Dynamic Load Identification Base On Support Vector Machine

It is generally very difficult to measure excitation in operating environment in the case of the complexity of the structure or the variant form of the excitation; sometimes it is even immeasurable for the impact location is usually inaccessible. Nevertheless, certain theories and techniques were developed for force identification or so-called force reconstruction. Aiming at the characteristic of the dynamic loads, by use of the response only, some novel theories are conducted to develop force identification and impact location approaches in the dissertation.Tradition dynamic load identification's precision did not rise, because it is affected by all kinds of condition. We try to use SVM to identify the dynamic loads in this thesis. The traditional neural network are subject to three hardly conquerable drawbacks in network training and network design a long time, including slow training speed, the training trending to sinking into local minimum and the reason for these drawbacks and the methods for overcoming these drawbacks are systemically studied from tow levels, algorithm level and computing theory level. Support vector machine appear later then NN, but it can...