Physics-based machine learning method and the application to energy consumption prediction in tunneling construction

Representing causality in machine learning to predict control parameters is state-of-the-art research in intelligent control. This study presents a physics-based machine learning method providing a prediction model that guarantees enhanced interpretability conforming to physical laws. The proposed approach encodes physical knowledge as mapping relationships between variables in engineering dataset into the learning procedure through dimensional analysis. This derives causal relationships between the control parameter and its influencing factors. The proposed machine learning method's objective function is further improved by the penalty term in the regularization strategy. Verifications on the energy consumption prediction of tunnel boring machine prove that, the established model accords with basic principles in this field. Moreover, the proposed approach traces the impact of three major factors (structure, operation, and geology) along the construction section, offering each component's contribution rates to energy consumption. Compared with several commonly used machine learning algorithms, the proposed method reduces the need for large amounts of training data and demonstrates higher accuracy. The results indicate that the revealed causality and enhanced prediction performance of the proposed method advance the applicability of machine learning methods to intelligent control during construction.     

我国服务业集聚与地区城市化存在关联关系吗？——基于1987年～2011年省级面板数据格兰杰因果检验的分析

本文通过面板数据格兰杰因果检验的方法,对我国东、中、西及东北四区的各省份服务业集聚与城市化的关联关系进行了实证分析。研究发现,虽然存在着明显的区域经济差异,但四个地区各个省份服务业集聚与城市化都表现出没有或具有单向及双向的关联关系,其原因也各有不同。从区域城市化的角度而言,各个地区要因地制宜,从而在不同的发展阶段实现服务业集聚与城市化的良性互动。     

Causal inference from noisy time-series data — Testing the Convergent Cross-Mapping algorithm in the presence of noise and external influence

Convergent Cross-Mapping (CCM) has shown high potential to perform causal inference in the absence of detailed models. This has implications for the understanding of complex information systems, as well as complex systems more generally. This article assesses the strengths and weaknesses of the CCM algorithm by varying coupling strength and noise levels in a model system consisting of two coupled logistic maps. As expected, it is found that CCM fails to accurately infer coupling strength and even causality direction in strongly coupled synchronized time-series, but surprisingly also in the presence of intermediate coupling. It is further found that the presence of noise reduces the level of cross-mapping fidelity, where the converged value of the CCM correlation decreases roughly linearly as a function of the noise, while the convergence rate of the CCM correlation shows little sensitivity to noise. The article proposes controlled noise injections in intermediate-to-strongly coupled systems could enable more accurate causal inferences. Initial investigation of an external driving signal indicates robustness of CCM toward this potentially confounding influence. Given the inherent noisy nature of real-world systems, the findings enable a more accurate evaluation of CCM applicability and the article advances suggestions on how to overcome the method’s weaknesses.     

Causality relationship between coal consumption and GDP: Difference of major OECD and non-OECD countries

This paper uses Granger causality tests to examine the differences of causal relationships between coal consumption and GDP in major OECD and non-OECD countries, using data for the period of 1980–2005. What we discovered is that unidirectional causality running from GDP to coal consumption exists in Japan and China, and no causality relationship between coal consumption and GDP in India, South Korea and South Africa while the series are not cointegrated in USA. The major OECD or non-OECD countries especially China, India and South Africa should reduce their CO₂ emissions in coal consumption to reach sustainable development.     

Energy consumption and economic growth revisited: Does the size of unrecorded economy matter?

We analyze the long-run relationship between energy consumption and real gross domestic product (GDP) in Turkey taking into account the size of unrecorded economy. Since in developing countries, mainly due to the unrecorded economic activities, the official GDP is not measured correctly, the investigation of the linkage between energy consumption and official GDP may not give reliable results. In this study, empirical results for the case of Turkey over the period 1970–2005 suggest that there is a long-run equilibrium relationship between the officially calculated GDP and energy consumption. Besides, using the error-correction modeling technique, we find out that unidirectional causality runs from official GDP to energy in both short and long runs. However, when we take into account unrecorded economy, we detect neither cointegration nor causality between energy consumption and true GDP. These empirical findings imply that: first, energy conservation policies can be implemented in order to reduce greenhouse gas emissions without any adverse effect on the recorded economic activities; second the production function in the unrecorded economy is not stable. Furthermore, economic policies to combat unrecorded economy may not serve as a complement to energy conservation policies.     

Application of causality check and of the reduced variables method for experimental determination of Young''s modulus of a viscoelastic material

An accurate determination of the complex dynamic Young's modulus of a viscoelastic material, in a broad frequency range, is presented in this paper. Curves of Young's modulus of the tested material (a mixture of polypropylene and calcium carbonate), at different temperatures, are experimentally obtained by means of a laser sensor. The experimental curves are then gathered into a unique master curve, by applying the reduced variables method and a causality check on the curves. The master curve represents Young's modulus of the viscoelastic material over a much broader frequency range, with respect to the range of a single experimental curve.     

Assessment of complex environmental health problems: Framing the structures and structuring the frameworks

Many environmental risks are multi-faceted and their health consequences can be far-ranging in both time and space. It can be a challenging task to develop informed policies for such risks. Integrated environmental health impact assessment aims to support policy by assessing environmental health effects in ways that take into account the complexities and uncertainties involved. For such assessment to be successful, a clear and agreed conceptual framework is needed, which defines the issue under consideration and sets out the principles on which the assessment is based. Conceptual frameworks facilitate involvement of stakeholders, support harmonized discussions, help to make assumptions explicit, and provide a framework for data analysis and interpretation.Various conceptual frameworks have been developed for different purposes, but as yet no clear taxonomy exists. We propose a three-level taxonomy of conceptual frameworks for use in environmental health impact assessment. At the first level of the taxonomy, structural frameworks show the wide context of the issues at hand. At the second level, relational frameworks describe how the assessment variables are causally related. At the third level, this causal structure is translated into an operational model, which serves as a basis for analysis. The different types of frameworks are complementary and all play a role in the assessment process. The taxonomy is illustrated using a hypothetical assessment of urban brownfield development for residential uses.We suggest that a better understanding of types of conceptual frameworks and their potential roles in the different phases of assessment will contribute to more informed assessments and policies.     

Tents,Tweets, and Events: The Interplay Between Ongoing Protests and Social Media

Recent protests have fuelled deliberations about the extent to which social media ignites popular uprisings. In this article, we use time‐series data of Twitter, Facebook, and onsite protests to assess the Granger causality between social media streams and onsite developments at the Indignados, Occupy, and Brazilian Vinegar protests. After applying Gaussianization to the data, we found contentious communication on Twitter and Facebook forecasted onsite protest during the Indignados and Occupy protests, with bidirectional Granger causality between online and onsite protest in the Occupy series. Conversely, the Vinegar demonstrations presented Granger causality between Facebook and Twitter communication, and separately between protestors and injuries/arrests onsite. We conclude that the effective forecasting of protest activity likely varies across different instances of political unrest.     

ISM在大豆价格影响因素分析中的应用

为了对影响大豆价格的诸多因素及其相互关系进行系统研究,运用系统工程的方法建立了系统解释结构模型,通过建立有向图、矩阵变换等方法,系统分析了市场环境下大豆价格影响因素之间的内部结构、层次及因果关系,并对结果进行了分析,提出了相关的建议。     

Monitoring of crevice corrosion with the electrochemical frequency modulation technique

In this work, it is investigated whether electrochemical frequency modulation can be used to monitor crevice corrosion. With this novel technique, a potential signal consisting of two sine waves of different frequencies is applied to a corroding system. As a corroding system is non-linear in nature, the ac-response will contain non-linear components at harmonic and intermodulation frequencies. Analysis of these components can give information about the corrosion behavior of the system under investigation like the uniform corrosion rate. Crevice corrosion has been investigated by measuring the so-called “causality factors”, which are calculated from the ratio of the current components in the ac-response.According to ASTM standard G48, crevice corrosion has been investigated under the rubber band and cylindrical TFE-fluorocarbon block. Tests were also conducted by creating crevice between circular boundary of metallic sample and epoxy in which metal is engraved. Thus, three patterns of crevice corrosion have been used to see the response of causality factors for AISI 304. Besides some simulations with a simple mathematical model, experiments with artificial crevices were carried out in chloride containing water. The results show that in most cases these causality factors do change when the system goes from uniform corrosion to crevice corrosion.