Nowadays, the elevator has become an indispensable means of indoor transportation in people's life, but in recent years this kind of traffic tools has caused many casualties because of the gate system fault. In order to ensure the safe and reliable operation of the elevator, the failure of elevator door system was predicted in this paper. Against the fault type of elevator door system: elevator door opened, excessive vibration when elevator door opened or closed, elevator door did not open or closed when reached the specified level. Three fault types were used as the output of the prediction model. There were 8 reasons for the failure, used them as input. A model based on particle swarm optimization (PSO) and BP neural network was established, using MATLAB to emulation; the results showed that: PSO-BP neural network algorithm was feasible in the fault prediction of the elevator door system.

To determine the angle and position in width direction of canted deck objectively, this paper analyzed the factors that influence the angled deck general arrangements. Principal component analysis was introduced to determine the essential factors which influence the general arrangement of canted deck. Based on several flight deck schemes of foreign mature aircraft carriers, support vector machine was introduced to regression and gain the characteristics of canted deck arrangement. The training result gained by support vector machine algorithm is more accurate than other regression methods. The regression for former Soviet Union Ulyanovsk aircraft carrier demonstrates that the accuracy and validity of this method is good.

In order to know the relation between the bending and temperature of coated steel beam in fire test, the authors carried out a certain amount of fire tests for coated steel beams. Through the analysis of testing data it can be seen that the bending and temperature of coated steel beam are closely related, and the time when the bending at the mid-span of the beam exceeds L 2 /400d mm is almost the same as that when the average temperature of the beam rises to 538 under the condition that the beam is subjected to a total load which represents 60 % of the design moment resistance.