Towards risk-targeted seismic hazard models for Europe.

Standards and Codes of Practice for designing new constructions and for assessing and strengthening existing ones are usually based on uniform hazard maps, where different Limit States (LSs) are associated with different hazard-exceedance probabilities. This approach yields non-homogeneous LS-exceedance probabilities across a territory, thus failing to achieve the goal of uniform risk throughout a territory. Such lack of uniformity stems from estimating the probability of failure using capacity and demand models. If the capacity of new constructions-or the capacity increase of strengthened existing constructions-are designed based on a prescribed hazard-exceedance probability, then the seismic risk depends on both the structure (depending on the design philosophy and corresponding design objectives), through the capacity model, and the location, through the hazard model. The aim of this study is threefold. First, it provides a seismic probability assessment formulation and a risk-targeted intensity measure based on a linear model in log-log coordinates of the hazard, under the assumption of log-normal capacity and demand. The proposed framework introduces a factor that multiplies the code hazard-based demand to account either for intentional (from design) over-capacity or for undesired (e.g., in existing constructions) under-capacity. Second, this paper shows an application to peak ground accelerations in Europe considering parameters taken from Standards and Codes of Practice. The developed framework is used to determine the risk-target levels of peak ground acceleration used for design in Europe, for both new and existing constructions. Third, the obtained target risk levels are used to determine a risk-based intensity modification factor and a risk-based mean return period modification factor, which can be readily implemented in current Standards to achieve risk-targeted design actions, with equal LS-exceedance probability across the territory. The framework is independent of the chosen hazard-based intensity measure, be it the commonly used peak ground acceleration or any other measure. The results highlight that in large areas of Europe the design peak ground acceleration should be increased to achieve the proposed seismic risk target and that this is particularly significant for existing constructions, given their larger uncertainties and typical low capacity with respect to the code hazard-based demand.

Garbage detection and classification using a new deep learning-based machine vision system as a tool for sustainable waste recycling.

Waste recycling is a critical issue for environment pollution management while garbage classification determines the recycling efficiency. In order to reduce labor costs and increase garbage classification capacity, a machine vision system is established based on the deep learning and transfer learning. In this new method, an improved MobileNetV2 deep learning model is proposed for garbage detection and classification, where the attention mechanism is introduced into the first and last convolution layers of the MobileNetV2 model to improve the recognition accuracy and the transfer learning uses a set of pre-trained weight parameters to extend the model generalization ability. In addition, the principal component analysis (PCA) is employed to reduce the dimension of the last fully connected layer to enable real-time operation of the developed model on an edge device. The experimental results demonstrate that the proposed method generates 90.7 % of the garbage classification accuracy on the "Huawei Cloud" datasets, the average inference time is 600 ms on the raspberry Pi 4B microprocessor, and the model volume compression is 30.1 % of the basic MobileNetV2 model. Furthermore, a garbage sorting porotype is designed and manufactured to evaluate the performance of the proposed MobileNetV2 model on the real-world garbage identification, which turns out that the average garbage classification accuracy is 89.26 %. Hence, the developed garbage sorting porotype can be used a effective tool for sustainable waste recycling.

Adaptive Contrastive Learning with Label Consistency for Source Data Free Unsupervised Domain Adaptation.

Unsupervised domain adaptation, which aims to alleviate the domain shift between source domain and target domain, has attracted extensive research interest; however, this is unlikely in practical application scenarios, which may be due to privacy issues and intellectual rights. In this paper, we discuss a more challenging and practical source-free unsupervised domain adaptation, which needs to adapt the source domain model to the target domain without the aid of source domain data. We propose label consistent contrastive learning (LCCL), an adaptive contrastive learning framework for source-free unsupervised domain adaptation, which encourages target domain samples to learn class-level discriminative features. Considering that the data in the source domain are unavailable, we introduce the memory bank to store the samples with the same pseudo label output and the samples obtained by clustering, and the trusted historical samples are involved in contrastive learning. In addition, we demonstrate that LCCL is a general framework that can be applied to unsupervised domain adaptation. Extensive experiments on digit recognition and image classification benchmark datasets demonstrate the effectiveness of the proposed method.

A New Deep Model for Detecting Multiple Moving Targets in Real Traffic Scenarios: Machine Vision-Based Vehicles.

When performing multiple target detection, it is difficult to detect small and occluded targets in complex traffic scenes. To this end, an improved YOLOv4 detection method is proposed in this work. Firstly, the network structure of the original YOLOv4 is adjusted, and the 4× down-sampling feature map of the backbone network is introduced into the neck network of the YOLOv4 model to splice the feature map with 8× down-sampling to form a four-scale detection structure, which enhances the fusion of deep and shallow semantics information of the feature map to improve the detection accuracy of small targets. Then, the convolutional block attention module (CBAM) is added to the model neck network to enhance the learning ability for features in space and on channels. Lastly, the detection rate of the occluded target is improved by using the soft non-maximum suppression (Soft-NMS) algorithm based on the distance intersection over union (DIoU) to avoid deleting the bounding boxes. On the KITTI dataset, experimental evaluation is performed and the analysis results demonstrate that the proposed detection model can effectively improve the multiple target detection accuracy, and the mean average accuracy (mAP) of the improved YOLOv4 model reaches 81.23%, which is 3.18% higher than the original YOLOv4; and the computation speed of the proposed model reaches 47.32 FPS. Compared with existing popular detection models, the proposed model produces higher detection accuracy and computation speed.

Evaluation of Different Bearing Fault Classifiers in Utilizing CNN Feature Extraction Ability.

In aerospace, marine, and other heavy industries, bearing fault diagnosis has been an essential part of improving machine life, reducing economic losses, and avoiding safety problems caused by machine bearing failures. Most existing bearing fault diagnosis methods face challenges in extracting the fault features from raw bearing fault data. Compared with traditional methods for bearing fault characteristics extraction, deep neural networks can automatically extract intrinsic features without expert knowledge. The convolutional neural network (CNN) was utilized most widely in extracting representative features of bearing faults. Fundamental to this, the hybrid models based on the CNN and individual classifiers were proposed to diagnose bearing faults. However, CNN may not be suitable for all bearing fault classifiers. It is crucial to identify the classifiers which can maximize the CNN feature extraction ability. In this paper, four hybrid models based on CNN were built, and their fault detection accuracy and efficiency were compared. The comparative analysis showed that the random forest (RF) and support vector machine (SVM) could make full use of the CNN feature extraction ability.

Damage Detection for Conveyor Belt Surface Based on Conditional Cycle Generative Adversarial Network.

The belt conveyor is an essential piece of equipment in coal mining for coal transportation, and its stable operation is key to efficient production. Belt surface of the conveyor is vulnerable to foreign bodies which can be extremely destructive. In the past decades, much research and numerous approaches to inspect belt status have been proposed, and machine learning-based non-destructive testing (NDT) methods are becoming more and more popular. Deep learning (DL), as a branch of machine learning (ML), has been widely applied in data mining, natural language processing, pattern recognition, image processing, etc. Generative adversarial networks (GAN) are one of the deep learning methods based on generative models and have been proved to be of great potential. In this paper, a novel multi-classification conditional CycleGAN (MCC-CycleGAN) method is proposed to generate and discriminate surface images of damages of conveyor belt. A novel architecture of improved CycleGAN is designed to enhance the classification performance using a limited capacity images dataset. Experimental results show that the proposed deep learning network can generate realistic belt surface images with defects and efficiently classify different damaged images of the conveyor belt surface.

Understanding Engineers' Responsibilities: A Prerequisite to Designing Engineering Education : Commentary on "Educating Engineers for the Public Good Through International Internships: Evidence from a Case Study at Universitat Politècnica de València".

The development of the curriculum for engineering education (course requirements as well as extra-curricular activities like study abroad and internships) should be based on a comprehensive understanding of engineers' responsibilities. The responsibilities that are constitutive of being an engineer include striving to fulfill the standards of excellence set by technical codes; to improve the idealized models that engineers use to predict, for example, the behavior of alternative designs; and to achieve the internal goods such as safety and sustainability as they are reflected in the design codes. Globalization has implications for these responsibilities and, in turn, for engineering education, by, for example, modifying the collection of possible solutions recognized for existing problems. In addition, international internships can play an important role in fostering the requisite moral imagination of engineering students.

A Reliability-Based Capability Approach.

This article proposes a rigorous mathematical approach, named a reliability-based capability approach (RCA), to quantify the societal impact of a hazard. The starting point of the RCA is a capability approach in which capabilities refer to the genuine opportunities open to individuals to achieve valuable doings and beings (such as being mobile and being sheltered) called functionings. Capabilities depend on what individuals have and what they can do with what they have. The article develops probabilistic predictive models that relate the value of each functioning to a set of easily predictable or measurable quantities (regressors) in the aftermath of a hazard. The predicted values of selected functionings for an individual collectively determine the impact of a hazard on his/her state of well-being. The proposed RCA integrates the predictive models of functionings into a system reliability problem to determine the probability that the state of well-being is acceptable, tolerable, or intolerable. Importance measures are defined to quantify the contribution of each functioning to the state of well-being. The information from the importance measures can inform decisions on optimal allocation of limited resources for risk mitigation and management.

Modeling the resilience of critical infrastructure: the role of network dependencies.

Water and wastewater network, electric power network, transportation network, communication network, and information technology network are among the critical infrastructure in our communities; their disruption during and after hazard events greatly affects communities' well-being, economic security, social welfare, and public health. In addition, a disruption in one network may cause disruption to other networks and lead to their reduced functionality. This paper presents a unified theoretical methodology for the modeling of dependent/interdependent infrastructure networks and incorporates it in a six-step probabilistic procedure to assess their resilience. Both the methodology and the procedure are general, can be applied to any infrastructure network and hazard, and can model different types of dependencies between networks. As an illustration, the paper models the direct effects of seismic events on the functionality of a potable water distribution network and the cascading effects of the damage of the electric power network (EPN) on the potable water distribution network (WN). The results quantify the loss of functionality and delay in the recovery process due to dependency of the WN on the EPN. The results show the importance of capturing the dependency between networks in modeling the resilience of critical infrastructure.

The responsibilities of engineers.

Knowledge of the responsibilities of engineers is the foundation for answering ethical questions about the work of engineers. This paper defines the responsibilities of engineers by considering what constitutes the nature of engineering as a particular form of activity. Specifically, this paper focuses on the ethical responsibilities of engineers qua engineers. Such responsibilities refer to the duties acquired in virtue of being a member of a group. We examine the practice of engineering, drawing on the idea of practices developed by philosopher Alasdair MacIntyre, and show how the idea of a practice is important for identifying and justifying the responsibilities of engineers. To demonstrate the contribution that knowledge of the responsibilities of engineers makes to engineering ethics, a case study from structural engineering is discussed. The discussion of the failure of the Sleipner A Platform off the coast of Norway in 1991 demonstrates how the responsibilities of engineers can be derived from knowledge of the nature of engineering and its context.

A scale of risk.

This article proposes a conceptual framework for ranking the relative gravity of diverse risks. This framework identifies the moral considerations that should inform the evaluation and comparison of diverse risks. A common definition of risk includes two dimensions: the probability of occurrence and the associated consequences of a set of hazardous scenarios. This article first expands this definition to include a third dimension: the source of a risk. The source of a risk refers to the agents involved in the creation or maintenance of a risk and captures a central moral concern about risks. Then, a scale of risk is proposed to categorize risks along a multidimensional ranking, based on a comparative evaluation of the consequences, probability, and source of a given risk. A risk is ranked higher on the scale the larger the consequences, the greater the probability, and the more morally culpable the source. The information from the proposed comparative evaluation of risks can inform the selection of priorities for risk mitigation.

Classification and moral evaluation of uncertainties in engineering modeling.

Engineers must deal with risks and uncertainties as a part of their professional work and, in particular, uncertainties are inherent to engineering models. Models play a central role in engineering. Models often represent an abstract and idealized version of the mathematical properties of a target. Using models, engineers can investigate and acquire understanding of how an object or phenomenon will perform under specified conditions. This paper defines the different stages of the modeling process in engineering, classifies the various sources of uncertainty that arise in each stage, and discusses the categories into which these uncertainties fall. The paper then considers the way uncertainty and modeling are approached in science and the criteria for evaluating scientific hypotheses, in order to highlight the very different criteria appropriate for the development of models and the treatment of the inherent uncertainties in engineering. Finally, the paper puts forward nine guidelines for the treatment of uncertainty in engineering modeling.

Gauging the societal impacts of natural disasters using a capability approach.

There is a widely acknowledged need for a single composite index that provides a comprehensive picture of the societal impact of disasters. A composite index combines and logically organizes important information policy-makers need to allocate resources for the recovery from natural disasters; it can also inform hazard mitigation strategies. This paper develops a Disaster Impact Index (DII) to gauge the societal impact of disasters on the basis of the changes in individuals' capabilities. The DII can be interpreted as the disaster impact per capita. Capabilities are dimensions of individual well-being and refer to the genuine opportunities individuals have to achieve valuable states and activities (such as being adequately nourished or being mobile). After discussing the steps required to construct the DII, this article computes and compares the DIIs for two earthquakes of similar magnitude in two societies at different levels of development and of two disasters (earthquake and wind storm) in the same society.

The acceptability and the tolerability of societal risks: a capabilities-based approach.

In this paper, we present a Capabilities-based Approach to the acceptability and the tolerability of risks posed by natural and man-made hazards. We argue that judgments about the acceptability and/or tolerability of such risks should be based on an evaluation of the likely societal impact of potential hazards, defined in terms of the expected changes in the capabilities of individuals. Capabilities refer to the functionings, or valuable doings and beings, individuals are able to achieve given available personal, material, and social resources. The likely impact of a hazard on individuals' capabilities should, we argue, be compared against two separate thresholds. The first threshold specifies the minimum level of capabilities attainment that is acceptable in principle for individuals to have in the aftermath of a hazard over any period of time. This threshold captures the level that individuals' capabilities ideally should not fall below. A risk is acceptable if the probability that the attained capabilities will be less than the acceptable level is sufficiently small. In practice, it can be tolerable for some individuals to temporarily fall below the acceptable threshold, provided this situation of lower capabilities attainment is temporary, reversible, and the probability that capabilities will fall below a tolerability threshold is sufficiently small. This second, tolerable threshold delimits an absolute minimum level of capabilities attainment below which no individual in a society should ever fall, regardless of whether that level of capabilities attainment is temporary or reversible. In this paper, we describe and justify this Capabilities-based Approach to the acceptability and tolerability of risks. We argue that the proposed theoretical framework avoids the limitations in current approaches to acceptable risk. The proposed approach focuses the attention of risk analysts directly on what should be our primary concern when judging the acceptability and the tolerability of risks, namely, how risks impact the well-being of individuals in a society. Also, our Capabilities-based Approach offers a transparent, easily communicable way for determining the acceptability and the tolerability of risks.

Determining public policy and resource allocation priorities for mitigating natural hazards: a capabilities-based approach.

This paper proposes a Capabilities-based Approach to guide hazard mitigation efforts. First, a discussion is provided of the criteria that should be met by an adequate framework for formulating public policy and allocating resources. This paper shows why a common decision-aiding tool, Cost-benefit Analysis, fails to fulfill such criteria. A Capabilities-based Approach to hazard mitigation is then presented, drawing on the framework originally developed in the context of development economics and policy. The focus of a Capabilities-based Approach is protecting and promoting the well-being of individuals. Capabilities are dimensions of well-being and specified in terms of functionings. Functionings capture the various things of value an individual does or becomes in his or her life, including being alive, being healthy, and being sheltered. Capabilities refer to the real achievability of specific functionings. In the context of hazard mitigation, from a Capabilities-based Approach, decision- and policy-makers should consider the acceptability and tolerability of risks along with the affectability of hazards when determining policy formulation and resource allocation. Finally, the paper shows how the proposed approach satisfies the required criteria, and overcomes the limitations of Cost-benefit Analysis, while maintaining its strengths.

The role of society in engineering risk analysis: a capabilities-based approach.

This article proposes a new conceptual framework in engineering risk analysis to account for the net impact of hazards on individuals in a society. It analyzes four limitations of prevailing approaches to risk analysis and suggests a way to overcome them. These limitations are a result of how societal impacts are characteristically accounted for and valued. Prevailing approaches typically focus too narrowly on the consequences of natural or man-made hazards, not accounting for the broader societal impacts of such hazards. Such approaches lack a uniform and consistent metric for accounting for the impact of the nonquantifiable consequences (like psychological trauma or societal impacts) and rely upon implicit and potentially inaccurate value judgments when evaluating risks. To overcome these limitations, we propose an alternative, Capabilities-Based Approach to the treatment of society in risk analysis. A similar approach is currently used by the United Nations to quantitatively measure the degree of development in countries around the world. In a Capabilities-Based Approach, the potential benefits and losses due to a hazard are measured and compared in a uniform way by using individual capabilities (functionings individuals are able, still able, or unable to achieve) as a metric. This Capabilities-Based Approach provides a foundation for identifying and quantifying the broader, complex societal consequences of hazards and is based on explicit, value judgments. The Capabilities-Based Approach can accommodate different methods or techniques for risk determination and for risk evaluation and can be used in assessing risk in diverse types of hazards (natural or man-made) and different magnitudes that range from minor to catastrophic. In addition, implementing a Capabilities-Based Approach contributes to the development of a single standard for public policy decision making, since a Capabilities-Based Approach is already in use in development economics and policy.

Analytical studies of shape memory alloy dampers for structural control of base isolated bridges

Base isolation provides a very effective passive method of protecting bridges from the hazard of earthquake. The proposed smart isolation system combines the laminated rubber bearing with the device made of shape memory alloy (SMA). The constitutive law for superelastic material is extended to describe a hardening of the stress-strain relation of SMA at large strain levels. The smart base isolation utilizes the different responses of the SMA at different levels of strain to control the displacements of the rubber bearing at various excitation levels. At the same time the hysteresis of the alloy is used to increase the energy dissipation capacity. The performance of the smart base isolation is compared with the responses of laminated rubber bearing with lead core to quantify the benefits of applying SMA for isolation of elevated highway bridge. (AU)