基于粒子群优化支持向量机的水面无人艇故障诊断

通过故障诊断可以对水面无人艇可能要发生的故障进行预报、分析和判断，从而及时调整控制策略以抑制故障的继续发展，为消除故障、维修设备提供准确的技术支持.SVM是基于统计学习理论的一种机器学习方法，常用于故障诊断，在解决小样本、高维度、非线性模式识别问题中有独特优势.SVM分类的准确率由其属性参数直接决定，而最佳的属性参数往往很难直接得到.基于粒子群优化SVM(PSO-SVM)的水面无人艇故障诊断方法，即将粒子群优化算法(PSO)用于SVM属性参数的优化选择中，充分发挥了PSO算法的全局搜索能力和易于实现的优势.水面无人艇故障诊断实例分析结果表明，PSO-SVM的故障诊断精度高于BP-NNs、GS-SVM、GA-SVM。PSO-SVM适用于水面无人艇故障诊断.

Fault diagnosis of USV based on support vector machine with PSO algorithm

Diagnosis of potential faults concealed inside USV is the key of safe navigation.Support vector machine(SVM) is a new machine learning method based on the statistical learning theory, which is a powerful tool for solving the problem with small sampling, non-linear and high dimension. The selection of SVM parameters has an important influence on the classification accuracy of SVM. However, it is very difficult to get appropriate SVM parameter directly. In this paper, support vector machine with particle swarm optimization(PSO-SVM) is applied to fault diagnosis of USV, in which PSO is used to select appropriate free parameters of SVM. The experimental data from HEU-1 USV are used to test the performance of the proposed PSO-SVM model. The experimental results illustrate that the PSO-SVM method can achieve higher diagnostic accuracy than BP-NNs,GS-SVM,GA-SVM.