Search

Bridge wear and deterioration occur over time under typical operations. Inspections can be resource intensive, infrequent, and sometimes require bridge closure. Instrumented passing vehicles may be used to record vibration responses and extract damage‐sensitive bridge frequency response characteristics. This paper presents a methodology for extracting bridge frequencies from crowdsourced dynamic response data recorded within passing vehicles. Detected bridge frequency changes and a novel point cloud methodology are used to identify critical damage scenarios and estimate remaining life. The use of a novel crowdsourced Welch methodology allows for spectra averaging that reduces the influence of noise and transient events. Numerical and experimental studies illustrate that bridge frequencies can be accurately estimated and that changes in bridge frequency caused by different damage scenarios can be characterized. Numerical examples for the damage scenario analysis, including estimation of remaining life, are provided for two bridge types and three specific damage scenarios. [ABSTRACT FROM AUTHOR]

Impairments that occur in structural systems may degrade performance or prevent a structure from functioning safely. Detecting impairments prior to a structural failure reduces the effect of impairments on the safety of those using a structure. This article describes the computational framework of a Structural Impairment Detection System (SIDS) that processes the digital data streams of electronic sensors attached to critical components of a structure. The resulting system comprises a competitive array of neural networks that can accurately describe the types and severity of likely impairments present in the structure. The competitive array of neural networks is trained to detect patterns in data streams specific to likely target impairments. Data streams generated from ABAQUS models and from electronic sensors are used in training and evaluating the system. As part of the initial development of this SIDS, the counterweight truss of a 100-year old railroad drawbridge was instrumented and evaluated. The resulting data streams were diagnosed autonomously by the SIDS as being similar to one of two operational conditions: unimpaired or a single impairment present in a member embedded within the counterweight. Further investigation of the counterweight truss is underway to verify the accuracy of the assessments. [ABSTRACT FROM AUTHOR]

Computer‐vision and deep‐learning techniques are being increasingly applied to inspect, monitor, and assess infrastructure conditions including detection of cracks. Traditional vision‐based methods to detect cracks lack accuracy and generalization to work on complicated infrastructural conditions. This paper presents a novel context‐aware deep convolutional semantic segmentation network to effectively detect cracks in structural infrastructure under various conditions. The proposed method applies a pixel‐wise deep semantic segmentation network to segment the cracks on images with arbitrary sizes without retraining the prediction network. Meanwhile, a context‐aware fusion algorithm that leverages local cross‐state and cross‐space constraints is proposed to fuse the predictions of image patches. This method is evaluated on three datasets: CrackForest Dataset (CFD) and Tomorrows Road Infrastructure Monitoring, Management Dataset (TRIMMD) and a Customized Field Test Dataset (CFTD) and achieves Boundary F1 (BF) score of 0.8234, 0.8252, and 0.7937 under 2‐pixel error tolerance margin in CFD, TRIMMD, and CFTD, respectively. The proposed method advances the state‐of‐the‐art performance of BF score by approximately 2.71% in CFD, 1.47% in TRIMMD, and 4.14% in CFTD. Moreover, the averaged processing time of the proposed system is 0.7 s on a typical desktop with Intel® Quad‐Core™ i7‐7700 CPU@3.6 GHz Processor, 16GB RAM and NVIDIA GeForce GTX 1060 6GB GPU for an image of size 256 × 256 pixels. [ABSTRACT FROM AUTHOR]