Pipejacking clogging detection in soft alluvial deposits using machine learning algorithms
TL;DR: A baseline assessment of clogging in slurry-supported pipejacking is performed using a combination of TBM parameters and semi-empirical diagrams proposed in the literature, and the potential for one-class support vector machines (OCSVM), isolation forest and robust covariance (Robcov) to assess the tendency for clogging is explored.
About: This article is published in Tunnelling and Underground Space Technology.The article was published on 2021-07-01. It has received 34 citations till now. The article focuses on the topics: Clogging.
Citations
More filters
TL;DR: In this article, the micro-scale structural characteristics of the loess exposed to acetic acid, phosphoric acid, sodium hydroxide, and sodium sulfate respectively are studied using scanning electron microscopy, X-ray diffraction, and energy dispersive spectroscopy tests.
Abstract: Soil contamination not only can cause environmental problems but also lead to a notable change in the mechanical properties of soil. Loess widely distributed over North-West (NW) China is featured with the metastable structure, and chemical contaminants produced especially during the rapid development of NW China in recent years seriously threaten the fragile loess environments. When exposed to chemical contaminants, the impacts on the microstructural characteristics of the loess and the resultant mechanical properties are deemed critical for land reclamation in NW China. In light of this, the microscale structural characteristics of the loess exposed to acetic acid, phosphoric acid, sodium hydroxide, and sodium sulfate respectively are studied using scanning electron microscopy, X-ray diffraction, and energy dispersive spectroscopy tests. Additionally, their resultant macroscale mechanical properties are determined by direct shear tests. The deterioration mechanism regarding the microscale structural characteristics when exposed to the contaminants is revealed, and the resultant macroscale mechanical properties present a good correspondence with the deteriorated microscale structural characteristics. The findings of this work provide some guideposts for contaminated land reclamation in NW China.
74 citations
49 citations
TL;DR: Wang et al. as discussed by the authors explored the potential use of the EICP technology for the protection of heritage buildings in NW China and found that the modified version performed the best with the highest calcite precipitation.
Abstract: Given that acid-rich rainfall can cause serious damage to heritage buildings in NW China and subsequently accelerate their aging problem, countermeasure to protect their integrity and also to preserve the continuity of Chinese culture is in pressing need. Enzyme-induced calcite precipitation (EICP) that modifies mechanical properties of the soil through enhancing the inter-particle bonds by the precipitated crystals and the formation of other carbonate minerals is under a spotlight in recent years. EICP is considered as an alternative to the microbial-induced calcite precipitation (MICP) because cultivating soil microbes are considered to be challenging in field applications. This study conducts a series of test tube experiments to reproduce the ordinary EICP process, and the produced calcite precipitation is compared to that of the modified EICP process subjected to the effect of higher MgCl2, NH4Cl, and CaCl2 concentrations respectively. The modified EICP subjected to the effect of higher MgCl2 concentrations performs the best, with the highest calcite precipitation. The enhancement mechanism of calcite precipitation is well interpreted through elevating the activity of urease enzyme by introducing the magnesium ions. Further, the degradation of calcite precipitation presents when subjected to the effect of higher NH4Cl concentration. The decreasing activity of urease enzyme and the reverse EICP process play a leading role in degrading the calcite precipitation. Moreover, when subjected to the effect of higher CaCl2 concentrations, the slower rate of ureolytic hydrolysis and the decreasing activity of urease enzyme are primarily responsible for forming the ‘hijacking’ phenomenon of calcite precipitation. The findings of this study explore the potential use of the EICP technology for the protection of heritage buildings in NW China.
48 citations
TL;DR: In this paper , the authors explored the potential of applying the MICP technology to remediate Pb-rich water bodies and Pbcontaminated loess soil sites, and found that the Pb immobilization efficiency of above 85% is attained through PbCO3 and PB(CO3)2(OH)2 precipitation.
18 citations
References
More filters
Journal Article•
TL;DR: Scikit-learn is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems, focusing on bringing machine learning to non-specialists using a general-purpose high-level language.
Abstract: Scikit-learn is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems. This package focuses on bringing machine learning to non-specialists using a general-purpose high-level language. Emphasis is put on ease of use, performance, documentation, and API consistency. It has minimal dependencies and is distributed under the simplified BSD license, encouraging its use in both academic and commercial settings. Source code, binaries, and documentation can be downloaded from http://scikit-learn.sourceforge.net.
47,974 citations
Book•
01 Jan 1995TL;DR: Setting of the learning problem consistency of learning processes bounds on the rate of convergence ofLearning processes controlling the generalization ability of learning process constructing learning algorithms what is important in learning theory?
Abstract: Setting of the learning problem consistency of learning processes bounds on the rate of convergence of learning processes controlling the generalization ability of learning processes constructing learning algorithms what is important in learning theory?.
40,147 citations
Posted Content•
TL;DR: Scikit-learn as mentioned in this paper is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems.
Abstract: Scikit-learn is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems. This package focuses on bringing machine learning to non-specialists using a general-purpose high-level language. Emphasis is put on ease of use, performance, documentation, and API consistency. It has minimal dependencies and is distributed under the simplified BSD license, encouraging its use in both academic and commercial settings. Source code, binaries, and documentation can be downloaded from this http URL.
28,898 citations
01 Jan 2001
TL;DR: The algorithm is a natural extension of the support vector algorithm to the case of unlabeled data by carrying out sequential optimization over pairs of input patterns and providing a theoretical analysis of the statistical performance of the algorithm.
Abstract: Suppose you are given some data set drawn from an underlying probability distribution P and you want to estimate a simple subset S of input space such that the probability that a test point drawn from P lies outside of S equals some a priori specified value between 0 and 1. We propose a method to approach this problem by trying to estimate a function f that is positive on S and negative on the complement. The functional form of f is given by a kernel expansion in terms of a potentially small subset of the training data; it is regularized by controlling the length of the weight vector in an associated feature space. The expansion coefficients are found by solving a quadratic programming problem, which we do by carrying out sequential optimization over pairs of input patterns. We also provide a theoretical analysis of the statistical performance of our algorithm. The algorithm is a natural extension of the support vector algorithm to the case of unlabeled data.
4,410 citations
TL;DR: In this paper, the authors propose a method to estimate a function f that is positive on S and negative on the complement of S. The functional form of f is given by a kernel expansion in terms of a potentially small subset of the training data; it is regularized by controlling the length of the weight vector in an associated feature space.
Abstract: Suppose you are given some data set drawn from an underlying probability distribution P and you want to estimate a "simple" subset S of input space such that the probability that a test point drawn from P lies outside of S equals some a priori specified value between 0 and 1. We propose a method to approach this problem by trying to estimate a function f that is positive on S and negative on the complement. The functional form of f is given by a kernel expansion in terms of a potentially small subset of the training data; it is regularized by controlling the length of the weight vector in an associated feature space. The expansion coefficients are found by solving a quadratic programming problem, which we do by carrying out sequential optimization over pairs of input patterns. We also provide a theoretical analysis of the statistical performance of our algorithm. The algorithm is a natural extension of the support vector algorithm to the case of unlabeled data.
4,397 citations