Direct falling weightless type material feeding method based on neural network

Abstract

The invention discloses a direct falling weightless type material feeding method based on a neural network. A neural network module is established in a controller, and the four input quantities of thematerial level, the material falling rate, the material density and the opening diameter of a feeding valve are mapped as a fed material weightlessness value by the adoption of the neural network; atraining sample is obtained, and offline training is conducted on the neural network; and when feeding control is conducted online, based on signals collected by a bin level sensor in a feeding bin and a weighing module bearing the feeding bin, the neural network predicts the material falling weightlessness value, a processing module corrects the feeding quantity based on the predicted value and then adjusts the closing time of the feeding valve. According to the direct falling weightless type material feeding method based on the neural network, the material falling weightlessness values at different material falling states are predicted by the adoption of the neural network, direct accurate feeding can be achieved, and the direct falling weightless type material feeding method based on the neural network is suitable for small-batch production; the material accumulation state in the feeding bin is detected and adjusted by the adoption of the bin level sensor and a stirrer, so that thematerial falling rate fluctuation is reduced; and the batch feeding total error is reduced through control over the feeding accumulative error.

Description

technical field [0001] The invention relates to the field of quantitative cutting, in particular to a neural network-based method for cutting materials in a straight-fall and weightless manner. Background technique [0002] In industrial and agricultural manufacturing and commodity packaging, there are a large number of powder materials, such as iron concentrate, coal powder and other ironmaking raw materials, polypropylene, polystyrene, polyvinyl chloride, light methyl cellulose, polypropylene nitrile, environmental protection, etc. Chemical raw materials such as oxygen resin powder coatings, building materials such as quartz sand and cement, household chemical products such as washing powder, agricultural products such as millet and soybeans, or processed foods such as powder, slag, and granules, agricultural production such as feed, chemical fertilizers, and pesticides Materials, as well as powdered health care products, Chinese and Western medicines, condiments, etc., al...

AI Technical Summary

Problems solved by technology

For example, the Chinese patents with application numbers 200710142591.6, 201010108011.3 and 201310178558.4 all measure the falling materials through the calculation of the weight reduction of the weighing bin. Although these schemes do not need to consider the amount of air, they do not consider the weight loss of materials when they fall from the feeding valve. The effect affects the accuracy of weighing and measurement, and cannot meet the requirements of high-precision blanking, and these solutions can only be used for continuous blanking and cannot be directly applied to batch blanking

Images