摘要
为了解决传统网络化制造系统安全检测技术检测精度低的难题,提出基于粒子群优化最小二乘支持向量机(PSO-LSSVM)的网络化制造系统安全检测方法。首先,确定网络化制造系统安全检测特征,并对特征进行预处理。然后,建立基于粒子群优化最小二乘支持向量机的网络化制造系统安全检测模型。最后,通过实例证明该方法的有效性及优越性。分别采用人工神经网络、支持向量机与PSO-LSSVM方法进行对比分析,实验结果表明,PSO-LSSVM对网络化制造系统的安全检测性能优于神经网络与支持向量机的安全检测性能。
In order to solve the problem of poor detection accuracy of traditional security detection method for networked manufacture system,security detection for networked manufacture system based on Least Square Support Vector Machine Optimized by Particle Swarm Optimization（PSO-LSSVM） is presented.Firstly,the security detection features for networked manufacture system are determined,and the features are preprocessed.Then,security detection model for networked manufacture system based on least square support vector machine optimized by particle swarm optimization is created.Finally,the cases are employed to testify the effectiveness and superiority of the proposed method.Artificial neural network,support vector machine are applied to compare with the proposed method.The experimental results indicate that detection ability of least square support vector machine optimized by particle swarm optimization is better than that of artificial neural network,support vector machine.
出处
《现代制造工程》
CSCD
北大核心
2011年第4期95-98,共4页
Modern Manufacturing Engineering
关键词
网络化制造
安全检测
最小二乘支持向量机
识别技术
非线性建模
networked manufacture
security detection
least square support vector machine
recognition technology
nonlinear modeling
