Zuo Yunbo

Design of Intelligent Internet of Things for Equipment Maintenance

In order to strengthen the security guarantee and improve the scientific management level of important equipments, the intelligent internet of things for equipment maintenance (IITEM) was presented in this paper. IITEM collects the static and dynamic information of electrical and mechanical equipments by all kinds of sensors, and standardizes various types of information, so as to suit the information transmission needs of the Internet of Things. According to the characteristics of mechanical and electrical equipment, IITEM makes intelligent processing of device information, including establishment of signal sample database and knowledge base, extraction of running status feature of complex equipment, state analysis, model building, fault diagnosis, fault prediction, etc. Centering on the functional objectives of IITEM, the demonstration project of IITEM was designed. It could realize online safety monitoring, fault prediction and comprehensive protection of key equipment groups, avoid economic losses and casualties, extend equipment maintenance cycle, and promote establishment of coding system, standards and norms related to the intelligent internet of things for equipment maintenance, which should be suitable for the Chinese Internet of Things.

Application of the state deterioration evolution based on bi-spectrum in wind turbine

Concerning the problem of large rotating machinery like wind turbine which runs in low speed and non-stationary state, this research mainly focuses on separating fault trend feature from non-fault feature and the method of state deterioration evolution based on bi-spectrum. Firstly, the experimental signal such as low-speed startup vibration signal of rotor test rig in the normal state and a plurality of unbalanced state have been collected. Bi-spectrum method is applied to extract fault feature which submerged in complex background noise. On the basis of bi-spectrum analysis, the fault feature evolutionary matrix is defined to represent the state of equipment deterioration. The eigenvalues of fault feature evolutionary matrix are computed and fitted to a normal distribution curve, from which the mean value and variance are taken as fault feature parameters. Fault feature parameters are verified effectively by experiments. Finally, depending on fault feature parameters, graphical representation of state deterioration evolution is established. It is beneficial to provide guidelines for equipment deterioration trend. This method is applied to analyze the real vibration signal of wind turbine with the type of WD646/600 KW, and actual equipment condition verified the effectiveness of the proposed method.

Condition monitoring and diagnosis for grid-connected photovoltaic power system

The photovoltaic power generation directly converts the solar energy into electric energy through photovoltaic cell, which is an important way to solve energy shortage and environmental pollution. In order to raise the reliability and reduce costs of grid-connected photovoltaic power station, we analyze types of common faults and causes, and specify numerous devices and disperse layout, design wireless monitoring diagnosis system to realize wireless monitor and control for grid-connected photovoltaic power station in order to ensure the safe operation.

Research on quantification method of fault deterioration based on 1.5-spectrum feature extraction method

Whether the large rotating electromechanical equipment running in safe and stable state has an important impact on the economy and society, so, this paper concerned on quantification method of fault deterioration based on 1.5-spectrum feature extraction method. Running stability deterioration feature extracting method based on higher-order cumulant diagonal slice has been discussed. Experiment data of varying degrees of deterioration under unbalance types of deterioration were collected from rotor test rig, and deterioration feature were extracted. The concept of frequency band mean energy based on 1.5-spectrum was proposed, and a quantification method based on this concept was proposed. 1.5 dimension frequency band mean energy was calculated to represent overall level of varying degrees of deterioration under unbalance types of deterioration, so, state deterioration sequence was obtained. The experiment shows that quantification method of fault deterioration is sensitive to the deterioration process of normal operation state changing to mild deterioration state; and it hastrend property to the overall deterioration process of normal operation state changing to severe deterioration state.

Large rotating machinery local fault prediction based on sensor information fusion

Data process of large rotating machinery is in line with basic features of information fusion. A frame of fault diagnosis and prediction based on sensor information fusion is built. An improved extracting method of features is used to deal with the information fusion of single sensor, which raises the calculation efficiency and precision. The local fault prediction process is presented, and the fault deterioration trend is judged on the basis of dynamic weighted method. Actual example of Beijing Yanshan Petrochemical Co. shows the correction of conclusion.