Search

With the increasing application of artificial intelligence (AI) techniques in the field of structural health monitoring (SHM), there is a growing interest in explaining the decision-making of the black-box models in deep learning-based SHM methods. In this work, we take explainability a step further by using it to improve the performance of AI models. In this work, the results of explainable artificial intelligence (XAI) algorithms are used to reduce the input size of a one-dimensional convolutional neural network (1D-CNN), hence simplifying the CNN structure. To select the most accurate XAI algorithm for this purpose, we propose a new evaluation method, feature sensitivity (FS). Utilizing XAI and FS, a reduced dimension 1D-CNN regression model (FS-X1D-CNN) is proposed to locate and predict the torque of loose bolts in a 16-bolt connected aluminum plate under varying temperature conditions. The results were compared with 1D CNN with raw input vector (RI-1D-CNN) and deep autoencoders-1D-CNN (DAE-1D-CNN). It is shown that FS-X1D-CNN achieves the highest prediction accuracy with 5.95 mm in localization and 0.54 Nm in torque prediction, and converges 10 times faster than RI-1D-CNN and 15 times faster than DAE-1D-CNN, while only using a single lamb wave signal path., Structural Integrity & Composites, Group Yue, Group Groves

With the improvements in computational power and advances in chip and sensor technology, the applications of machine learning (ML) technologies in structural health monitoring (SHM) are increasing rapidly. Compared with traditional methods, deep learning based SHM (Deep SHM) methods are more efficient and have a higher accuracy. However, due to the black box nature of deep learning, the trained models are usually difficult to interpret, which blocks their practical application. Therefore, it is of great importance to develop explainable artificial intelligence (XAI) methods to understand the internal decision-making mechanisms of damage classification in Deep SHM. In this paper, a novel XAI algorithm named Deep Gradient-weighted Class Activation Mapping (Deep Grad CAM) is proposed by combining the existing method Grad CAM with the convolutional neural network (CNN) deconvolution mechanism. In this paper, Deep Grad CAM is used to interpret a one-dimensional convolutional neural network trained to detect bolt loosening based on guided wave propagation. The interpretation performance of Deep Grad CAM is compared with Grad CAM, and their performances are quantified using Infidelity. The results show that the Infidelity of Deep Grad CAM is much smaller than that of Grad CAM, indicating significant improvements in explanation accuracy and reliability., Structural Integrity & Composites, Group Yue, Group Groves

Continuous monitoring of tissue microphysiology is a key enabling feature of the organ-on-chip (OoC) approach for in vitro drug screening and disease modeling. Integrated sensing units are particularly convenient for microenvironmental monitoring. However, sensitive in vitro and real-time measurements are challenging due to the inherently small size of OoC devices, the characteristics of commonly used materials, and external hardware setups required to support the sensing units. Here we propose a silicon-polymer hybrid OoC device that encompasses transparency and biocompatibility of polymers at the sensing area, and has the inherently superior electrical characteristics and ability to house active electronics of silicon. This multi-modal device includes two sensing units. The first unit consists of a floating-gate field-effect transistor (FG-FET), which is used to monitor changes in pH in the sensing area. The threshold voltage of the FG-FET is regulated by a capacitively-coupled gate and by the changes in charge concentration in close proximity to the extension of the floating gate, which functions as the sensing electrode. The second unit uses the extension of the FG as microelectrode, in order to monitor the action potential of electrically active cells. The layout of the chip and its packaging are compatible with multi-electrode array measurement setups, which are commonly used in electrophysiology labs. The multi-functional sensing is demonstrated by monitoring the growth of induced pluripotent stem cell-derived cortical neurons. Our multi-modal sensor is a milestone in combined monitoring of different, physiologically-relevant parameters on the same device for future OoC platforms., EKL Processing, Biomechanical Engineering, Electronic Components, Technology and Materials

The provision of sanitation service requires fulfilment of system processes including containment, conveyance, treatment, and disposal/reuse—or the sanitation value chain (Trémolet, 2011; Blackett et al., 2014; Tilley et al., 2014) as shown in Figure 1. The conveyance process is further divided into emptying and transport for decentralized system or faecal sludge management (FSM) system, and with sewerage network for centralized system or sewer-based (SB) system. For low and middle income countries, FSM is the norm covering 60-100% of the population (WSP, 2016). However, irrespective of the type of sanitation system, the problem lies on unsustainable sanitation projects due to unaccounted life cycle costs and incomplete consideration of the entire sanitation chain (Moriarty et al., 2011; Fonseca et al., 2011)., Sanitary Engineering

Production of waste materials, via industrial and human activities, creates big environmental and economic problems but also opportunities to recover valuable resources. EU28 currently generates 461 million tons per year of ever more complex Construction and Demolition Waste (CDW) with average recycling rates of around 46%. There is still a significant loss of potential valuable minerals, metals and organic materials all over Europe. Considering the fact that public and private sectors have become aware of the urgency and importance of CDW recycling, the European Commission has taken initiatives towards sustainable treatment and recycling of CDW funding three tandem projects focusing on the development of an innovative and sustainable concrete recycling process. To that end, this article will firstly present the main achievements and ongoing activities for developing the innovative concrete recycling technology in the course of the EU C2CA, HISER and VEEP projects. In addition some figures related to the cost of each recycling unit process and the selling price of the recycled products are presented., Materials and Environment

Ninety five percent of the construction and demolition waste is recycled in the Netherlands. Most of it is used for low value applications such as road base materials; the use of secondary material in buildings is still less than 3%7. In order to recover waste for higher value applications, enhancing selective demolition and waste management practices is of crucial importance. In this study Life Cycle Assessment and Life Cycle Costing of a demolition project in Almere was carried out to identify the environmental and financial hotspots in the selective demolition and waste management in the Dutch context. Results suggest that (1) the best practice selective demolition and (2) the substitution of virgin concrete aggregate with secondary aggregate processed by Advanced Dry Recovery (ADR) system, will lead to environmental and financial improvements compared to the business as usual practice. On the building level, the advantage is mainly due to connecting the demolition and the re-development projects, which maximizes local reuse of old building components in the new building. The key of success for selective demolition is pre-audit to identify and connect to the market for material reuse. This is a direction that BIM (building information modeling) technology can contribute. With regards to the ADR concrete aggregate manufacturing, it was found that the transport distance for aggregate supply was the largest contributor to the environmental impacts and costs. Therefore it is important to locate ADR facilities next to concrete manufactures and/or provide ADR service on- site., Materials and Environment

Production of waste materials, via industrial and human activities, creates big environmental and economic problems but also opportunities to recover valuable resources. EU28 currently generates 461 million tons per year of ever more complex Construction and Demolition Waste (CDW) with average recycling rates of around 46%. There is still a significant loss of potential valuable minerals, metals and organic materials all over Europe. Considering the fact that public and private sectors have become aware of the urgency and importance of CDW recycling, the European Commission has taken initiatives towards sustainable treatment and recycling of CDW funding three tandem projects focusing on the development of an innovative and sustainable concrete recycling process. To that end, this article will firstly present the main achievements and ongoing activities for developing the innovative concrete recycling technology in the course of the EU C2CA, HISER and VEEP projects. In addition some figures related to the cost of each recycling unit process and the selling price of the recycled products are presented., Materials and Environment

Ninety five percent of the construction and demolition waste is recycled in the Netherlands. Most of it is used for low value applications such as road base materials; the use of secondary material in buildings is still less than 3%7. In order to recover waste for higher value applications, enhancing selective demolition and waste management practices is of crucial importance. In this study Life Cycle Assessment and Life Cycle Costing of a demolition project in Almere was carried out to identify the environmental and financial hotspots in the selective demolition and waste management in the Dutch context. Results suggest that (1) the best practice selective demolition and (2) the substitution of virgin concrete aggregate with secondary aggregate processed by Advanced Dry Recovery (ADR) system, will lead to environmental and financial improvements compared to the business as usual practice. On the building level, the advantage is mainly due to connecting the demolition and the re-development projects, which maximizes local reuse of old building components in the new building. The key of success for selective demolition is pre-audit to identify and connect to the market for material reuse. This is a direction that BIM (building information modeling) technology can contribute. With regards to the ADR concrete aggregate manufacturing, it was found that the transport distance for aggregate supply was the largest contributor to the environmental impacts and costs. Therefore it is important to locate ADR facilities next to concrete manufactures and/or provide ADR service on- site., Materials and Environment

The provision of sanitation service requires fulfilment of system processes including containment, conveyance, treatment, and disposal/reuse—or the sanitation value chain (Trémolet, 2011; Blackett et al., 2014; Tilley et al., 2014) as shown in Figure 1. The conveyance process is further divided into emptying and transport for decentralized system or faecal sludge management (FSM) system, and with sewerage network for centralized system or sewer-based (SB) system. For low and middle income countries, FSM is the norm covering 60-100% of the population (WSP, 2016). However, irrespective of the type of sanitation system, the problem lies on unsustainable sanitation projects due to unaccounted life cycle costs and incomplete consideration of the entire sanitation chain (Moriarty et al., 2011; Fonseca et al., 2011)., Sanitary Engineering

Materials and Environment

Materials and Environment

Structural Engineering, Civil Engineering and Geosciences

Structural Engineering, Civil Engineering and Geosciences