Civil & Environmental Engineering

Permanent URI for this communityhttp://hdl.handle.net/1903/2221

Browse

Subject: search.filters.subject.Artificial intelligence

Search Results

Now showing 1 - 5 of 5
  • Thumbnail Image
    Item
    Prediction of Marine Timber Pile Damage Ratings Using a Gradient Boosted Regression Model
    (2023) Willmott, Carly; Attoh-Okine, Nii O.; Civil Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    Marine pilings are critical structural elements exposed to harsh environmental conditions. Specialized routine inspection and regular maintenance are essential to keep marine facilities in good working condition. These activities generate data that can be exploited for knowledge gain with machine learning tools. A gradient boosted random forest regressor machine learning algorithm, XGBoost, was applied to datasets that contain timber pile underwater inspection and repair data over a period of 23 years. First, the data was visualized to show the longevity of different timber pile repair types. An XGBoost model was then tuned and trained on a dataset for timber piles at one pier. Variables in the dataset were evaluated for feature importance in predicting damage ratings assigned during routine underwater inspections. Next, an ensemble of XGBoost models was trained and applied to a second dataset containing the same features for an adjacent pier. This dataset was reserved for testing to demonstrate whether the ensemble trained on one pier’s data could be generalized to predict timber pile damage ratings at a nearby but separate pier. Finally, the ensemble was used to predict damage ratings on piles that had earlier data but were not rated in the two most recent inspection events. Results suggest that the ensemble is capable of predicting timber pile damage ratings to approximately +/- one damage rating on both the training and test datasets. Feature importances revealed that half of the variables (time since the first event, repair type, exposed pile length, and time since the last repair) contributed to two thirds of the relative importance in predicting damage ratings. Data visualization showed that a few repair types, such as pile replacements and encapsulations, appeared to be most successful over the long term compared with shorter-lived repairs like wraps and encasements. These results are promising indications of the advantages machine learning algorithms can offer in processing and gleaning new insights from structural repair and inspection data. Economic benefits to marine facility owners can potentially be realized through earlier anticipation of repairs and more targeted inspection and rehabilitation efforts. There are also opportunities for better understanding of deterioration rates if more data is gathered over the lifespans of structures, as well as more detailed data that can be introduced as new features.
  • Thumbnail Image
    Item
    EVENT-DRIVEN OPERATION OF DISTRIBUTED SYSTEMS WITH ARTIFICIAL INTELLIGENCE TECHNOLOGIES AND BEHAVIOR MODELING
    (2022) Montezzo Coelho, Maria Eduarda; Austin, Mark A; Civil Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    This dissertation aims to enhance decision making in urban settings by integrating artificial intelligence technologies with distributed behavior modeling. Today’s civil engineering systems are far more heterogeneous than their predecessors and may be connected to other types of systems in completely new ways, making the task of system design, analysis and integration of multi-disciplinary concerns much more difficult than in the past. These challenges can be addressed by combining machine learning formalisms and semantic model representations of urban systems, that work side-by-side in collecting data, identifying events, and managing city operations in real-time. We exercise the proposed approach on a problem involving anomaly detection in an urbanwater distribution system and a metrorail system.
  • Thumbnail Image
    Item
    ARTERIAL PROBABILISTIC TRAFFIC MODELING AND REAL-TIME TRAVEL TIME PREDICTION WITH VEHICLE PROBE DATA USING MACHINE LEARNING
    (2018) Zarin, Bahar; Haghani, Ali; Civil Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    This study proposes a probabilistic modeling framework for the estimation and prediction of link-based arterial travel time distribution using GPS data. The spatiotemporal correlations of the network are modeled using a directional acyclic graphical model, and several external variables in the prediction model are included to yield a better prediction in a variety of situations. This study also aims to investigate the effects of each factor on the travel time and the uncertainty associated with it. In the proposed model, factors such as weather conditions, seasons, time of day, and day of the week are added as external variables in the graphical model. After determining the structure of the model, Streaming Variational Bayes (SVB) is used for training and parameter inference; this offers a valuable option when constant streaming data is utilized. SVB adaptively changes its parameters gradually with a lower computational cost, which makes the process less time-consuming and more efficient. The analysis shows that incorporating external variables can improve the model performance. The data used in this study is INRIX vehicle trajectory raw data from four months - February, June, July, and October of 2015 - which makes it possible to take into account the effects of seasons and weather conditions on travel time and its uncertainty. One of the products of this study is a framework for vehicle trajectory data cleaning process including trip identification, removing outliers, and cleaning the trips data. Once the data are cleaned and ready to use, they should be mapped to the roads. The Hidden Markov Model (HMM) map matching algorithm is used to map the GPS latitude/longitude data to the Open Street Map (OSM) base map and find the traversed links between each pair of GPS points of vehicle trajectories. Finally, a novel procedure to compare any travel time prediction model with any available commercial routing API is proposed and tested to compare the proposed model with Google API.
  • Thumbnail Image
    Item
    DECISION ANALYSIS IN CONSTRUCTION CLAIMS
    (2016) Lessani, Arian; Baecher, Gregory B; Civil Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    Claims in construction projects are inevitable and can result in costly litigation. Construction contract ambiguity, overly restrictive terms, and unfairly allocated risks are among the factors increasing the likelihood of conflict between parties in construction claims. The source of conflict is a gap between parties’ beliefs over specifics of a claim. This research introduces a settlement negotiation model that provides methods for disagreeing parties to understand the gaps in their beliefs and possibly to come to an agreement before litigation. The quantitative decision analysis approach identifies a range for the optimal settlement amount in the claim process. Each party holds private information regarding its belief over the specifics of a claim. The specifics of a claim are classified into Liability, the likelihood of the defendant being found liable at a trial, and Damages, unanticipated expenditures plaintiff incurred due to the defendant’s alleged fault. A Bayesian Network model quantifies parties’ beliefs over Liability and Damages. This model represents parties’ legal arguments and their respective strengths and credibility. These beliefs become inputs to a non-cooperative game theory model. Non-cooperative game theory analyzes interactions between the claim parties at each stage of the claim. The asymmetric information game considers each party’s actions and strategy based on its belief over the expected outcome from litigation, and its belief over the opponent’s expected outcome from litigation. The analysis results in equilibriums that help parties decide how to resolve the claim and avoid costly and timely litigation. The resulting approach reveals predictive outcomes in construction claims using economic theory to analyze construction disputes.
  • Thumbnail Image
    Item
    Semantic-driven modeling and reasoning for enhanced safety of cyber-physical systems
    (2016) Petnga, Leonard; Austin, Mark; Civil Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    This dissertation is concerned with the development of new methodologies and semantics for model-based systems engineering (MBSE) procedures for the behavior modeling of cyber-physical systems (CPS). Our main interest is to enhance system-level safety through effective reasoning capabilities embedded in procedures for CPS design. This class of systems is defined by a tight integration of software and physical processes, the need to satisfy stringent constraints on performance, safety and a reliance on automation for the management of system functionality. Our approach employs semantic–driven modeling and reasoning : (1) for the design of cyber that can understand the physical world and reason with physical quantities, time and space, (2) to improve synthesis of component-based CPS architectures, and (3) to prevent under-specification of system requirements (the main cause of safety failures in software). We investigate and understand metadomains, especially temporal and spatial theories, and the role ontologies play in deriving formal, precise models of CPS. Description logic-based semantics and metadomain ontologies for reasoning in CPS and an integrated approach to unify the semantic foundations for decision making in CPS are covered. The research agenda is driven by Civil Systems design and operation applications, especially the dilemma zone problem. Semantic models of time and space supported respectively by Allen’s Temporal Interval Calculus (ATIC) and Region Connectedness Calculus (RCC-8) are developed and demonstrated thanks to the capabilities of Semantic Web technologies. A modular, flexible, and reusable reasoning-enabled semantic-based platform for safety-critical CPS modeling and analysis is developed and demonstrated. The platform employs formal representations of domains (cyber, physical) and metadomains (temporal and spatial) entities using decidable web ontology language (OWL) formalisms. Decidable fragments of temporal and spatial calculus are found to play a central role in the development of spatio-temporal algorithms to assure system safety. They rely on formalized safety metrics developed in the context of cyber-physical transportation systems and collision avoidance for autonomous systems. The platform components are integrated together with Whistle, a small scripting language (under development) able to process complex datatypes including physical quantities and units. The language also enables the simulation, visualization and analysis of safety tubes for collision prediction and prevention at signalized and non-signalized traffic intersections.