Research on the Adaptive Control in Sugar Evaporative Crystallization Using LSSVM and SaDE-ELM

Abstract

The process of sugar evaporative crystallization is a nonlinear process with large time lag and strong coupling. It is difficult to establish a reasonable mechanism model. In this paper, we use the data driving modeling method to establish an Adaptive Control model for batch boiling sugar crystallization process. First, by analyzing the main influencing factors of the evaporative crystallization process of intermittent boiling sugar, the most important two parameters, brix and liquid level, are selected as the control object. The self-adaptive differential evolution Extreme Learning Machine (SaDE-ELM) is used to construct the control model. A least squares support vector machine (LSSVM) is established and connected in the control loop to control the opening of the feed valve so that to control the feed flowrate according to the objective values of syrup Brix and liquid level. Experiments are conducted and the obtained data are used to train and verify the learning machines. Experiments indicate that the learning machines are able to realize adaptive control to key parameters of the crystallization process. Comparison of different neural networks indicates that the LSSVM performs better than BP, RBF and ELM and SaDE-ELM with prediction error of below 0.01, and training time of below 0.05 s.

Optimization design of cane sugar evaporative crystallizer based on orthogonal test and computational fluid dynamics

“…In orthogonal experimental design, analysis of variance (ANOVA) is used to select the optimal level of factors and the significance of the impact on indicators (Meng, Wei, et al, ; Meng, Zhang, et al, ). The IBM SPSS Statistics was used to analyze the variances and the outcomes are listed in Table .…”

“…Thus, these four factors are selected as the variables of the orthogonal test of numerical simulations. According to cane sugar engineering practices (Rein, ), Tube d takes value in the range of 100–120 mm, Tube l takes in the range of 900–1,500 mm, Downtake d should be 0.4 times the crystallizer diameter, and Level h should be in 1.2–1.6 m. In this study, we scale down them due to our experiment equipment limitation (Meng et al, ; Meng, Wei, Wei, Chen, & Cui, ). Each variable divided into four levels.…”

“…The anemometer probe was installed on the midpoint of downtake and 27 cm from the bottom of the crystallizer. Tests were performed through the sugar evaporative crystallization system based on our laboratory platform (Meng, Wei, et al, ; Meng, Zhang, et al, ), and in order to reduce the experimental error, each test was repeated three times. Sugar with a brix of 91 was used for test.…”

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

“…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.…”