Search

A new intelligent diagnosis method based on a hybrid algorithm of multi-scale permutation entropy and multi-core limit learning machine was proposed to address the complex internal structure of reciprocating compressors, difficulties in extracting bearing clearance fault features, and low recognition accuracy. Firstly, a generalized multi-scale permutation entropy (GMPE) algorithm was proposed to solve the problem that the mean coarse-grained method of multi-scale permutation entropy in the multi-scale process “neutralized” the dynamic mutation behavior of the original signal to a certain extent and reduced the accuracy of entropy analysis. Then, in order to solve the limitations of kernel extreme learning machine in dealing with complex data sample classification, Gaussian kernel function, polynomial kernel function and perceptron kernel function were linearly superimposed to construct a hybrid kernel function, and a multiple kernel extreme learning machine (MKELM) model was proposed. The simulation results show that the fault diagnosis accuracy of the proposed method is as high as 98%, and the intelligent diagnosis of different types of bearing faults is realized efficiently. [ABSTRACT FROM AUTHOR]

In order too effectively mitigate losses induced by loess collapse which is normally characterized by suddenness, concealment, and difficulty in capturing precursor information, the investigation into new methods for monitoring of loess collapse holds great engineering and scientific significance. There still remains a lack of a reliable theoretical and / or practical basis for the application of acoustic emission technology in monitoring and early-warning of loess collapse, while this technique has been found successful rock slopes. The single side connected loess slope model tests with water contents of 3%, 7% and 10% were conducted. The tests were complemented by employing active waveguide method for real-time acoustic emission monitoring in order to explore the acoustic emission response characteristics during the process of loess. The destructive form of loess collapse and the time-sequence evolution of acoustic emission counts in the deformation and destruction process were also analyzed. The results indicate that the failure pattern of loess slope model with 3% or 10% water content is dominated by local collapse of small pieces. On the other hand, the failure pattern of loess model with 7% water content is dominated by the overall collapse of large pieces. With deformation, the value of acoustic emission events also increased. As the acoustic emission counts increased rapidly before the overall failure, the initial point can be regarded as a precursor of loess collapse. [ABSTRACT FROM AUTHOR]

Copyright of Science Technology & Engineering is the property of Chinese Society of Technology Economics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The pelican optimization algorithm (POA) has some defects, such as slow convergence speed, poor population diversity, and premature. To overcome these shortcomings, an improved algorithm was propped. The improved algorithm was proposed incorporating 3D spiral flight and a hybrid backward learning strategy. Firstly, the Gauss mapping was used to initialize the population to improve the population diversity. Secondly, the three-dimensional spiral flight and the hybrid optimal-worst backward learning strategy were used to strengthen the ability of the algorithm to jump out of the local optimum. Finally, the adaptive balance factor and adaptive step size were introduced to propose a pelican falling strategy to simulate the small changes. In the Finally, IPOA was tested by 12 benchmark functions and actual cases and compared with 8 bionic algorithms. Test results and Wilcoxon signed rank sum test results showing that IPOA has improved convergence accuracy and stability. [ABSTRACT FROM AUTHOR]

Copyright of Science Technology & Engineering is the property of Chinese Society of Technology Economics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Pre-excavation dewatering treatment before excavation of phreatic aquifer can cause surface settlement. It is of great significance to predict the surface settlement value in advance for practical engineering. The surface settlement value caused by pre-excavation dewatering treatment was solved by theoretical calculation and numerical simulation respectively. In theoretical calculation, the effect of group wells was considered, and the predicted drawdown curve of water level was put forward. The original groundwater level and the predicted drawdown curve were taken as the boundary, and the settlement amount was calculated in different regions. The final settlement amount was obtained after superposition. The PLAXIS 3D modeling was adopted in the numerical simulation, and the well unit was used to simulate the precipitation well. The fluid-structure interactions was used to solve the surrounding surface settlement during the pre-excavation dewatering period, and the variation law of pumping flow and pore pressure under the group well effect was revealed. In order to verify the feasibility of the theoretical calculation method, the calculation results of the design standards and the in-situ data are verified and analyzed. The results show that the theoretical calculation method and the numerical simulation value method can approach the measured value better, and has certain practical value in engineering. [ABSTRACT FROM AUTHOR]

The genesis of the Early Paleozoic granites in South China and the formation mechanism of the post-collision extensional environment are still controversial. The early Paleozoic Lichuan granite of South China was selected to carry out zircon U-Pb isotopic and whole-rock geochemistry studies, to further reveal its genesis, and analyzed the starting time and formation mechanism of the post-collision extensional environment. The Lichuan intrusion was formed at 443 Ma, which belonged to the product of the Silurian Landovian magmatic activity. The samples belong to the high potassium calc-alkaline granite series with high silicon and rich potassium. Its A/CNK value is 1.04～1.39, showing the characteristics of peraluminous granite. The trace elements in the sample showed that Ba, Nb, Sr, P, Ti were depleted and Rb, Th, U, K, Pb were enriched. Relative enrichment of light rare earths, strong negative Eu ano-maly (δEu=0.27～0.74). It has a low εNd (t) value (-8.4～-9.8), high (87Sr/86Sr)i value (0.478 83～0.723 64), high 104×Ga/Al (3.24～4.19) ratios. The above characteristics indicate that the Lichuan granite belongs to the category of A-type magmatic rocks. The elemental and isotopic geochemical characteristics indicate that the Lichuan peraluminous A-type granite may be the product of partial melting of the precambrian metasedimentary rocks. Combined with the geochronological characteristics of the high-grade metamorphic rocks and granites of the early Paleozoic Wuyi-Yunkai orogeny in South China, it is found that the early Paleozoic Wuyi block in South China has changed from a co-collisional environment to a post-collisional extensional environment since the Silurian Landovian. The extensional environment may be affected by the rapid crustal thinning and underplating of hotmantle magma induced themelting of the orogenic root and crust-mantle interaction. [ABSTRACT FROM AUTHOR]

Copyright of Science Technology & Engineering is the property of Chinese Society of Technology Economics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Science Technology & Engineering is the property of Chinese Society of Technology Economics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Science Technology & Engineering is the property of Chinese Society of Technology Economics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Science Technology & Engineering is the property of Chinese Society of Technology Economics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)