Search

In order to improve and protect human being's environment, water resource should be effectively monitored and managed. The support vector machine (SVM) is an algorithm based on structure risk minimizing principle and having high generalization ability. It is strong to solve the problem with small sample, nonlinear and high dimension. In this paper, based on a lot of research fruits of water quality forecast methods at home and abroad, a water forecast method based on support vector machine is put forward, and a water quality multi-classification forecasting model based on time sequence's SVM is established. Its water quality of Tai Lake is aimed and researched by the forecast method of water quality. Its correct rate of SVM model can reach 84.62%, its correct rate of back-propagation neutral network (BPNN) model is 80.77%. The simulation results have proved that its training speed and testing accuracy of SVM are higher than back-propagation neutral network. From the experimental result, the water quality forecast model based on SVM can correctly predict its grade of water quality and provide a new way for forecast of water quality.

Magnetorheological (MR) fluid as a new smart material has done well in the vibration and impact control engineering fields because of its good electromechanical coupling characteristics, preferable dynamic performance and higher sensitivity. And success of MRF has been apparent in many engineering applied fields, such as semi-active suspension, civil engineering, etc. So far, little research has been done about MR damper applied into the weapon system. Its primary purpose of this study is to identify its dynamic performance and controability of the artillery recoil mechanism equipped with MR damper. Firstly, based on the traditional artillery recoil mechanism, a recoil dynamic model is developed in order to obtain an ideal rule between recoil force and its stroke. Then, its effects of recoil resistance on the stability and firing accuracy of artillery are explored. Because MR gun recoil damper under high impact load shows a typical nonlinear character and there exists a shear-thinning phenomenon, to establish an accurate dynamic model has been a seeking aim of its design and application for MR damper under high impact load. Secondly, in this paper, considering its actual bearing load, an inertia factor was introduced to Herschel-Bulkley model, and some factor's effect on damping force are simulated and analyzed by using numerical simulation, including its dynamic performance under different flow coefficients and input currents. Finally, both of tests with the fixed current and different On-Off control algorithms have been done to confirm its controability of MR gun recoil damper under high impact load. Experimental results show its dynamic performances of the large-scale single-ended MR gun recoil damper can be changed by altering the applied currents and it has a good controllability.

The dynamic response and active vibration control of flexible composite material barrel under moving projectile are studied in this paper. After analyzing its vibration characteristics, the active vibration control technology is introduced to suppress its vibration. Combining theoretical modeling and experimental developing, some key problems of applying the active vibration control technology to vibration control of flexible composite barrel are discussed, which provides the technology foundation for later developing of flexible smart composite barrel. The coupling vibration model between the moving projectile and flexible composite barrel is established and solved by applying numerical iterative method and simulation experimental study, and many valuable conclusions are made. Besides, the dynamic response model and state space model for active vibration control of barrel under a moving projectile is established. And the adaptive fuzzy control strategy is introduced to suppress the flexible composite material barrel vibration. The testing system of dynamic response and active vibration control for barrel under a moving projectile is designed and developed. The experimental results showed the effectiveness of this kind of control strategy for flexible composite material barrel bonded with piezoelectric self-sensing actuator under a moving projectile, which demonstrated that using the smart material could suppress the time-varying system flexible structure vibration active control.

The support vector machine (SVM) is an algorithm based on structure risk minimizing principle and having high generalization ability. It is strong to solve the problem with small sample, nonlinear and high dimension. The fundamental theory of DGA (Dissolved Gas Analysis, DGA) and fault characteristic of transformer is firstly researched in this paper, and then the disadvantages of traditional method of transformer fault diagnosis are analyzed, finally, a new fault diagnosis method using multi-class support vector machines (M-SVMs) based on DGA theory for transformer is put forward. Then the fault diagnosis model based on M-SVMs for transformer is established. At the same time, the fault diagnosis system based on M-SVMs for transformer is developed. The system can realize the acquisition of the dissolving gas in the transformer oil and data timely and low cost transmission by GPRS (General Packet Radio Service, GPRS). And it can identify out the transformer running state according to the acquisition data. The test results show that the method proposed has an excellent performance on correct ratio. And it can overcome the disadvantage of the traditional three-ratio method which lacks of fault coding and no fault types in the existent coding. Combining the wireless communication technology with the monitoring technology, the designed and developed system can greatly improve the real-time and continuity for the transformer' condition monitoring and fault diagnosis.