DQN-based die-casting process automatic optimization method

Abstract

The invention discloses a DQN-based die-casting process automatic optimization method, which comprises the following steps: (1) labeling water valves in a cooling system of a die-casting machine, namely a water valve No.1 to a water valve N, and representing the opening and closing states of the water valve by a vector with the length of 2N, wherein the valve with the larger value is the state of the valve at the next moment; (2) obtaining a thermogram of a cooling system in the working process of the die-casting machine; (3) establishing a DQN model by taking the thermogram in the step (2) as input and taking a vector with the length of 2N as output; (4) training the DQN model established in the step (3) through big data generated by multiple pilot production; and (5) applying the model trained in the step (4) to die-casting work, and performing logic control on a valve switch of a cooling system to realize automatic optimization of a product production process. Production optimization of the die-casting process is achieved based on the DQN, it is guaranteed that different positions of the die can be evenly cooled, the product percent of pass is high, and the service life of the die is prolonged.

Description

Technical field [0001] The present invention relates to the field of die-casting processes, and more particularly to a DQN-based die-casting process automatic optimization method. Background technique [0002] The die-casting process is a three major elements such as machines, molds, and alloys, and the process, speed and time uniform process, using high pressure to press the metal melt into the shape of the shape complex metal mold. [0003] Die is characterized by high production precision, high material utilization, high production efficiency, and can be made of complicated shape, clear contour, metal parts of the thin-walled cavity, thereby getting more broad applications. [0004] After the die casting of the metal liquid, the mold temperature was increased at the same time, and then the metal liquid solidified formed the product, and the mold temperature also fell. In this process, due to the complexity of the mold type cavity, the temperature difference between the mold is...

AI Technical Summary

Problems solved by technology

In this process, due to the complex shape of the mold cavity and the large temperature difference between different positions of the mold, the mold is prone to microscopic deformation at this time, causing the appearance of microcracks, resulting in mold failure and product failure

Although the existing mold is generally equipped with a cooling system composed of several cooling roads to ensure that different positions of the mold can be cooled evenly, but due to the lack of effective control, the current product qualification rate is not high and the mold life is short.

Images