Papers by Author: Yu Gang Fan

Abstract: For the complex terrain, in long-distance slurry pipeline, the core equipment of the running pipeline - valve monitoring is particularly important. This paper based on the actual running conditions of Yunnan Dahongshan pipeline, developed an intelligent valve control system. Valve monitoring and management can be seen in this system, which combines software programming, measurement technology, communication networks, as well as order management, fault management, spare parts management, query statistics. Getting running parameters rely on the monitoring system, and then for the mathematical model of solid traffic in slurry pipeline transportation, the slurry weight can be measured. The system achieved valve monitoring and management very well, improving the long-distance slurry pipeline running reliability.

Abstract: The mechanism model needs to assume a lot of prerequisites, but it is lack of these conditions in the solid-liquid two-phase flow in long-distance pipeline, therefore there will be a deviation between the friction drag loss of mechanism model and the actual value. This paper adopted the least square support vector machine (LS-SVM) to fix the value of the mechanism model, and increase the prediction accuracy. Meanwhile, for improving real-time online LS-SVM performance, introducing the local LS-SVM. The experiment result shows, LS-SVM and local LS-SVM greatly improved the forecast accuracy, compared with the mechanism model correction.

Abstract: Designed and implemented acoustic emission signal acquisition system core with microprocessor STM32F103RB. Acquisition system included high sensitivity acoustic emission sensors: PXR20; signal conditioning for acoustic emission, used high-speed ADC AD9225 for A/D conversion; used FIFO module for data buffer; used USB to serial port technology for data communications and transmissions. Central control unit design included gain control of amplifier circuit, clock control of external AD-chip and data cache chip, data acquisition port control, data output port control. Experimental results show that the system implements a multi-channel, parallel, high-precision acquisition and transmission for acoustic emission data.

Abstract: This paper studies the content from the urgent needs of production practice, it will take mechanism analysis to be a breakthrough to solve the problem of the resistance loss of complex terrain of iron ore slurry transportation. Through the analysis of past formula of pipeline resistance loss, combined with the actual characteristics of Dahongshan pipeline, correction formula of pipeline transportation resistance loss is derived. And we use the actual production data to prove the accuracy of the formula, the error is under control within 10%. The formula ignores energy loss due to the movement of particles, so the bias between the calculated and measured values still exists. But the formula still has important engineering significance.

Abstract: Miniature unmanned helicopter (MUH) is a controlled member which is very complicated, due to their some characteristics such as highly nonlinear, close coupled, time-variation, open-loop unstable etc. The traditional method of identification is a whole model method. Although those can solve some hard problem, the time-variation is not treated well. The paper introduces a method of model building for miniature unmanned helicopter (MUH), based on local least square support vector machine. Namely the nearest samples to the predicted sample are selected online, and model building is finished by those samples with prediction. The feature of this method is that using the idea of local model building updates the model online, and the global model building brings the low ability of model generalization. In the last, compared with the traditional method of least square support vector machine in the experiment, the results show the algorithm is more effective.

Abstract: Under the premise of transportation inconvenient, reducing pollution and environmental protection, iron concentrate pipeline transportation developing rapidly. However, due to pipeline related to fluid mechanics, solid-liquid two-phase flow, rheology, and other subjects, many scientific problems are still not resolved. Because of these problems, a further study on running control, security management, and optimize operations of pipeline transportation are needed, ensuring pipeline security, stability and efficient running. Intelligent plant design of pipeline transportation presents in this paper, taking intelligent data integration technologies, holding real-time data, running conditions of pipeline transportation and equipment, devices modeling integrated into a platform, achieving optimal scheduling, the goal of intelligent scheduling, as a result it can improve the management level, achieve energy conservation, improve production efficiency.