Browsing by Subject "artificial neural networks"
Now showing 1 - 4 of 4
Results Per Page
Sort Options
Item A Methodology for Developing Performance-Related Specifications for Pavement Preservation Treatments(2013-09-23) Liu, LitaoCurrent materials and construction specifications for pavement preservation treatments are predominantly prescriptive and they have little or no methodical linkage between initial treatment quality and future performance. There is an imperative need for performance-related specifications (PRS) that link the initial quality of pavement preservation treatments to their long-term performance and life-cycle costs so that rational pay adjustment and acceptance decisions can be made. However, the current literature lacks a methodology for developing PRS for pavement preservation treatments. The aim of this research is to fill this gap in the literature, with focus on thin HMA overlays. In this dissertation, a novel approach was devised for developing performance prediction models for pavements that received preservation treatments. In this approach, the model consists of two tightly-coupled components: the first component is responsible for predicting the performance (e.g., IRI) of the existing pavement if no treatment was applied. The second component is responsible for predicting the reduction in pavement deterioration due to the application of the treatment. Inputs to the first component include material and construction properties of the existing pavement layers, climatic conditions, and traffic factors. Inputs to the second component include the treatment?s acceptance quality characteristics (AQCs), climatic conditions, and traffic factors. The artificial neural networks (ANNs) and the Bayesian regression methods were used for developing the two model components. Using this approach, a model was developed for predicting the International Roughness Index (IRI) of flexible pavement treated with thin HMA overlay. The data used for developing and testing this model was obtained from the Long-Term Pavement Performance (LTPP) database. Artificial neural networks (ANNs) and Bayesian regression techniques were employed for developing the first and second components of this model, respectively. A PRS methodology was developed for quantifying the difference between the initial quality levels of as-constructed and as-designed treatments. This methodology consists of a novel approach for determining the probability distributions of service life and present-worth value (PWV). This approach allows for transforming the probabilistic distribution of future IRI (predicted by the Bayesian model) into probability distributions for service life and PWV. Pay factors are then estimated based on the difference between the as-constructed and target PWVs. Finally, this dissertation provides insights into the relationships between initial quality (measured in terms of both mean and standard deviation of key acceptance quality characteristics) and expected pay factors through analysis of real world case studies of asphalt pavements treated with thin HMA overlays.Item Computational Fracture Prediction in Steel Moment Frame Structures with the Application of Artificial Neural Networks(2012-10-19) Long, XiaoDamage to steel moment frames in the 1994 Northridge and 1995 Hyogken-Nanbu earthquakes subsequently motivated intensive research and testing efforts in the US, Japan, and elsewhere on moment frames. Despite extensive past research efforts, one important problem remains unresolved: the degree of panel zone participation that should be permitted in the inelastic seismic response of a steel moment frame. To date, a fundamental computational model has yet to be developed to assess the cyclic rupture performance of moment frames. Without such a model, the aforementioned problem can never be resolved. This dissertation develops an innovative way of predicting cyclic rupture in steel moment frames by employing artificial neural networks. First, finite element analyses of 30 notched round bar models are conducted, and the analytical results in the vicinity of the notch root are extracted to form the inputs for either a single neural network or a competitive neural array. After training the neural networks, the element with the highest potential to initiate a fatigue crack is identified, and the time elapsed up to the crack initiation is predicted and compared with its true synthetic answer. Following similar procedures, a competitive neural array comprising dynamic neural networks is established. Two types of steel-like materials are created so that material identification information can be added to the input vectors for neural networks. The time elapsed by the end of every stage in the fracture progression is evaluated based on the synthetic allocation of the total initiation life assigned to each model. Then, experimental results of eight beam-to-column moment joint specimens tested by four different programs are collected. The history of local field variables in the vicinity of the beam flange - column flange weld is extracted from hierarchical finite element models. Using the dynamic competitive neural array that has been established and trained, the time elapsed to initiate a low cycle fatigue crack is predicted and compared with lab observations. Finally, finite element analyses of newly designed specimens are performed, the strength of their panel zone is identified, and the fatigue performance of the specimens with a weak panel zone is predicted.Item Predicting bid prices in construction projects using non-parametric statistical models(2009-05-15) Pawar, RoshanBidding is a very competitive process in the construction industry; each competitor?s business is based on winning or losing these bids. Contractors would like to predict the bids that may be submitted by their competitors. This will help contractors to obtain contracts and increase their business. Unit prices that are estimated for each quantity differ from contractor to contractor. These unit costs are dependent on factors such as historical data used for estimating unit costs, vendor quotes, market surveys, amount of material estimated, number of projects the contractor is working on, equipment rental costs, the amount of equipment owned by the contractor, and the risk averseness of the estimator. These factors are nearly similar when estimators are estimating cost of similar projects. Thus, there is a relationship between the projects that a particular contractor has bid in previous years and the cost the contractor is likely to quote for future projects. This relationship could be used to predict bids that the contractor might quote for future projects. For example, a contractor may use historical data for a certain year for bidding on certain type of projects, the unit prices may be adjusted for size, time and location, but the basis for bidding on projects of similar types is the same. Statistical tools can be used to model the underlying relationship between the final cost of the project quoted by a contractor to the quantities of materials or amount of tasks performed in a project. There are a number of statistical modeling techniques, but a model used for predicting costs should be flexible enough that it could adjust to depict any underlying pattern. Data such as amount of work to be performed for a certain line item, material cost index, labor cost index and a unique identifier for each participating contractor is used to predict bids that a contractor might quote for a certain project. To perform the analysis, artificial neural networks and multivariate adaptive regression splines are used. The results obtained from both the techniques are compared, and it is found that multivariate adaptive regression splines are able to predict the cost better than artificial neural networks.Item Understanding, Modeling and Predicting Hidden Solder Joint Shape Using Active Thermography(2012-07-16) Giron Palomares, JoseCharacterizing hidden solder joint shapes is essential for electronics reliability. Active thermography is a methodology to identify hidden defects inside an object by means of surface abnormal thermal response after applying a heat flux. This research focused on understanding, modeling, and predicting hidden solder joint shapes. An experimental model based on active thermography was used to understand how the solder joint shapes affect the surface thermal response (grand average cooling rate or GACR) of electronic multi cover PCB assemblies. Next, a numerical model simulated the active thermography technique, investigated technique limitations and extended technique applicability to characterize hidden solder joint shapes. Finally, a prediction model determined the optimum active thermography conditions to achieve an adequate hidden solder joint shape characterization. The experimental model determined that solder joint shape plays a higher role for visible than for hidden solder joints in the GACR; however, a MANOVA analysis proved that hidden solder joint shapes are significantly different when describe by the GACR. An artificial neural networks classifier proved that the distances between experimental solder joint shapes GACR must be larger than 0.12 to achieve 85% of accuracy classifying. The numerical model achieved minimum agreements of 95.27% and 86.64%, with the experimental temperatures and GACRs at the center of the PCB assembly top cover, respectively. The parametric analysis proved that solder joint shape discriminability is directly proportional to heat flux, but inversely proportional to covers number and heating time. In addition, the parametric analysis determined that active thermography is limited to five covers to discriminate among hidden solder joint shapes. A prediction model was developed based on the parametric numerical data to determine the appropriate amount of energy to discriminate among solder joint shapes for up to five covers. The degree of agreement between the prediction model and the experimental model was determined to be within a 90.6% for one and two covers. The prediction model is limited to only three solder joints, but these research principles can be applied to generate more realistic prediction models for large scale electronic assemblies like ball grid array assemblies having as much as 600 solder joints.