scholarly journals Identification of Bridge Key Performance Indicators Using Survival Analysis for Future Network-Wide Structural Health Monitoring

Sensors ◽  
2020 ◽  
Vol 20 (23) ◽  
pp. 6894
Author(s):  
Nicola-Ann Stevens ◽  
Myra Lydon ◽  
Adele H. Marshall ◽  
Su Taylor
Keyword(s):  
Survival Analysis ◽  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Performance Indicators ◽  
Key Performance Indicators ◽  
Predictive Maintenance ◽  
Sensor Data ◽  
Transport Networks ◽  
Data Set ◽  
Structural Health

Machine learning and statistical approaches have transformed the management of infrastructure systems such as water, energy and modern transport networks. Artificial Intelligence-based solutions allow asset owners to predict future performance and optimize maintenance routines through the use of historic performance and real-time sensor data. The industrial adoption of such methods has been limited in the management of bridges within aging transport networks. Predictive maintenance at bridge network level is particularly complex due to the considerable level of heterogeneity encompassed across various bridge types and functions. This paper reviews some of the main approaches in bridge predictive maintenance modeling and outlines the challenges in their adaptation to the future network-wide management of bridges. Survival analysis techniques have been successfully applied to predict outcomes from a homogenous data set, such as bridge deck condition. This paper considers the complexities of European road networks in terms of bridge type, function and age to present a novel application of survival analysis based on sparse data obtained from visual inspections. This research is focused on analyzing existing inspection information to establish data foundations, which will pave the way for big data utilization, and inform on key performance indicators for future network-wide structural health monitoring.

The Modal Identification of Structure Using Distributed ERA and EFDD Methods

2010 ◽  
Vol 163-167 ◽  
pp. 2532-2536
Author(s):  
Ying Lei ◽  
Zhi Lu Lai
Keyword(s):  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Large Volume ◽  
Modal Identification ◽  
Modal Parameters ◽  
Identification Algorithm ◽  
Civil Infrastructure ◽  
Complicated Structure ◽  
Data Set ◽  
Structural Health

Structural health monitoring (SHM) is an emerging field in civil engineering, offering the potential for continuous and periodic assessment of the safety and integrity of civil infrastructure. In this paper, a distributed computing strategy for modal identification of structure is proposed, which is suitable for the problem of solving large volume of data set in structural health monitoring. Numerical example of distribute computing the modal properties of truss illustrates the distributed out-put only modal identification algorithm based on NExT / ERA techniques and EFDD. This strategy can also be applied to other complicated structure to determine modal parameters.

Elevator-Assisted Sensor Data Collection for Structural Health Monitoring

2012 ◽  
Vol 11 (10) ◽  
pp. 1555-1568 ◽  
Author(s):  
Tao Zhang ◽  
Dan Wang ◽  
Jiannong Cao ◽  
Yi Qing Ni ◽  
Li-Jun Chen ◽  
...  
Keyword(s):  
Structural Health Monitoring ◽  
Data Collection ◽  
Health Monitoring ◽  
Sensor Data ◽  
Structural Health

scholarly journals Detecting damage events in concrete using diffuse ultrasound structural health monitoring during strong environmental variations

2017 ◽  
Vol 17 (2) ◽  
pp. 410-419 ◽  
Author(s):  
Patrik Fröjd ◽  
Peter Ulriksen
Keyword(s):  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Environmental Conditions ◽  
Continuous Wave ◽  
Data Set ◽  
Phase Measurements ◽  
Structural Health ◽  
Wave Measurements ◽  
Environmental Variations ◽  
Window Approach

Diffuse ultrasonic wave measurements used in structural health monitoring applications can detect damage in concrete. However, the accuracy is very susceptible to environmental variations. In this study, a large concrete floor slab was monitored using diffuse wave fields that were generated by continuous-wave transmissions between ultrasonic transducers. The slab was monitored for several weeks while being subjected to changes in environmental conditions. Subsequently, it was damaged using impact hits, resulting in centimeter-scale cracking. The variations caused by the environment masked the effects of the damage in the measurements. To address this issue, the Mahalanobis distance was used to distinguish between the influence of the damage and the influence of the environmental variations. The Mahalanobis model uses amplitude and phase measurements of continuous waves at a set of different frequencies as inputs. A moving window approach was applied to the baseline data set to account for slow trends. This study shows that this technique greatly suppresses most of the variations caused by environmental conditions. All damage events in our data set have been detected.

Optimal Sensor Configuration for Fatigue Life Prediction in Structural Applications

2019 ◽  
Author(s):  
Mohamed Khalil ◽  
Ioannis Kouroudis ◽  
Roland Wüchner ◽  
Kai-Uwe Bletzinger
Keyword(s):  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Estimation Error ◽  
Operating Conditions ◽  
Added Value ◽  
Sensor Data ◽  
Damage Prediction ◽  
Structural Health ◽  
Structural Applications ◽  
Prediction Approach

Abstract Structural health monitoring is spreading widely across engineering domains. Its added value is not restricted to observing structural behavior, but crosses over to enabling the assessment of structural integrity under varying operating conditions. Damage prognosis is one vital demand from structural health monitoring solutions. Many methods have been developed to update damage predictions based on sensor data, nonetheless the selection and positioning of sensors to alleviate the prediction errors remains a question under investigation. In this work, an optimal sensor placement method is proposed for fatigue damage prediction in structures. An optimization problem is formulated to minimize the a-posteriori damage estimation error based on a Kalman filter. The derivation of the objective function is presented, along with a discussion of algorithm-related issues. Finally, the mentioned damage prediction approach is applied to two structures to verify the adequacy of the sensor configurations proposed by the method.

Ontology-based sharing of structural health monitoring data

2019 ◽  
Author(s):  
Seppo Törmä ◽  
Markku Kiviniemi ◽  
Mikko Lampi ◽  
Pekka Toivola ◽  
Päivi Puntila ◽  
...  
Keyword(s):  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Service Providers ◽  
Facility Management ◽  
Monitoring Data ◽  
Sensor Data ◽  
Health Monitoring System ◽  
Structural Health ◽  
Monitoring Model ◽  
Monitoring Service

<p>A structural health monitoring system installed in a bridge produces a vast amount of sensor data that is analyzed and periodically reported to a bridge owner at an aggregate level. The data itself typically remains in the monitoring service of a service provider; it may be accessible to clients and third parties through a dedicated user interface and API. This paper presents an ontology to defining the monitoring model based on the Semantic Sensor Network Ontology by W3C. The goal is to enable an asset owner to utilize preferred tools to view and access monitoring data from different service providers, and in longer term, increase the utilization of monitoring data in facility management. The ultimate aim is to use BrIM as a digital twin of a bridge and to link external datasets to improve information management and maintenance over its lifecycle.</p>

scholarly journals Structural health monitoring for mechanical structures using multi-sensor data

2018 ◽  
Vol 14 (9) ◽  
pp. 155014771880201 ◽  
Author(s):  
Jia-Wei Xiang ◽  
Zhi-Bo Yang ◽  
Jose L Aguilar
Keyword(s):  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Sensor Data ◽  
Structural Health

scholarly journals Structural Health Monitoring for Advanced Composite Structures: A Review

2020 ◽  
Vol 4 (1) ◽  
pp. 13 ◽  
Author(s):  
Alfredo Güemes ◽  
Antonio Fernandez-Lopez ◽  
Angel Renato Pozo ◽  
Julián Sierra-Pérez
Keyword(s):  
Structural Health Monitoring ◽  
Fiber Optics ◽  
Health Monitoring ◽  
Composite Structures ◽  
Guided Waves ◽  
Probability Of Detection ◽  
Sensor Data ◽  
Structural Health ◽  
Early Fault Detection ◽  
Pod Analysis

Condition-based maintenance refers to the installation of permanent sensors on a structure/system. By means of early fault detection, severe damage can be avoided, allowing efficient timing of maintenance works and avoiding unnecessary inspections at the same time. These are the goals for structural health monitoring (SHM). The changes caused by incipient damage on raw data collected by sensors are quite small, and are usually contaminated by noise and varying environmental factors, so the algorithms used to extract information from sensor data need to focus on sensitive damage features. The developments of SHM techniques over the last 20 years have been more related to algorithm improvements than to sensor progress, which essentially have been maintained without major conceptual changes (with regards to accelerometers, piezoelectric wafers, and fiber optic sensors). The main different SHM systems (vibration methods, strain-based fiber optics methods, guided waves, acoustic emission, and nanoparticle-doped resins) are reviewed, and the main issues to be solved are identified. Reliability is the key question, and can only be demonstrated through a probability of detection (POD) analysis. Attention has only been paid to this issue over the last ten years, but now it is a growing trend. Simulation of the SHM system is needed in order to reduce the number of experiments.

scholarly journals Integration with 3D Visualization and IoT-Based Sensors for Real-Time Structural Health Monitoring

Sensors ◽  
2021 ◽  
Vol 21 (21) ◽  
pp. 6988
Author(s):  
Hung-Fu Chang ◽  
Mohammad Shokrolah Shokrolah Shirazi
Keyword(s):  
Structural Health Monitoring ◽  
Real Time ◽  
Health Monitoring ◽  
3D Model ◽  
3D Visualization ◽  
Sensor Data ◽  
Unique Identifier ◽  
Element Analysis ◽  
Structural Dynamic ◽  
Structural Health

Real-time monitoring on displacement and acceleration of a structure provides vital information for people in different applications such as active control and damage warning systems. Recent developments of the Internet of Things (IoT) and client-side web technologies enable a wireless microcontroller board with sensors to process structural-related data in real-time and to interact with servers so that end-users can view the final processed results of the servers through a browser in a computer or a mobile phone. Unlike traditional structural health monitoring (SHM) systems that deliver warnings based on peak acceleration of earthquake, we built a real-time SHM system that converts raw sensor results into movements and rotations on the monitored structure’s three-dimensional (3D) model. This unique approach displays the overall structural dynamic movements directly from measured displacement data, rather than using force analysis, such as finite element analysis, to predict the displacement statically. As an application to our research outcomes, patterns of movements related to its structure type can be collected for further cross-validating the results derived from the traditional stress-strain analysis. In this work, we overcome several challenges that exist in displaying the 3D effects in real-time. From our proposed algorithm that converts the global displacements into element’s local movements, our system can calculate each element’s (e.g., column’s, beam’s, and floor’s) rotation and displacement at its local coordinate while the sensor’s monitoring result only provides displacements at the global coordinate. While we consider minimizing the overall sensor usage costs and displaying the essential 3D movements at the same time, a sensor deployment method is suggested. To achieve the need of processing the enormous amount of sensor data in real-time, we designed a novel structure for saving sensor data, where relationships among multiple sensor devices and sensor’s spatial and unique identifier can be presented. Moreover, we built a sensor device that can send the monitoring data via wireless network to the local server or cloud so that the SHM web can integrate what we develop altogether to show the real-time 3D movements. In this paper, a 3D model is created according to a two-story structure to demonstrate the SHM system functionality and validate our proposed algorithm.

Sign in / Sign up

Export Citation Format

Share Document