Health Management of Complex Systems Integrating Multisource Sensing, Nondestructive Evaluation, and Machine Learning

168296-Thumbnail Image.png
Description
Structural/system health monitoring (SHM) and prognostic health management (PHM) are vital techniques to ensure engineering system reliability and safety during the service. As multi-functionality and enhanced performance are in demand, modern engineering systems including aerospace, mechanical, and civil applications have…

Structural/system health monitoring (SHM) and prognostic health management (PHM) are vital techniques to ensure engineering system reliability and safety during the service. As multi-functionality and enhanced performance are in demand, modern engineering systems including aerospace, mechanical, and civil applications have become more complex. The constituent and architectural complexity, and multisource sensing sources in modern engineering systems may limit the monitoring capabilities of conventional approaches and require more advanced SHM/PHM techniques. Therefore, a hybrid methodology that incorporates information fusion, nondestructive evaluation (NDE), machine learning (ML), and statistical analysis is needed for more effective damage diagnosis/prognosis and system safety management.This dissertation presents an automated aviation health management technique to enable proactive safety management for both aircraft and national airspace system (NAS). A real-time, data-driven aircraft safety monitoring technique using ML models and statistical models is developed to enable an early-stage upset detection capability, which can improve pilot’s situational awareness and provide a sufficient safety margin. The detection accuracy and computational efficiency of the developed monitoring techniques is validated using commercial unlabeled flight data recorder (FDR) and reported accident FDR dataset. A stochastic post-upset prediction framework is developed using a high-fidelity flight dynamics model to predict the post-impacts in both aircraft and air traffic system. Stall upset scenarios that are most likely occurred during loss of control in-flight (LOC-I) operation are investigated, and stochastic flight envelopes and risk region are predicted to quantify their severities. In addition, a robust, automatic damage diagnosis technique using ultrasonic Lamb waves and ML models is developed to effectively detect and classify fatigue damage modes in composite structures. The dispersion and propagation characteristics of the Lamb waves in a composite plate are investigated. A deep autoencoder-based diagnosis technique is proposed to detect fatigue damage using anomaly detection approach and automatically extract damage sensitive features from the waves. The patterns in the features are then further analyzed using outlier detection approach to classify the fatigue damage modes. The developed diagnosis technique is validated through an in-situ fatigue tests with periodic active sensing. The developed techniques in this research are expected to be integrated with the existing safety strategies to enhance decision making process for improving engineering system safety without affecting the system’s functions.
Date Created
2021
Agent

Context Integration for Reliable Anomaly Detection from Imagery Data for Supporting Civil Infrastructure Operation and Maintenance

158646-Thumbnail Image.png
Description
Imagery data has become important for civil infrastructure operation and

maintenance because imagery data can capture detailed visual information with high

frequencies. Computer vision can be useful for acquiring spatiotemporal details to

support the timely maintenance of critical civil infrastructures that serve society.…

Imagery data has become important for civil infrastructure operation and

maintenance because imagery data can capture detailed visual information with high

frequencies. Computer vision can be useful for acquiring spatiotemporal details to

support the timely maintenance of critical civil infrastructures that serve society. Some

examples include: irrigation canals need to maintain the leaking sections to avoid water

loss; project engineers need to identify the deviating parts of the workflow to have the

project finished on time and within budget; detecting abnormal behaviors of air traffic

controllers is necessary to reduce operational errors and avoid air traffic accidents.

Identifying the outliers of the civil infrastructure can help engineers focus on targeted

areas. However, large amounts of imagery data bring the difficulty of information

overloading. Anomaly detection combined with contextual knowledge could help address

such information overloading to support the operation and maintenance of civil

infrastructures.

Some challenges make such identification of anomalies difficult. The first challenge is

that diverse large civil infrastructures span among various geospatial environments so

that previous algorithms cannot handle anomaly detection of civil infrastructures in

different environments. The second challenge is that the crowded and rapidly changing

workspaces can cause difficulties for the reliable detection of deviating parts of the

workflow. The third challenge is that limited studies examined how to detect abnormal

behaviors for diverse people in a real-time and non-intrusive manner. Using video andii

relevant data sources (e.g., biometric and communication data) could be promising but

still need a baseline of normal behaviors for outlier detection.

This dissertation presents an anomaly detection framework that uses contextual

knowledge, contextual information, and contextual data for filtering visual information

extracted by computer vision techniques (ADCV) to address the challenges described

above. The framework categorizes the anomaly detection of civil infrastructures into two

categories: with and without a baseline of normal events. The author uses three case

studies to illustrate how the developed approaches can address ADCV challenges in

different categories of anomaly detection. Detailed data collection and experiments

validate the developed ADCV approaches.
Date Created
2020
Agent

Predictive Control of Interpersonal Communication Processes in Civil Infrastructure Systems Operations

158609-Thumbnail Image.png
Description
Interpersonal communications during civil infrastructure systems operation and maintenance (CIS O&M) are processes for CIS O&M participants to exchange critical information. Poor communications that provide misleading information can jeopardize CIS O&M safety and efficiency. Previous studies suggest that communication contexts…

Interpersonal communications during civil infrastructure systems operation and maintenance (CIS O&M) are processes for CIS O&M participants to exchange critical information. Poor communications that provide misleading information can jeopardize CIS O&M safety and efficiency. Previous studies suggest that communication contexts and features could be indicators of communication errors and relevant CIS O&M risks. However, challenges remain for reliable prediction of communication errors to ensure CIS O&M safety and efficiency. For example, existing studies lack a systematic summarization of risky contexts and features of communication processes for predicting communication errors. Limited studies examined quantitative methods for incorporating expert opinions as constraints for reliable communication error prediction. How to examine mitigation strategies (e.g., adjustments of communication protocols) for reducing communication-related CIS O&M risks is also challenging. The main reason is the lack of causal analysis about how various factors influence the occurrences and impacts of communication errors so that engineers lack the basis for intervention.

This dissertation presents a method that integrates Bayesian Network (BN) modeling and simulation for communication-related risk prediction and mitigation. The proposed method aims at tackling the three challenges mentioned above for ensuring CIS O&M safety and efficiency. The proposed method contains three parts: 1) Communication Data Collection and Error Detection – designing lab experiments for collecting communication data in CIS O&M workflows and using the collected data for identifying risky communication contexts and features; 2) Communication Error Classification and Prediction – encoding expert knowledge as constraints through BN model updating to improve the accuracy of communication error prediction based on given communication contexts and features, and 3) Communication Risk Mitigation – carrying out simulations to adjust communication protocols for reducing communication-related CIS O&M risks.

This dissertation uses two CIS O&M case studies (air traffic control and NPP outages) to validate the proposed method. The results indicate that the proposed method can 1) identify risky communication contexts and features, 2) predict communication errors and CIS O&M risks, and 3) reduce CIS O&M risks triggered by communication errors. The author envisions that the proposed method will shed light on achieving predictive control of interpersonal communications in dynamic and complex CIS O&M.
Date Created
2020
Agent

Characterization of Fatigue Damage in Aerospace Materials under Complex Multiaxial Loading

156788-Thumbnail Image.png
Description
Multiaxial mechanical fatigue of heterogeneous materials has been a significant cause of concern in the aerospace, civil and automobile industries for decades, limiting the service life of structural components while increasing time and costs associated with inspection and maintenance. Fiber…

Multiaxial mechanical fatigue of heterogeneous materials has been a significant cause of concern in the aerospace, civil and automobile industries for decades, limiting the service life of structural components while increasing time and costs associated with inspection and maintenance. Fiber reinforced composites and light-weight aluminum alloys are widely used in aerospace structures that require high specific strength and fatigue resistance. However, studying the fundamental crack growth behavior at the micro- and macroscale as a function of loading history is essential to accurately predict the residual fatigue life of components and achieve damage tolerant designs. The issue of mechanical fatigue can be tackled by developing reliable in-situ damage quantification methodologies and by comprehensively understanding fatigue damage mechanisms under a variety of complex loading conditions. Although a multitude of uniaxial fatigue loading studies have been conducted on light-weight metallic materials and composites, many service failures occur from components being subjected to variable amplitude, mixed-mode multiaxial fatigue loadings. In this research, a systematic approach is undertaken to address the issue of fatigue damage evolution in aerospace materials by:

(i) Comprehensive investigation of micro- and macroscale crack growth behavior in aerospace grade Al 7075 T651 alloy under complex biaxial fatigue loading conditions. The effects of variable amplitude biaxial loading on crack growth characteristics such as crack acceleration and retardation were studied in detail by exclusively analyzing the influence of individual mode-I, mixed-mode and mode-II overload and underload fatigue cycles in an otherwise constant amplitude mode-I baseline load spectrum. The micromechanisms governing crack growth behavior under the complex biaxial loading conditions were identified and correlated with the crack growth behavior and fracture surface morphology through quantitative fractography.

(ii) Development of novel multifunctional nanocomposite materials with improved fatigue resistance and in-situ fatigue damage detection and quantification capabilities. A state-of-the-art processing method was developed for producing sizable carbon nanotube (CNT) membranes for multifunctional composites. The CNT membranes were embedded in glass fiber laminates and in-situ strain sensing and damage quantification was achieved by exploiting the piezoresistive property of the CNT membrane. In addition, improved resistance to fatigue crack growth was observed due to the embedded CNT membrane.
Date Created
2018
Agent

Investigating the Relationship between Energy Consumption, CO2 Emissions, and the Factors Affecting Them in the United States Building Sector: A Macro and Micro View

156707-Thumbnail Image.png
Description
The United States building sector was the most significant carbon emission contributor (over 40%). The United States government is trying to decrease carbon emissions by enacting policies, but emissions increased by approximately 7 percent in the U.S. between 1990 and…

The United States building sector was the most significant carbon emission contributor (over 40%). The United States government is trying to decrease carbon emissions by enacting policies, but emissions increased by approximately 7 percent in the U.S. between 1990 and 2013. To reduce emissions, investigating the factors affecting carbon emissions should be a priority. Therefore, in this dissertation, this research examine the relationship between carbon emissions and the factors affecting them from macro and micro perspectives. From a macroscopic perspective, the relationship between carbon dioxide, energy resource consumption, energy prices, GDP (gross domestic product), waste generation, and recycling waste generation in the building and waste sectors has been verified. From a microscopic perspective, the impact of non-permanent electric appliances and stationary and non-stationary occupancy has been investigated. To verify the relationships, various kinds of statistical and data mining techniques were applied, such as the Granger causality test, linear and logarithmic correlation, and regression method. The results show that natural gas and electricity prices are higher than others, as coal impacts their consumption, and electricity and coal consumption were found to cause significant carbon emissions. Also, waste generation and recycling significantly increase and decrease emissions from the waste sector, respectively. Moreover, non-permanent appliances such as desktop computers and monitors consume a lot of electricity, and significant energy saving potential has been shown. Lastly, a linear relationship exists between buildings’ electricity use and total occupancy, but no significant relationship exists between occupancy and thermal loads, such as cooling and heating loads. These findings will potentially provide policymakers with a better understanding of and insights into carbon emission manipulation in the building sector.
Date Created
2018
Agent

Teaching Non-Technological Skills for Successful Building Information Modeling (BIM) Projects

156647-Thumbnail Image.png
Description
Implementing Building Information Modeling (BIM) in construction projects has many potential benefits, but issues of projects can hinder its realization in practice. Although BIM involves using the technology, more than four-fifths of the recurring issues in current BIM-based construction projects…

Implementing Building Information Modeling (BIM) in construction projects has many potential benefits, but issues of projects can hinder its realization in practice. Although BIM involves using the technology, more than four-fifths of the recurring issues in current BIM-based construction projects are related to the people and processes (i.e., the non-technological elements of BIM). Therefore, in addition to the technological skills required for using BIM, educators should also prepare university graduates with the non-technological skills required for managing the people and processes of BIM. This research’s objective is to develop a learning module that teaches the non-technological skills for addressing common, people- and process-related, issues in BIM-based construction projects. To achieve this objective, this research outlines the steps taken to create the learning module and identify its impact on a BIM course. The contribution of this research is in the understanding of the pedagogical value of the developed problem-based learning module and documenting the learning module’s development process.
Date Created
2018
Agent

Comparing Building Information Modeling Skills of Project Managers and BIM Managers Based on Social Media Analysis

127944-Thumbnail Image.png
Description

Building Information Modeling (BIM) education may accelerate the process of adopting BIM in construction projects. The education community has been examining the best ways of introducing BIM into the curricula. However, individuals in different positions, such as project managers and…

Building Information Modeling (BIM) education may accelerate the process of adopting BIM in construction projects. The education community has been examining the best ways of introducing BIM into the curricula. However, individuals in different positions, such as project managers and BIM managers, may require different BIM skills in practice. Thus, understanding BIM skills could help to better formulate the education program for college students and industry professionals. The authors explored this topic by addressing two research questions: 1) What are the BIM skills possessed by individuals that increase the likelihood of having the titles “project manager” and “BIM manager”? 2) How do these skill-sets differ between project managers and BIM managers? These questions are addressed through an analysis of the LinkedIn profiles of architecture, engineering, construction, and operations (AECO) professionals. Data collection involved gathering endorsed skills, number of endorsements, current position, past positions, and years of work experiences from LinkedIn profiles of AECO professionals. This article identified BIM skills and other skills correlated with BIM skills that increase the likelihood of an individual to own the titles of “project manager” and “BIM manager.” This analysis showed that the number of skills shared between project managers and BIM managers were greater than the number of unique skills possessed by either position. While the two positions shared certain skills, subsequent analysis suggested that many of those skills were correlated with different skills. This may suggest that, while there is overlap in the skills possessed between individuals in each position, the way in which they use those skillsets may differ.

Date Created
2016-05-20
Agent

Automatic Logical Inconsistency Detection in the National Bridge Inventory

127957-Thumbnail Image.png
Description

Studies about the data quality of National Bridge Inventory (NBI) reveal missing, erroneous, and logically conflicting data. Existing data quality programs lack a focus on detecting the logical inconsistencies within NBI and between NBI and external data sources. For example,…

Studies about the data quality of National Bridge Inventory (NBI) reveal missing, erroneous, and logically conflicting data. Existing data quality programs lack a focus on detecting the logical inconsistencies within NBI and between NBI and external data sources. For example, within NBI, the structural condition ratings of some bridges improve over a period while having no improvement activity or maintenance funds recorded in relevant attributes documented in NBI. An example of logical inconsistencies between NBI and external data sources is that some bridges are not located within 100 meters of any roads extracted from Google Map. Manual detection of such logical errors is tedious and error-prone. This paper proposes a systematical “hypothesis testing” approach for automatically detecting logical inconsistencies within NBI and between NBI and external data sources. Using this framework, the authors detected logical inconsistencies in the NBI data of two sample states for revealing suspicious data items in NBI. The results showed that about 1% of bridges were not located within 100 meters of any actual roads, and few bridges showed improvements in the structural evaluation without any reported maintenance records.

Date Created
2016-05-20
Agent

Adaptive 3D Imaging and Tolerance Analysis of Prefabricated Components for Accelerated Construction

127968-Thumbnail Image.png
Description

Tolerance analysis of prefabricated components poses challenges to effective quality control of accelerated construction projects in urban areas. In busy urban environments, accelerated construction methods quickly assemble prefabricated components to achieve workflows that are more efficient and reduce impacts of…

Tolerance analysis of prefabricated components poses challenges to effective quality control of accelerated construction projects in urban areas. In busy urban environments, accelerated construction methods quickly assemble prefabricated components to achieve workflows that are more efficient and reduce impacts of construction on urban traffic and business. Accelerated constructions also bring challenges of “fit-up:” misalignments between components can occur due to less detailed tolerance assessments of components. Conventional tolerance checking approaches, such as manual mock-up, cannot provide detailed geometric assessments in a timely manner. This paper proposes the integration of an adaptive 3D imaging and spatial pattern analysis methods to achieve detailed and frequent “fit-up” analysis of prefabricated components. The adaptive 3D imaging methods progressively adjust imaging parameters of a laser scanner according to the geometric complexities of prefabricated components captured in data collected so far. The spatial pattern analysis methods automatically analyze deviations of prefabricated components from as-designed models to derive tolerance networks that capture relationships between tolerances of components and identify risks of misalignments.

Date Created
2015-09-14
Agent

Human-Centered Automation for Resilience in Acquiring Construction Field Information

155812-Thumbnail Image.png
Description
Resilient acquisition of timely, detailed job site information plays a pivotal role in maintaining the productivity and safety of construction projects that have busy schedules, dynamic workspaces, and unexpected events. In the field, construction information acquisition often involves three types…

Resilient acquisition of timely, detailed job site information plays a pivotal role in maintaining the productivity and safety of construction projects that have busy schedules, dynamic workspaces, and unexpected events. In the field, construction information acquisition often involves three types of activities including sensor-based inspection, manual inspection, and communication. Human interventions play critical roles in these three types of field information acquisition activities. A resilient information acquisition system is needed for safer and more productive construction. The use of various automation technologies could help improve human performance by proactively providing the needed knowledge of using equipment, improve the situation awareness in multi-person collaborations, and reduce the mental workload of operators and inspectors.

Unfortunately, limited studies consider human factors in automation techniques for construction field information acquisition. Fully utilization of the automation techniques requires a systematical synthesis of the interactions between human, tasks, and construction workspace to reduce the complexity of information acquisition tasks so that human can finish these tasks with reliability. Overall, such a synthesis of human factors in field data collection and analysis is paving the path towards “Human-Centered Automation” (HCA) in construction management. HCA could form a computational framework that supports resilient field data collection considering human factors and unexpected events on dynamic job sites.

This dissertation presented an HCA framework for resilient construction field information acquisition and results of examining three HCA approaches that support three use cases of construction field data collection and analysis. The first HCA approach is an automated data collection planning method that can assist 3D laser scan planning of construction inspectors to achieve comprehensive and efficient data collection. The second HCA approach is a Bayesian model-based approach that automatically aggregates the common sense of people from the internet to identify job site risks from a large number of job site pictures. The third HCA approach is an automatic communication protocol optimization approach that maximizes the team situation awareness of construction workers and leads to the early detection of workflow delays and critical path changes. Data collection and simulation experiments extensively validate these three HCA approaches.
Date Created
2017
Agent
Subscribe to Tang, Pingbo