The early detection of fire is of utmost importance since it is related to devastating threats regarding human lives and economic losses. Unfortunately, fire alarm sensory systems are known to be prone to failures and frequent false alarms, putting people and buildings at risk. In this sense, it is essential to guarantee smoke detectors’ correct functioning. Traditionally, these systems have been subject to periodic maintenance plans, which do not consider the state of the fire alarm sensors and are, therefore, sometimes carried out not when necessary but according to a predefined conservative schedule. Intending to contribute to designing a predictive maintenance plan, we propose an online data-driven anomaly detection of smoke sensors that model the behaviour of these systems over time and detect abnormal patterns that can indicate a potential failure. Our approach was applied to data collected from independent fire alarm sensory systems installed with four customers, from which about three years of data are available. For one of the customers, the obtained results were promising, with a precision score of 1 with no false positives for 3 out of 4 possible faults. Analysis of the remaining customers’ results highlighted possible reasons and potential improvements to address this problem better. These findings can provide valuable insights for future research in this area.

An online data-driven predictive maintenance approach for railway switches using data logs obtained from the interlocking system of the railway infrastructure is proposed in this paper. The proposed approach is detailed described and consists of a two-phase process - anomaly detection and remaining useful life prediction. The approach is applied to and validated in a real case study, the Metro do Porto, from which seven months of data is available. The approach has been revealed to be satisfactory in detecting anomalies. The results open the possibilities for further studies and validation with a more extensive dataset on the remaining useful life prediction.

One of the major challenges of Structural Health Monitoring when transiting from academia to real practical applications is the distinction between the variations due to normal environmental and operational effects and the variations due to structural damage. In this context, two alternative methodologies for online data normalisation are described and compared - multiple linear regression followed by principal component analysis and multivariate cointegration. The developed algorithms are applied to the Corgo Bridge, a reinforced and prestressed concrete bridge of which 3.5 years of continuous data is available, and their performance is evaluated and compared. In order to evaluate the sensitivity to damage of the proposed approaches, several damage scenarios are simulated by corrupting the measured time with the structural response to the damage events obtained from a finite element model of the bridge. Both methodologies are shown to provide robust results and reasonable sensitivity to damage.

One of the main challenges that Structural Health Monitoring (SHM) faces when transitioning from academia to real-world applications is the discernment between structural changes due to damage and normal environmental, operational and long-term effects. In this context, a strategy for early damage detection based on multivariate cointegration analysis and statistical process control is proposed. The effects of environmental and operational variations are suppressed using cointegration analysis, being the cointegrating vector estimated following the multivariate Johansen procedure. The cointegrated residuals are then used for novelty detection by means of the Hotelling T2 control chart. The proposed strategy is systematised and is applied to a large prestressed concrete cable-stayed bridge of which 3.5 years of data are available, being the stay-cable forces used as damage sensitive-features. Several damage scenarios are studied involving increasing section loss of the stay cables. The damage intensities that can be detected using the proposed methodology and the available sensory system are quantified.

An online data-based methodology for early damage detection and localisation under the effects of environmental and operational variations (EOVs) is proposed. The methodology is described in detail and implemented in a large prestressed concrete cable-stayed bridge of which 3.5 years of data are available. The effects of EOVs are suppressed by the combined application of two well-established multivariate data analysis methods - multiple linear regression and principal component analysis. Criteria for the systematic choice of the predictor variables and the number of principal components to retain are proposed. Because the bridge is new and sound, the experimental time series are corrupted with numerically simulated damage scenarios in order to evaluate the damage detection ability. It is demonstrated that the sensitivity to damage is increased when daily, 2-day, or 3-day averaged data are used instead of hourly data. The effectiveness of the proposed methodology is also demonstrated with the detection of a real, small, and temporary sensor anomaly. The implemented methodology has revealed to be robust and efficient, presenting a contribution to the transition of structural health monitoring from academia to industry.

Daily and seasonal temperature variations have a significant influence on the structural response of bridges, inducing strains, displacements or rotations of the same order of magnitude, or even larger, than those due to dead or live loads. Besides understanding the structural behaviour under the operational loads, the characterization of the structural response induced by the daily and seasonal temperature variations is mandatory for the critical assessment of the bridge structural condition and when proactive conservation is envisaged. In this study, a methodology is proposed for the simulation of the structural response of large concrete bridges under the effects of realistic temperature variations, aiming at the optimum compromise between accuracy and simplicity of the involved procedures. The transient temperature field in a set of representative cross-sections is obtained from the available meteorological data via two-dimensional thermal analyses. The temperature field is decomposed into uniform, linear and non-linear components, the former two being introduced in a mechanical model of the bridge to obtain the transient structural response. The methodology is applied to a concrete cable-stayed bridge equipped with a permanent structural monitoring system. The measured and calculated hourly temperatures, deflections, bearing displacements, rotations and stay-cable forces are compared during a period of 17 months and good agreement is generally found. The consideration of the radiative cooling effects is demonstrated to be essential in other to obtain a good estimation of the thermal field of the bridge. The behaviour of the bridge is discussed and the relative contribution of each temperature component to a given structural response is disclosed. A discussion on the optimal deployment location of a minimum set of embedded temperature sensors in order achieve the best estimators of the temperature components (uniform and linear) is also presented.