Search

As the core power for the aviation industry, shipbuilding industry, and power station industry, it is essential to ensure that the gas turbines operate safely, reliably, greenly and efficiently. Learn from the advantages and disadvantages of the thermodynamic model based and data-driven artificial intelligence based gas-path diagnosis methods, a newfangled gas turbine gas-path diagnosis approach on the basis of knowledge data-driven artificial intelligence is proposed. That is a hybrid method of deep learning and gas path analysis. First, gas turbine thermodynamic model of the object to be diagnosed is constructed by adaptation modeling strategy. And the engine thermodynamic model is taken as the basal model to simulate various gas path faults. Secondly, a large number of knowledge data corresponding to component health parameters and gas turbine boundary condition parameters & gas-path measurable parameters are simulated by setting different component health parameter values and different boundary conditions based on this basal model. And next, define the vector composed of the boundary condition parameters & the gas path measurable parameters in the knowledge database as the input vector, and the component health parameter vector as the output vector, and a deep learning model for regression modeling of this knowledge database is designed. At last, along with the gas turbine engine runs, the trained model outputs component health parameters in real time after trained deep learning model is deployed to the corresponding gas turbine power plant. The simulation experiment results show that, accurate and quantified health parameters of each gas path component can be obtained by the proposed method in this paper, and the overall root mean square error does not exceed 0.033%, and the maximum relative error does not exceed 0.36%, which illustrates the proposed method has great application potential.

Data attacks from illegal access devices of the Internet of Things will cause serious interference and threats to the entire network. It is difficult to ensure the security of the communication system only by relying on traditional application layer password authentication methods. Therefore, it is of great significance to design an effective physical layer authentication system based on radio frequency fingerprints. Regarding the issue above, this paper proposes a novel physical layer authentication method for Internet of Things based on differential contour stellar. Through the test of identification and authentication of 20 WiFi network card devices from same manufacturer, same type and same batch, the recognition accuracy rate can reach 98.6% by the proposed method. The proposed method can improve the effect of radio frequency fingerprint identification from three aspects: i. The differential processing can effectively reduce the negative influence of phase rotation caused by carrier frequency offset and Doppler effects; ii. The color processing can effectively reduce the negative influence of random noise caused by channel noise; iii. It is suitable for processing large-scale networks and the massive data they bring.

To avoid disrepair and over-repair and improve gas turbine reliability and availability, gas-path diagnosis is an effective technical means of disseminating early warning information for evolving or impending deterioration. Aiming at the problems of existing gas-path diagnosis methods (i.e., data-driven based gas-path diagnosis and a model-based gas-path diagnosis), this paper proposes a novel gas-path diagnosis method based on model-data hybrid drive, which is a forward solving mathematical process, to ensure real-time monitoring performance. Through case analysis, the proposed diagnostic method is not limited by the intrinsic nonlinear shape change of the characteristic maps of the actual component, which has good diagnostic applicability. And after the quadratic feature extraction of the two-dimensional entropy features (i.e., Shannon entropy and exponential entropy features), it is convenient to obtain visualized gas turbine gas-path diagnosis results for the operation and maintenance personnel. Moreover, although the extracted two-dimensional entropy values will change slightly when the operating conditions change, it can maintain good inter-class separation and intra-class aggregation performance.

In recent years, signal processing theory and deep learning theory have been developed rapidly, providing a solid theoretical foundation for feature extraction and classification of bearing fault signals. Bearing fault signals are usually nonlinear and non-steady, traditional time-domain or frequency-domain methods are difficult to classify fault signals. Therefore, this paper proposes a bearing fault signal diagnosis method based on entropy feature fusion equipotential planet map, combined with constellation diagram the principle extracts the approximate entropy and permutation entropy of the original fault signal into two-dimensional features, uses the equipotential planet map to convert the entropy feature fault signal into images, uses the deep learning PCANet network to classify the fault signal, and performs the bearing fault data set simulation shows that the accuracy of the fault diagnosis model has reached 100%. The study of this method is expected to provide a reliable theoretical basis for related engineering practices in the field of fault diagnosis.

Gas turbine engines have been the key power machine for energy conversion & utilization in the 21st century efficiently and cleanly. To improve equipment reliability and availability, prolong service life and reduce O&M costs, gas path component diagnosis is an effective technique for detecting evolving deterioration. Although many diagnostic methods based on steady state or quasi-steady state have been obtained, but no complete scientific system of gas-path diagnosis has been formed yet. Aiming at the above problems, a research route of gas-path component fault diagnosis for gas turbine engine is proposed. The proposed research route provides a new solution for diagnosis for complex nonlinear thermodynamic systems.

With the rapid development of software radio and communication technologies, wireless communication environment is becoming more complicated. How to accurately identify communication modulation signals under low SNR environment has become a hot topic in current research. Fractal is an effective tool to describe the geometric irregularity and geometric scale characteristics, and feature extraction of signals has become possible by fractal theory. However, whether the communication signals have fractal characteristics, and whether the fractal feature can be used to achieve accurate feature extraction of signals is still a problem worth exploring. This paper first took QPSK signal as an example, and used mathematical methods to prove that the communication modulation signals have fractal characteristics. Then, an improved fractal box dimension algorithm was used to extract and recognize five signals to verify the effectiveness of fractal theory based feature extraction. Simulation results illustrate that the recognition result can achieve 97.8% even under the SNR of 10dB environment. This provides a theoretical basis for the wide application of fractal theory in the field of signal identification.

The efficient modulation communication systems via multiple antennas are considered. By using the impacting signals that been filtered after the special impacting filter (SIF) as the transmitted signals, the problem of combining the efficient modulation technique with the space-time coding has been addressed. Additionally, the theoretical analysis of the demodulation and the maximum likelihood (ML) decoding performance has been discussed. Numerical simulations support the theoretical analysing, show that the novel efficient modulation system via multiple antennas can achieve outstanding performance and enhance the space diversity compare with the single antenna efficient systems.

As bearing vibration signal is of nonlinear and nonstationary characteristics, and the condition-indicating information distribution in the vibration signal is complex, a new rolling bearing vibration signal analysis approach based on dual-entropy, holder coefficient and gray relation theory was proposed in this paper. Firstly, a dual-entropy and holder coefficient algorithm was proposed to extract the health status feature vector from the bearing vibration signals, and secondly a gray relation algorithm was used to achieve bearing fault diagnosis intelligently based on the extracted feature vector. The experimental analysis has demonstrated the proposed approach can simply and efficiently recognize various bearing fault types as well as severities with good real-time performance.

For a marine gas turbine generation set, the speed of power turbine must keep constant. Due to the varying load demand, the real and reactive power balance is damaged and thus the speed of power turbine becomes deviated from nominal value. It is necessary for an intelligent controller to keep the speed of power turbine within a permissible range during the varying load operation. The design of an adptive fuzzy PID controller fit for this marine gas turbine generation set were achieved. The simulating experiments were performed at different load conditions to test the effectiveness of the proposed method. Simulation results have shown the improved control performance. The proposed method overcomes the drawbacks of the traditional PID controller and improvement was achieved for the aspects of settling time, oscillations and overshoot.

Nowadays, it is difficult to identify the individual radiation source under low SNR environment. To this problem, the paper proposed a new fractal box dimension based algorithm, to calculate the fractal box dimension of different communication individual radio signals as the subtle characteristics. Basing on the traditional fractal box dimension, the proposed algorithm calculated the derivations of different reconstructing phase space points, and getting the fractal box dimension of the communications signals under different reconstructing conditions, which constitute a feature vector, to realize the purpose of extracting the subtle characteristics of individual radiation source more exactly. Finally, neural network was used to process and classify the fractal box dimension vector features, in order to achieve the purpose of classifying and recognizing different communication radiation source under complex environment.

With the increasingly complex electromagnetic environment of communication, as well as the gradually increased radar signal types, how to effectively identify the types of radar signals at low SNR becomes a hot topic. A radar signal recognition algorithm based on entropy features, which describes the distribution characteristics for different types of radar signals by extracting Shannon entropy, Singular spectrum Shannon entropy and Singular spectrum index entropy features, was proposed to achieve the purpose of signal identification. Simulation results show that, the algorithm based on entropies has good anti-noise performance, and it can still describe the characteristics of signals well even at low SNR, which can achieve the purpose of identification and classification for different radar signals.

Three-dimensional (3D) urban geological models (3DUGMS) are a very important support for urban planning, construction and management, for they can reduce the blindness in geological cognition and the huge risk in underground engineering design and construction with the representation of spatial structure and relationships of geological objects and phenomena. This paper firstly divides the data in 3D urban geological modeling (3DUGM) into six types: the source data in modeling, 3D geological structure models, 3D geological property models, 3D urban buildings and structures, Digital Elevation Models, 3D thematic surface models. Add then, the characteristics of these models, such as multi-element, multi-thematic, multi-dimensional, multi-scale, massive data, complex data association, are all analyzed in detail. Furthermore, based on the characteristics of every kind of models, we discuss their modeling methods. Specially, an emphasis is given for 3D urban geological structure modeling, of which the architecture, including the modeling methods, dynamic and incremental model updating, model smoothing and optimization, model uncertainty analysis and quality control, the integrated and collaborative visualization and analysis of massive model data, is presented in detail. At last, three models at the plain area, Tongzhou new region and CBD business district in Beijing are presented for showing the effective applications of 3DUGMS in the urban planning and construction.

With the rapid urban growth in China, there is an increasing requirement for the multi-element 3D urban geological information system (MUGIS), which can provide diverse and timely urban geological information for scientific and rational urban planning, safe urban construction and effective urban management. This paper firstly analyzes the significance, history and current status of urban geological informationization. Add then, the architecture of MUGIS, including support system, guarantee system, technology system, the whole process informationization in urban geology survey (UGS) and service system, is introduced in detail. Furthermore, we discuss the software system and several key technologies. Urban geological data center provides the integration and management of the multi-source, heterogeneous, massive, multi-dimensional, multistage, multi-scale, multi-thematic urban geological data. Urban geological data engine is the middleware providing transparent access for urban geological data. Urban geological information management and service basic platform provides the basic software functions for data management, modeling, analysis and sharing based on the integration of 2D GIS and 3D GIS. 3D urban geological modeling, a very important and difficult step, is highlighted. Analysis and assessment Model Base is important in the assistant decision-making for new region and subway line planning, dumping site selection, selection of emergency water source bases, etc. At last, based on the research in this paper, the development and applications of MUGIS in Beijing, Hangzhou and Hefei, China are presented.