To address the problem of low detection accuracy when the fault node rate was higher than 50% in Wireless Sensor Network (WSN), a wireless sensor fault diagnosis algorithm based on the precondition of neighbor nodes and neighbor node data was proposed. Firstly, the historical data of nodes were used to pre-calculate the states of sensor nodes initially. Then the final state of each node was judged by taking advantage of similarity of nodes and pre-states of neighbor nodes. Finally, the fault node information was sent to the base station by mobile sensors through the optimal path, which effectively reduced the number of communications. A WSN was simulated in an area of 100 m*100 m. The experimental results show that compared with the traditional Distributed Fault Detection (DFD) algorithm, the diagnosis accuracy of the proposed algorithm is improved by 9.84 percentage points. Moreover, the proposed algorithm even achieves more than 95% fault diagnosis accuracy when the node failure rate is as high as 50% in the network. In practical application, the proposed algorithm improves the fault diagnosis accuracy, reduces the energy consumption effectively, and prolongs the network lifetime as well.

To improve the performance of the co-training algorithm and expand the range of applications, a multi-view semi-supervised collaboration classification algorithm with the combination of consistent and inconsistent label rules was proposed, which aimed at providing a more effective method for the classification of the bridge structured health data. The proposed algorithm used combination of agreement and disagreement label rules for the unlabeled data by judging whether the two classifiers were consistent. Put the sample to the label set, if the label results were consistent. If the label results were inconsistent and the confidence was beyond the threshold, it put the label result of the high confidence to the label set, took full use of the unlabeled data to improve the performance of the classifier, and updated the classification model by the difference of the classifiers. The experimental results of the proposed algorithm on the bridge structured health datasets and standard UCI datasets verify the effectiveness and feasibility of the proposed model on the multi-view classification problems.