Radiator optimization method based on improved particle swarm neural network algorithm

• Main Authors: YAO XIAOFEI, PENG JING, LIU ZHIYUAN, CHEN JIALI, MA YI, DENG YUNKUN, LI HAO, TAN XIANGYU, WANG KE, SUN LIQIONG, CHEN YUMIN
• Format: Patent
• Language: Chinese; English
• Published: 23.07.2019
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention discloses a radiator optimization method based on an improved particle swarm neural network algorithm, and the method comprises the steps: building a geometric model of a radiator, and determining influence parameters of the thermal resistance of the radiator; initializing a BP neural network structure; optimizing the BP neural network by using the improved particle swarm; and the optimized BP neural network is used to process the influence parameters of the thermal resistance of the radiator to obtain the optimal value of the thermal resistance of the radiator. According to theradiator optimization method provided by the invention, the BP neural network parameters are optimized by the particle swarm optimization algorithm and applied to the actual radiator optimization method, the influence parameters of the thermal resistance of the radiator are optimized, and the optimization of the radiator is realized more accurately, quickly and effectively, so that the radiating efficiency of the radiator