Fabrication technology and structural engineering states-of-art have led to a growing use of slender structures, making them more susceptible to static and dynamic actions that may lead to some sort of damage. In this context, regular inspections and evaluations are necessary to detect and predict structural damage and establish maintenance actions able to guarantee structural safety and durability with minimal cost. However, these procedures are traditionally quite time-consuming and costly, and techniques allowing a more effective damage detection are necessary. This paper assesses the potential of Artificial Neural Network (ANN) models in the prediction of damage localization in structural members, as function of their dynamic properties – the three first natural frequencies are used. Based on 64 numerical examples from damaged (mostly) and undamaged steel channel beams, an ANN-based analytical model is proposed as a highly accurate and efficient damage localization estimator. The proposed model yielded maximum errors of 0.2 and 0.7 % concerning 64 numerical and 3 experimental data points, respectively. Due to the high-quality of results, authors’ next step is the application of similar approaches to entire structures, based on much larger datasets.

A essencialidade do saneamento à uma qualidade de vida para o ser humano e para manutenção de um meio sustentável e salobre é indubitável. O esgotamento sanitário, entre os serviços de saneamento, ainda apresenta déficits significativos em todo Brasil. A falta de cobertura a determinadas áreas, a prestação de maneira negligente e o tratamento inadequado das águas servidas é um fator determinante no atraso econômico e social de várias populações. Com base nessa problemática, o presente trabalho investiga e descreve alguns dos aspectos da prestação do serviço de esgotamento sanitário em municípios de pequeno porte na Paraíba, descrevendo o cenário atual do mesmo. Para tal, foi feito um levantamento, junto a órgãos públicos, prefeituras e população, que permitiu o tratamento e organização de informações que serviram para construção de um banco de dados, que permitiu a análise e caracterização de aspectos desse serviço no estado , principalmente, no que se refere, ao acesso a coleta e tratamento dos esgotos gerados na zona urbana. Ficou evidente que os municípios com pequena população são os que apresentam piores índices e taxas de atendimento e tratamento. A situação de atendimento é precária em todas as localidades avaliadas, não atingindo taxas de coleta acima de 55%. Em todos os municípios foram encontrados lançamento de esgotos a céu aberto, sendo que em alguns deles, essa era a única destinação final das águas servidas. Foi possível, desta forma, identificar os quadros mais frágeis para o atendimento desse serviço, para que sejam criadas políticas de planejamento direcionadas para essas fragilidades e também para que esses serviços atinjam o acesso de maneira satisfatória e igualitária para todas as esferas da sociedade direcionando as autoridades competentes, de modo eficiente, para esse objetivo.

O controle e vigilância da qualidade da água são essenciais para prevenir doenças de veiculação hídrica, como as diarreias agudas, causadas pelo consumo de água não tratada. Os parâmetros Escherichia coli e Cloro residual livre (CRL) são indicadores primários da qualidade da água, relacionados à contaminação fecal e à eficácia do tratamento, respectivamente. Neste sentido, este estudo investiga a relação entre a incidência de doenças diarreicas agudas e esses indicadores, buscando identificar variações regionais e temporais nos dados do Sistema de Informação de Vigilância da Qualidade da Água para Consumo Humano (Sisagua) de 2014 a 2023. Para isso, foram utilizadas análises estatísticas para verificar a influência das características dos sistemas (SAA) e soluções alternativas coletivas (SAC) de abastecimento de água na porcentagem de inconformidade nas amostras de E. coli e CRL. Com o intuito de avaliar os dados espacial e temporalmente, aplicou-se o índice de Moran e o teste de Mann-Kendall. Os resultados obtidos revelaram a existência de desigualdade entre os dados de qualidade da água em sistemas localizados nas zonas urbana e rural, com a zona rural e as SAC tendo maior incidência de amostras inconformes. Os estados do Pará, Maranhão e Piauí destacam-se por problemas quando ao atendimento aos planos de amostragem, inconformidade das amostras e ocorrência de doenças diarreicas agudas, necessitando de políticas públicas específicas para mitigação dos efeitos. As regiões Sul e Sudeste do Brasil demonstraram melhor desempenho geral no atendimento à portaria de potabilidade, enquanto o Ceará se destacou pelo cumprimento do plano de amostragem. O trabalho auxilia na elaboração de estratégias voltadas para aprimorar a qualidade da água e fortalecer o cumprimento aos planos de amostragem, através da identificação das áreas com maiores deficiências, permitindo a priorização de ações de vigilância da qualidade da água pelo poder público ou da implantação de novas tecnologias, como os sistemas inteligentes de monitoramento da qualidade da água.

The natural and accidental deterioration of civil structures, combined with the increasing complexity of engineering projects, demands continuous monitoring strategies to ensure structural safety and durability. In this context, Structural Health Monitoring (SHM) techniques based on variations in modal properties have been widely investigated due to their capability for global assessment. However, practical limitations—such as information loss during modal identification and the low sensitivity of certain modal parameters to damage—have motivated the development of alternative approaches. Among these approaches, methodologies based on statistical features extracted directly from acceleration time series have gained prominence, particularly when combined with Machine Learning (ML) classifiers. Although several studies have successfully employed statistical indicators for damage detection, the relative relevance of these indicators and the potential benefits of dimensionality reduction can still be explored through a systematic evaluation, particularly under Sim-to-Real conditions. This study investigates the performance of ten statistical indicators as input features for ML-based damage detection, applied to an experimentally tested frame structure, using numerically obtained data for training. A structured variable analysis was conducted to assess the individual and combined impact of the indicators, supported by visualization techniques and classifier performance metrics. The results showed some possible redundancies between certain indicators and demonstrated that a reduced set of attributes can achieve comparable or superior classification performance, while simultaneously improving training stability and computational efficiency. These findings highlight the importance of systematic feature selection and the effectiveness of reduced-dimensional statistical representations for SHM applications in Sim-to-Real scenarios.

Water Safety Plans (WSPs) are a preventive and collaborative approach to ensuring safe drinking water, particularly in rural communities where simplified supply systems present unique operational and governance challenges. The traditional risk assessment methodology recommended by the World Health Organization (WHO) relies solely on the product of occurrence and severity scores, which can result in tied rankings among hazardous events and fail to capture the full complexity of rural water supply contexts. This study proposes a risk assessment model integrating Fuzzy logic with Failure Mode and Effects Analysis (FMEA) to improve the prioritization of hazardous events in WSPs developed for rural communities. The model was applied to two rural communities in Aracati, Ceará, Brazil — one served by a simplified water supply system and another by collective alternative supply solutions — and compared with the WHO-recommended methodology. Two Mamdani fuzzy inference systems were constructed, combining occurrence and severity to generate a Risk Criticality Index, subsequently combined with detection to produce a Fuzzified Risk Priority Number. The model increased the number of prioritization levels from 11 to 17 in the water supply system and by four levels in the alternative supply solutions, reducing tied rankings and enabling more granular risk differentiation. Severity was found to exert greater influence on risk levels than occurrence, and hazardous events related to user water handling practices received higher priority in the alternative supply scenario due to low detectability. The proposed model demonstrated superior performance compared to the traditional WHO methodology, offering a more context-sensitive and decision-support tool for rural water safety management.

Efficient structural health monitoring requires not only robust computational strategies but also reliable data acquisition systems capable of capturing representative dynamic responses of real structures. In this study, a continuous dynamic monitoring system composed of accelerometers strategically distributed along the bridge deck provides the foundational data for all subsequent computational analyses. The integrated application of t-Distributed Stochastic Neighbor Embedding (t-SNE) and Learning Vector Quantization (LVQ) is evaluated for the identification of structural damage in the Infante D. Henrique Bridge, located in Porto, Portugal. Data obtained from five years of continuous monitoring were used, with a portion of the identified natural frequencies employed for training and validation of the LVQ algorithm. The robustness of the approach was assessed through artificial modification of data from the second year of monitoring, simulating different damage scenarios. The results demonstrate that the t-SNE–LVQ combination improves discrimination between normal and damaged structural states, achieving identification rates above 70%. The main contribution of this work lies in demonstrating the feasibility and effectiveness of an integrated hardware-to-software machine learning framework applied to real monitoring data, highlighting its potential for structural health monitoring and decision-support systems.