Sintered brick quality prediction method and device based on BP neural network

The invention discloses a sintered brick quality prediction method based on a BP neural network, and the method comprises the steps: carrying out the crushing, mixing, aging and water adding of sintered brick raw materials according to a preset proportion, and forming a wet blank through a setting machine; drying the wet blank through a drying kiln to form a dry blank; firing the dry blank througha roasting kiln, and detecting the firing temperature of a plurality of temperature points in the roasting kiln; and inputting the firing temperature into a pre-trained BP neural network model, so that the BP neural network model outputs a quality prediction result of the fired brick fired by the calcining kiln. By inputting the firing temperature into the trained BP neural network model, the quality prediction result of the sintered bricks can be accurately obtained, the yield and quality of the sintered bricks of the tunnel kiln are improved, energy waste can be reduced, the environment isprotected, and social and