Dandan Kong

A Neural Network Approach to Predict Quality of Pellet Feed Basing on Materiel and Process Parameters

Abstract. With the development of feed industry, the proper way to reducing production cost while keeping quality gained more attention from producer. While processing of pellet feed as main part of formula feed has been confirmed as an extremely complicated system due to varieties of hydrothermal conversion as well as stress fluctuation which effected by lots of factors. Meantime, the comprehensive relationships in the process including nonlinear relation between these factors bring difficulties for exact quantitative mathematical model to describe the relationship between these effected parameters and production quality. Therefore, if a particular tool can be applied to forecast production quality in an certain reliability based on effected parameters before actual production, it will assist producer to make targeted adjustment of these effected parameters to promote production quality in time which avoiding the risk of loss of benefits. As a typical Black Box Approach, model established by Artificial Neural Network (ANN) is based on inside relation between inputs and outputs which overcome the limitations of traditional mathematical model facing the complexity of feed processing, avoiding interference of human factors in maximum. For this reason, the Back-Propagation algorithm was selected to modeling the processing of pellet feed and achieves quality prediction on account of effected parameters. Basing on livestock feed, an indicator system consisted by inputs (processing parameters and diet character) as well as outputs (Pellet Durability Index and pellet hardness) was established. Meantime, the ANN model was actualized applying a toolbox in the MATLAB software using the Levenberg-Marquardt algorithm which shows high stability and fast convergence rate. After a preliminary experiment, the structure of the model was designed as four layers include input layer, output layer and two hidden layers with 7 and 8 neurons accordingly. By analyzing results of the testing, it can be concluded that the utilization of ANN in predicting the product quality of pellet feed was feasible with relative ideal results. The application of this method is capable of saving time and money costing for proper processing parameters search as well as product quality fluctuation in a certain degree, which is meaningful to the profit growth of enterprise and the rational use of social resources.

The Analysis of the Ring Die Hole of Pellet Mill Based on Finite Element

Abstract. The granulation process needs to be accomplished in conjunction with ring die and roller, so the ring die and roller need to have good mechanical properties and service life. Based on full study of domestic and international pellet mill, a kind of small pellet mill will be designed and its 3D model also will be established with 3D design software PROE. After that, the gradual process of pellets during extruding will be simulated and analyzed based on Finite Element, the internal stress and displacement fields in the extrusion will be gotten, the deformation trends and friction during the extrusion stress distribution were analyzed. The results can provide a reliable scientific basis for correct design of pellet mill. The results can provide theoretical basis for the optimization design of pellet mill, improve it’s service life, reduce the development cost and provide the basis for high efficiency and low energy consumption production of feed manufacturers and enterprises.

Research on thermal characteristics of whey powder, milk replacer and lactose

Abstract. In order to study the stability of feed ingredients during conditioning, the heat-sensitive material of sucking pig feed was chosen for this research. The specific heat of six kinds of whey powder, a milk replacer and lactose from 25℃ to 100℃ was measured by using differential scanning calorimeter (DSC). And the thermal conductivity and thermal diffusivity of the eight kinds of samples from 30℃ to 80℃ was measured by a KD2 Pro thermal properties analyzer. The result was that the specific heat of eight materials increased with increasing temperature. The cubic regression model about the specific heat on temperature of each sample was got though the SPSS. The R 2 of the regression equations were above 0.970 except the milk replacer’s 0.875. The fitting effects were good. Moisture content significantly affected the specific heat of whey powder, and the composition of whey powder affected the shape of regression model. The thermal conductivity of most different materials at the same temperature had no significant difference, while the thermal conductivity of different moisture had significant difference mostly. The thermal diffusivity of different materials at the same temperature had significant difference. Moisture and whey protein content significantly affected the thermal diffusivity. The microstructure of the eight materials at different temperature was observed by a scanning electron microscope (SEM). It had been found that the particles of whey powder and milk replacer were conglomerated at high temperature, which explained why the thermal conductivity of the materials was positively correlated with temperature.