Search

Fault diagnosis plays an essential role in maintaining the safe and stable operation of hydroelectric units. In this paper, an intelligent fault diagnosis method based on radar maps and improved GoogleNet by depthwise separate convolution (DSC) is proposed to address the problems of low recognition accuracy and weak computing speed of fault diagnosis models in the field of hydroelectric unit fault diagnosis at present. Firstly, a one-dimensional signal sequence is obtained and denoised. Secondly, five time-domain features are extracted and radar maps are plotted. Then, an improved GoogleNet intelligent fault diagnosis model based on DSC (DSC-GoogLeNet) is constructed for training and validation. To assess the effectiveness of the proposed model, two case studies are conducted using the simulated dataset of the rotor experimental bench and the actual measured dataset of a domestic hydroelectric power plant. The results demonstrate that the average recognition accuracy of the fault diagnosis method proposed in this paper is as high as 99.04% on the simulated dataset, and even though the recognition accuracy decreases on the actually measurement dataset, it still has a recognition rate of 98.79%. The fault diagnosis performance is better than the other types of comparison models. The results demonstrate that the proposed fault diagnosis method holds significant engineering applicability in the domain of safe operation of hydroelectric units. It effectively addresses the existing challenges in fault diagnosis within this field with accuracy, stability, and efficiency. [ABSTRACT FROM AUTHOR]

Speed governing control is significant in ensuring the stable operation of pumped storage units. In this study, a state-space equation mathematical model of the pumped storage governing system considering the complex hydraulic pipeline structure of the pumped storage plant is proposed to describe the system's dynamic behaviors under small disturbance conditions. Considering the frequent operating condition transitions and the complicated nonlinear dynamic characteristics of the pumped storage units, the fractional-order PID (FOPID) scheme that possesses a higher degree of control freedom than the traditional PID scheme is discussed in detail. To optimize the control parameters of the unit governor, an improved gravitational search algorithm (IGSA) that combines the basic searching mechanisms of the gravitational search algorithm and chaotic search, elastic sphere boundary treatment, and elite guidance strategy is developed. Comparative studies have been carried out under frequency and load disturbance conditions. Simulation results indicate that the control performance of FOPID is better than that of PID under diverse operating conditions and the proposed IGSA has satisfactory parameter optimization capability. [ABSTRACT FROM AUTHOR]

In today's human society, diesel generators (DGs) are widely applied in the human energy and electricity supply system due to its technical, operational, and economic advantages. This paper proposes an intelligent nonlinear H 2 / H ∞ robust controller based on the chaos particle swarm gravity search optimization algorithm (CPSOGSA), which controls the speed and excitation of a DG. In this method, firstly, establish the nonlinear mathematical model of the DG, and then design the nonlinear H 2 / H ∞ robust controller based on this. The direct feedback linearization and the H 2 / H ∞ robust control theory are combined and applied. Based on the design of the integrated controller for DG speed and excitation, the system's performance requirements are transformed into a standard robust H 2 / H ∞ control problem. The parameters of the proposed solution controller are optimized by using the proposed CPSOGSA. The introduction of CPSOGSA completes the design of an intelligent nonlinear H 2 / H ∞ robust controller for DG. The simulation is implemented in MATLAB/Simulink, and the results are compared with the PID control method. The obtained results prove that the proposed method can effectively improve the dynamic accuracy of the system and the ability to suppress disturbances and improve the stability of the system. [ABSTRACT FROM AUTHOR]

With the emerging of the Internet of Things, chemiresistive gas sensors have been extensively applied in industrial production, food safety, medical diagnosis, and environment detection, etc. Considerable efforts have been devoted to improving the gas‐sensing performance through tailoring the structure, functions, defects and electrical conductivity of sensitive materials. Among the numerous sensitive materials, mesoporous semiconductor metal oxides possess unparalleled properties, including tunable pore size, high specific surface area, abundant metal–oxygen bonds, and rapid mass transfer/diffusion behavior (Knudsen diffusion), which have been regarded as the most potential sensitive materials. Herein, the synthesis strategies for mesoporous metal oxides are overviewed, the classical functionalization techniques of sensitive materials are also systemically summarized as a highlight, including construction of mesoporous structure, regulation of micro‐nano structure (i.e., heterojunctions), noble metal sensitization (e.g., Au, Pt, Ag, Pd) and heteroatomic doping (e.g., C, N, Si, S). In addition, the structure–function relationship of sensitive materials has been discussed at molecular‐atomic level, especially for the chemical sensitization effect, elucidating the interface adsorption/catalytic mechanism. Moreover, the challenges and perspectives are proposed, which will open a new door for the development of intelligent gas sensor in various applications. [ABSTRACT FROM AUTHOR]