基于改进粒子群算法的苹果圆形度检测

Circularity of apple measurement based on the improved algorithm of the particle swarm optimization

为解决苹果圆形度检测问题,研究圆形度的改进粒子群算法。建立苹果圆形度数学模型,并对广义钟形分布隶属函数的惯性权重控制过程、基于Z形隶属函数的自适应调节粒子位置过程、适应度函数选择方法进行算法改进,给出了算法终止条件以及算法流程。仿真试验结果表明,改进粒子群算法收敛较快,乔纳金、富士苹果改进粒子群算法的圆形度检测较其他算法正确率高,分别为96%和97%,说明能用该方法进行苹果圆形度机器检测。

In order to solve the problem in the accuracy of circularity of apple,the improved algorithm of the particle swarm was adopted.Firstly,mathematical model circularity of apple was established.Secondly,particle swarm algorithm was improved,which was included inertia weight fuzzy control based on membership function of generalized bell shaped distribution,adaptive Z shaped membership function adjustment process,and selecting fitness function.Finally,the algorithm termination condition and flow were given.The experimental simulation results showed that the improved particle swarm optimization algorithm convergence was faster than the particle swarm optimization,and the accuracy of Jonakin and Fuji Apple roundness detection,about 96% and 97%,was higher than that of other algorithms.In conclusion,this could algorithm be used for circularity of apple measurement.