarcane milling system

Flocculation Performance of Industrial Sugarcane Juice by Acrylamide-Based Anionic Flocculant

A Novel Hybrid Deep Learning Model for Sugar Price Forecasting Based on Time Series Decomposition

Contact Info

Product

Resources

About