Water Leakage Research Articles

Performance comparison of geopolymer and clay-cement grouting pastes and goaf effect evaluation of grouting backfilling method

The problem of goaf treatment has become more and more prominent, posing a significant risk to the safety of transportation and causing environmental damage if it is not treated properly. This study aims to conduct a comparative analysis of various grouting pastes and evaluate their application in goaf treatment according to grouting backfilling. This research begins by discussing different grouting pastes’ properties, including clay-cement composite grouting material and geopolymer grouting material, which have excellent engineering performance, environmental friendliness, and are easy to operate in complex geological environments. Moreover, the factors affecting the performance of grouting pastes, such as water-solid ratio and curing time, are also examined. Based on detailed information about the boreholes provided by drilling television, a reasonable treatment plan is formulated for goaf treatment. Finally, this study evaluates the effectiveness of different grouting pastes in real-world goaf treatment projects. The study draws the following conclusions: a direct relationship exists among flowability, setting time as well as water-solid ratio. An inverse relationship exists between the compressive strength of grouting materials and the water-solid ratio. Drilling data reveals complex goaf structures with defects such as water leakage, collapse and cavity, indicating potential geological risks in shallow areas. A treatment plan is formulated based on the geological conditions of goafs by drilling television. The effectiveness of backfill grouting in goaf areas is inspected using ground-penetrating radar (GPR) technology, and results indicate that adjusting water-solid ratio of grouting material can improve treatment effects.

Domain-informed variational neural networks and support vector machines based leakage detection framework to augment self-healing in water distribution networks

The reduction of water leakage is essential for ensuring sustainable and resilient water supply systems. Despite recent investments in sensing technologies, pipe leakage remains a significant challenge for the water sector, particularly in developed nations like the UK, which suffer from aging water infrastructure. Conventional models and analytical methods for detecting pipe leakage often face reliability issues and are generally limited to detecting leaks during nighttime hours. Moreover, leakages are frequently detected by the customers rather than the water companies. To achieve substantial reductions in leakage and enhance public confidence in water supply and management, adopting an intelligent detection method is crucial. Such a method should effectively leverage existing sensor data for reliable leakage identification across the network. This not only helps in minimizing water loss and the associated energy costs of water treatment but also aids in steering the water sector towards a more sustainable and resilient future. As a step towards ‘self-healing’ water infrastructure systems, this study presents a novel framework for rapidly identifying potential leakages at the district meter area (DMA) level. The framework involves training a domain-informed variational autoencoder (VAE) for real-time dimensionality reduction of water flow time series data and developing a two-dimensional surrogate latent variable (LV) mapping which sufficiently and efficiently captures the distinct characteristics of leakage and regular (non-leakage) flow. The domain-informed training employs a novel loss function that ensures a distinct but regulated LV space for the two classes of flow groupings (i.e., leakage and non-leakage). Subsquently, a binary SVM classifier is used to provide a hyperplane for separating the two classes of LVs corresponding to the flow groupings. Hence, the proposed framework can be efficiently utilised to classify the incoming flow as leakage or non-leakage based on the encoded surrogates LVs of the flow time series using the trained VAE encoder. The framework is trained and tested on a dataset of over 2000 DMAs in North Yorkshire, UK, containing water flow time series recorded at 15-minute intervals over one year. The framework performs exceptionally well for both regular and leakage water flow groupings with a classification accuracy of over 98 % on the unobserved test dataset

Study of the physicochemical, mineralogical, and geotechnical properties of clayey soils to improve the durability of eco-construction materials in the rural region

This study aims to preserve and improve the durability of earthen buildings in rural areas of Morocco, particularly in the Al Haouz province of the Marrakech-Safi region. In this paper, a survey was conducted to identify defects in earthen building materials and investigate factors that lead villagers to use cement over traditional earth-based construction methods. To propose solutions to these shortcomings, mineralogical, physicochemical, and geotechnical studies were conducted on four soils commonly used as rural building materials. Subsequently, some corrections were implemented in the treatment of raw materials and the production process of compressed earth blocks (CEBs), which were then subjected to mechanical, physical, and morphological characterization. The findings of this study revealed several building pathologies in earthen construction in this region, including ceiling water leaks, formulations made, and cracks. Research shows that the key factors influencing the durability of building materials are particle size distribution, mineralogy composition, moisture content, and construction process.

Pilot Scale Assessment of High-Pressure Processing (HPP) to Enhance Microbiological Quality and Shelf Life of Fresh Ready-to-Eat (RTE) Blue Crab Meat.

Blue crab (Callinectes sapidus) is a highly valuable wild fishery species of crab native to the waters of the western Atlantic Ocean and the Gulf of Mexico. The annual commercial production of live blue crabs is approximately 50,000 metric tons with a dockside value of USD 200 million. Presently the US blue crab processing industry sells crab meat in three basic forms: fresh crab meat, pasteurized crab meat, and frozen crab meat. By far "Fresh" is the most desirable form of crab meat. However, fresh crab meat has a limited shelf life. This study evaluated the effects of high-pressure processing (HPP) on enhancing the microbiological quality and shelf life of blue crab meat. Live blue crabs were pressure-cooked in a retort (≥115 °C for 4-6 min). The crab meat was handpicked, packed in plastic containers with seals, subjected to HPP treatment, and stored at 4 °C. Container integrity and water leakage issues were examined by observation in addition to weight comparison before and after HPP treatment; the shelf life of crab meat with and without HPP treatments was examined via microbiological tests and sensory evaluations. Results show that polypropylene containers sealed with 10K OTR (oxygen transmission rate) film could withstand high pressure without water leakage issues; HPP treatment at 600 MPa for 3 min could extend the shelf life of fresh, cooked, and handpicked crab meat from 6 days to 18 days based on the strictest APC (aerobic plate account) limit (APC ≤ 100,000 CFU/g). The sensory quality of the HPP-treated crab meat was well accepted throughout the 3-week storage period. The results support the use of HPP as an effective non-thermal processing technology to enhance the microbiological quality and extend the shelf life of fresh RTE blue crab meat.

Abstract A099: Higher proportions of racial and ethnic minority cancer survivors experience health-related social needs compared to non-Hispanic cancer survivors in the All of Us Research Program

Abstract Background: Cancer survivors are at a greater risk of experiencing financial hardship and unmet health-related social needs (HRSN), such as food or housing insecurity, after a cancer diagnosis. HRSN has been associated with lower access, utilization, and delivery of timely quality cancer care and poorer cancer-related outcomes. Cancer survivors experiencing HRSN may also be less likely to engage and participate in research (e.g., clinical trials). As the most diverse cohort worldwide, the All of Us Research Program provides a unique opportunity to better understand the prevalence of HRSN among cancer survivors. The purpose of this study is to characterize the proportion of All of Us cancer survivors experiencing food and housing insecurity and identify potential differences across racial and ethnic populations. Results: We identified a total of 37,146 All of Us cancer survivors out of 412,211 core participants. Of these, the majority self-identified as non-Hispanic White (84%), 4% as non-Hispanic Black, 4% as Hispanic, 2% as multiracial, and <1% self-reported as Asian, Native American/American Indian, Native Hawaiian/Pacific Islander, or Middle Eastern/North African. Among cancer survivors, 5.5% stated being worried about running out of food and 4.4% stated that their food didn’t last and did not have money to get more. While only about 1% of cancer survivors stated moving more than once within the last 12 months, 6.1% stated that they worried about not having a place to live and 16% experienced at least one poor housing quality characteristic (e.g., mold, water leak, or bug infestation). There was a significant difference in the proportion of cancer patients who reported food and housing insecurity across racial and ethnic populations (p<0.001), with a higher proportion of cancer survivors from racial and ethnic groups underrepresented in biomedical research experiencing these HRSN. Conclusion: While less than 6% of cancer survivors in the All of Us Program experienced food or housing insecurity, the proportion of racial and ethnic minority populations experiencing these HRSN was higher compared to non-Hispanic White cancer survivors. Future research should assess the impact of experiencing HRSN on research participation and health related outcomes within the All of Us Research Program. Citation Format: JoAnn Smith, Samantha Tesfaye, Martin Mendoza, Janeth Sanchez. Higher proportions of racial and ethnic minority cancer survivors experience health-related social needs compared to non-Hispanic cancer survivors in the All of Us Research Program [abstract]. In: Proceedings of the 16th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2023 Sep 29-Oct 2;Orlando, FL. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2023;32(12 Suppl):Abstract nr A099.

Hybrid diagnostic approach for the diagnosis of district heating networks

Decarbonization of the heating sector is a mandatory target towards climate neutrality by 2050. In this framework, District Heating Networks (DHNs) do play an important role since the heat carrier is dispatched from a heat source to end-users.Reliability of DHNs can be affected by several faults, of which the negative consequences can be prevented by employing diagnostic methodologies to evaluate the health state of the DHN and promptly localize the fault cause.In the literature, DHN faults are usually detected by means of physics-based and data-driven methodologies, but their drawbacks may hinder their application. Thus, this paper proposes a hybrid approach composed of two steps aimed at detecting the most common faults occurring in DHNs, i.e., water leakages as well as anomalous heat and pressure losses. First, a data-driven diagnostic methodology is employed to assess whether a fault is occurring. Then, a physics-based diagnostic approach identifies the health indices of each pipe of the DHN, the fault position, its type and magnitude. In this paper, the hybrid diagnostic approach is applied to the DHN of the campus of the University of Parma, where different faults were artificially implanted.The diagnostic approach proves to correctly detect and identify the implanted faults, by also correctly estimating their magnitude even in the most challenging scenarios.

Wind-driven rain tightness of building-integrated photovoltaics panels

The exposure to wind-driven rain (WDR) is a key factor impacting the performance and the durability of the building envelope. Building-integrated photovoltaic (BIPV) panels are increasingly used as roofing and façade materials, but little information is available on their weather protection performance. Although WDR exposure has been qualitatively investigated in laboratories, only few studies have directly quantified the water intrusion through BIPV. This article presents the results from a WDR laboratory test of a BIPV product, where water intrusion was both qualitatively and quantitatively investigated. Furthermore, as roof integration is the primary function of the studied BIPV panels, the results from the same test performed on another traditional roofing material, i.e., concrete tiles, are described and discussed. The test results showed that the BIPV panels performed better as façade cladding than as roofing material, since no quantifiable water leakages were detected at 90° inclination. At 15° and 30° inclinations, the total water leakages through the BIPV system were around 90% lower than those of the concrete tile roofing. This article’s findings demonstrate that the quantification of water intrusion through BIPV panels is feasible and can provide significant information for further developing and improving the design of BIPV systems as climate screens.

Assessment of Salinity in Fresh and Saline Aquifers in the Coastal Area of Jiangsu Province

Within the littoral alluvial expanse of the Yangtze River Delta, the phreatic zone encompassing the aquifer represents a prolific ecosystem, which has been subjected to an enduring epoch of marine sediment deposition, and is conspicuously susceptible to the escalating phenomenon of urbanization. The prodigious abstraction of the groundwater reserves has engendered a recent encroachment of seawater and leakage of connate saline water, culminating in the salinization of freshwater sources. For an incisive comprehension of the gradations of salinity (viz., fresh, brackish, and saline) and to execute evaluations of the groundwater’s quality, the spatial distributions of the total dissolved solids (TDS) were interpolated employing bifurcate power functions that establish a relationship between the Vertical Electrical Sounding (VES)-predicated transformation average resistivity and the assayed TDS from the systematically sampled boreholes corresponding to the aquifer stratum. The scrutiny of the groundwater’s physicochemical attributes is of paramount significance to efficaciously steer the exploitation and management of hydric resources within the area under investigation.

Investigating the possibility of leakage detection in water distribution networks using cosmic ray neutrons in the thermal region

Water distribution systems can experience high levels of leakage, originating from different sources, such as deterioration due to aging of pipes and fittings, material defects, and corrosion. In addition to causing financial losses and supply problems, leakages in treated water distribution also represent a risk for public health. Despite several techniques for leak detection are already available, there is still a lot of interest in new non-invasive approaches, especially for scenarios where acoustic techniques struggle, such as in noisy environmental conditions.In this work we investigated the possibility of using cosmic ray (CR) neutrons for the detection of underground leakages in water distribution networks, by exploiting the difference in the above ground thermal neutron flux between dry and wet soil conditions. The potential of the technique has been assessed by means of an extensive set of Monte Carlo simulations based on GEANT4, involving realistic scenarios based on the Italian aqueduct design guidelines. Simulation studies focused on sandy soils and results suggest that a significative signal, associated with a leakage, could be detected with a data-taking lasting from a few minutes to a half-hour, depending on the environmental soil moisture, the leaking water distribution in soil, and the soil chemical composition.Finally, a brief description of a new portable and low-cost detector for thermal neutrons, currently under commission, is also presented.

Analysis of the changes in structural modification, physicochemical properties, and water distribution of porcine myofibrillar proteins induced by sub-freezing short storage (−6 °C and −12 °C, 7 d)

The changes in structure, oxidative denaturation, and moisture distribution of myofibrillar proteins (MP) stored at −6 °C or −12 °C for 7 d were analyzed using fresh meat (FM), chilling (4 °C) and freezing (−18 °C) for 7 d as controls. The results showed that the structures of MP under −12 °C treatment and −18 °C treatment were similar (P > 0.05). Furthermore, compared to 4 °C treatment, −12 °C treatment could inhibit the MP's denaturation and alleviate the MP's oxidation. Regarding the static rheology and water distribution results, −12 °C treatment was more beneficial for maintaining the rheology properties and water holding capacity than 4 °C treatment. Conversely, the oxidative denaturation and water leakage of MP at 4 °C for 7 d were severe, due to the structural destruction. Therefore, −12 °C sub-freezing short storage (7 d) could be considered an ideal alternative to −18 °C short storage (7 d) with low power consumption.

A framework for GPR‐based water leakage detection by integrating hydromechanical modelling into electromagnetic modelling

AbstractTimely and accurate detection of water pipe leakage is critical to preventing the loss of freshwater and predicting potential hazards induced by the change in underground water conditions, thereby developing mitigation strategies to improve the resilience of pipeline infrastructure. Ground‐penetrating radar (GPR) has been widely applied to investigating ground conditions and detecting pipe leakage. However, due to uncertainties of complex underground environments and time‐lapse change, a proper interpretation of GPR data has been a challenging task. This paper aims to leverage hydromechanical (HM) modelling to predict electromagnetic (EM) responses of water leakage detection in diverse leakage cases. A high‐fidelity 3D digital model of an actual pipeline network, hosting pipes with various sizes and materials, was reconstructed to represent the complex geometry and various mediums. The interoperability between the digital model and the numerical models utilized in HM and EM simulations was improved to better capture the irregular pipelines. Based on Kriging interpolation and the volumetric complex refractive index model, a linking technique was employed to replicate material heterogeneity caused by water intrusion. Thus, a framework was developed to accommodate the interoperability among digital modelling, HM modelling and finite‐difference time‐domain forward modelling. Moreover, sensitivity studies were conducted to evaluate the influences of different time stages, leak positions and pipe types on GPR responses. In GPR B‐scans, the presence of hyperbolic motion and horizontal reflections serve as indicators to estimate the location and scale of water leakage. Specifically, a downward‐shifting hyperbola indicates that the pipeline is submerged by leaked water, whereas the emergence of horizontal reflection is linked to the wetting front of saturated areas. The developed framework can be expanded for complicated applications, such as unknown locations and unforeseen failure modes of pipelines. It will increase the efficiency and accuracy of traditional interpretations of GPR‐based water leakage detection and thus enable automated interpretations by data‐driven methods.

Properties and Application of Chemical Grouting Materials for Construction Joint Leakage

This paper aims to disclose the properties of the chemical grouting materials under different conditions. Firstly, the water-soluble polyurethane (WPU) slurry, oil-soluble polyurethane (OPU) slurry, epoxy resin (EP) slurry, a slurry mixed by WPU slurry, and OPU slurry marked as (WPU + OPU) slurry were selected to test the properties. The setting time, volume shrinkage, and adhesive strength were measured under room conditions and water conditions. Then, the tunnel construction joints were simulated, and the injectability and water blocking effect were analyzed to evaluate the suitability of the different grouting slurry. In addition, the results were applied in the water leakage management of the Taihu Lake tunnel project. The test results showed that each of the four materials had its performance advantages and disadvantages and provided vital guidance for the engineering application.

Machine learning-based system for vacuum leakage detection in EAST fusion device

In order to achieve real-time monitoring of partial pressures of residual gases and timely detection of vacuum leakage in fusion devices, a machine learning-based system was successfully developed on the LabVIEW software platform for its first-time application in the EAST fusion device. This system acquires partial pressure data from the quadrupole mass spectrometer (QMS) in both histogram and P&T scanning modes to identify the nature of vacuum leakage. The backpropagation (BP) neural network algorithm is employed for leakage detection. To train the BP neural network model, historical data from normal and leakage scenarios on the EAST device are utilized as inputs. Subsequently, the trained model is integrated into the system. The BP neural network model exhibited an identification accuracy of 95.27 % on the test set, effectively detecting water and gas leakage on EAST. Consequently, this system enables rapid detection of vacuum leakage in fusion devices, facilitating prompt mitigation of their impact on plasma experiments and ensuring the device's safety and stability.

Computational fluid dynamics analysis for smart control of water supply

Abstract This work investigated the partition walls or baffles’ effects on hydraulic parameters and water retention time in a reservoir. According to this aim, the water system was equipped with remote sensing (RS), networked sensors, advanced modems, and data loggers. The study showed how to control hydraulic parameters by the Internet of things and RS. The higher retention time led to the probability growth of rebar oxidation in concrete in the presence of chlorine and increased the possibility of water loss. This work also showed how to decrease the probability of water leakage in reservoirs. The computational fluid dynamics analysis results showed that the two baffles case led to the emergence of three eddy currents in the three zones created. The better fluid interpenetration caused the reduction in retention time. In the areas where the vortex was formed, the number of eddy currents decreased and the retention time increased. Regression analysis showed that the P value was 0.998 and 0.977 for the inlet flow and outlet flow for the reservoir, respectively (two baffles case perpendicular to the flow direction). The curve estimation showed that the power function had a suitable correlation on the scatter diagram and with the best curve fit.

Detection of Water Leakage in Drip Irrigation Systems Using Infrared Technique in Smart Agricultural Robots.

In the future, the world is likely to face water and therefore food shortages due to reasons such as global warming, population growth, the melting of glaciers, the destruction of agricultural lands over time or their use for different purposes, and environmental pollution. Although technological developments are important for people to live a more comfortable and safer life, it is also possible to reduce and even repair the damage to nature and protect nature itself thanks to new technologies. There is a requirement to detect abnormal water usage in agriculture to avert water scarcity, and an electronic system can help achieve this objective. In this research, an experimental study was carried out to detect water leaks in the field in order to prevent water losses that can occur in agriculture, where water consumption is the highest. Therefore, in this study, low-cost embedded electronic hardware was developed to detect over-watering by means of normal and thermal camera sensors and to collect the required data, which can be installed on a mobile agricultural robot. For image processing and the diagnosis of abnormal conditions, the collected data were transferred to a personal computer server. Then, software was developed for both the low-cost embedded system and the personal computer to provide a faster detection and decision-making process. The physical and software system developed in this study was designed to provide a water leak detection process that has a minimum response time. For this purpose, mathematical and image processing algorithms were applied to obtain efficient water detection for the conversion of the thermal sensor data into an image, the image size enhancement using interpolation, the combination of normal and thermal images, and the calculation of the image area where water leakage occurs. The field experiments for this developed system were performed manually to observe the good functioning of the system.

Smart Buildings: Water Leakage Detection Using TinyML.

The escalating global water usage and the increasing strain on major cities due to water shortages highlights the critical need for efficient water management practices. In water-stressed regions worldwide, significant water wastage is primarily attributed to leakages, inefficient use, and aging infrastructure. Undetected water leakages in buildings' pipelines contribute to the water waste problem. To address this issue, an effective water leak detection method is required. In this paper, we explore the application of edge computing in smart buildings to enhance water management. By integrating sensors and embedded Machine Learning models, known as TinyML, smart water management systems can collect real-time data, analyze it, and make accurate decisions for efficient water utilization. The transition to TinyML enables faster and more cost-effective local decision-making, reducing the dependence on centralized entities. In this work, we propose a solution that can be adapted for effective leakage detection in real-world scenarios with minimum human intervention using TinyML. We follow an approach that is similar to a typical machine learning lifecycle in production, spanning stages including data collection, training, hyperparameter tuning, offline evaluation and model optimization for on-device resource efficiency before deployment. In this work, we considered an existing water leakage acoustic dataset for polyvinyl chloride pipelines. To prepare the acoustic data for analysis, we performed preprocessing to transform it into scalograms. We devised a water leak detection method by applying transfer learning to five distinct Convolutional Neural Network (CNN) variants, which are namely EfficientNet, ResNet, AlexNet, MobileNet V1, and MobileNet V2. The CNN models were found to be able to detect leakages where a maximum testing accuracy, recall, precision, and F1 score of 97.45%, 98.57%, 96.70%, and 97.63%, respectively, were observed using the EfficientNet model. To enable seamless deployment on the Arduino Nano 33 BLE edge device, the EfficientNet model is compressed using quantization resulting in a low inference time of 1932 ms, a peak RAM usage of 255.3 kilobytes, and a flash usage requirement of merely 48.7 kilobytes.

Analysis of the Water Leakage Rate from the Cells of Nursery Containers

In container production, the key issue is proper irrigation and fertilization. Typically, the water required for plant growth is supplied through an irrigation ramp system, which can also perform fertilization. The frequency of irrigation and the amount of water supplied by the ramp depends on several factors, such as the species of plants grown, the container used, the substrate, and atmospheric factors accompanying production. For effective irrigation, the substrate in the container cell must retain the supplied water long enough for plant absorption. However, any excess water should drain from the container. To optimize irrigation, it is important to determine the parameter of the water outflow speed from the container cell, which is difficult to determine. This work proposes a new solution for a station that can measure the water outflow speed from various container cells (patent application P.443675 2022). In tests, the water outflow speed was assessed for two Styrofoam container types (V150—650/312/150 mm, 74 cells, and 0.145 dm3 cell volume; and V300—650/312/180 mm, 53 cells, and 0.275 dm3 cell volume). Both were filled with a peat and perlite substrate (95/5%) using the Urbinati Ypsilon line (V150 substrate moisture 75.7 ± 1.1%, and V300 75.9 ± 2.1%, efficiency of the line 400 containers∙h−1, vibration intensity of the vibrating table—maximum acceleration 12 G). The results indicated that the water outflow speed varied between container types. The V300 container had a higher outflow speed (0.0344 cm·s−1) compared to the V150 (0.0252 cm·s−1). This discrepancy may be due to differences in dry bulk density, with a correlation of r = −0.523. The V300 had a lower actual and dry bulk density (0.418 g·cm−3; 0.079 g·cm−3) compared to V150 (0.322 g·cm−3; 0.103 g·cm−3). This highlights the need for individual selection of parameters on the backfilling line for different container types when filling. Using identical parameters for diverse containers can lead to varying substrate volume densities, impacting water outflow rates.

Tool for estimating scope of building damage based on results of geometric operations between elements in building information models

ABSTRACT As a building ages, various types of problem caused by issues such as water leakage become more likely. Building information models (BIMs) are becoming more commonly used in the design and construction phases. Effort has been expended to also make them more effective in the maintenance phase. This study develops an add-on tool for predicting the scope of water leakage using the results of geometric operations between different elements in a BIM. A case study of water leakage associated with deteriorating rooftop waterproofing is presented. The development of the tool is based on interviews and a literature survey. The process of water spreading from a starting spot is described using multiple stages. A drawing on a plan view and calculation results based on the number of elements are presented to the user. The developed add-on tool is evaluated using a case study on some rooms in a BIM. The proposed tool can represent the knowledge and experience related to facility management using BIM technology. The novelty of the proposed tool is that it focuses on the detailed geometry and exact placement of elements in a BIM used for maintenance purposes and uses these elements in edited form.

An efficient system for water leak detection and localization based on IoT and lightweight deep learning

Nowadays, Water Distribution Networks (WDNs) efficiency is limited due to leakage issues, which result in large water losses that exceed about one third of the input volume. Considering the problems of growing population and water scarcity especially in Africa and Asia continents, an urgent humanitarian need arisen to efficiently detect and localize pipeline water leaks. To address this need, this paper proposes an end-to-end system for leak detection and localization in water pipelines based on IoT and deep learning. The IoT solution is deployed allowing real time monitoring of pipelines by using non-invasive IoT devices equipped with acoustic sensors which are installed on the pipeline surface. A lightweight one-Dimensional Convolutional Neural Network (1D-CNN) classification model is embedded on these devices to detect leaks. This model uses raw audio signals generated by sensors as input information. Information about the detected leaks is then remotely transmitted using long range and low energy LoRaWAN protocol to the LoRa gateway. The gateway relays messages to a data processing Server. A 1D-CNN regression model has been then created and deployed in this server to directly estimate the 2D position of the leak. As an illustration, An IoT device prototype is designed and used as a case study to test the performance of the proposed system. We demonstrated that our proposal achieves an accuracy of 97 % for detecting leaks and can fix the 2D position of leak with an error of 0.0006 on the X coordinate and 0.0004 on the Y coordinate. Experiments confirm the effectiveness of the proposed solution.

Test study on performance of U80 standardized glass curtain wall system

In order to study the air infiltration performance, water penetration performance, structural performance under wind pressure and seismic inter-story drift performance of U80 standardized glass curtain wall system, one full size test specimen was designed according to the actual engineering situation. The test specimen was composed of six-unit curtain walls with exposed frames and six-unit curtain walls with concealed frames. According to the specification of United Stated, the various performance of the test specimen was investigated. The results show that the rate of air leakage of the specimen is within allowable values under design pressure. No water leakage is observed when the water penetration tests with static and dynamic pressure tests. During the structural performance tests at 100% design wind pressure, the deflections of framing members as well as glass panels are all within the allowable deflection limits. No breakage is observed under the 150% design wind pressure. Permanent deformations of framing members remain less than 0.1% of clear span. After 3 cycles of elastic and inelastic inter-story drift performance tests, no damage is observed. The U80 standardized glass curtain wall system has great air infiltration performance, water penetration performance, structural performance and seismic inter-story drift performance. And it can be used in the practical engineering.