Prediction of Sewer Condition Grade Using Support Vector Machines

Assessing the condition of sewer networks is an important asset management approach. However, because of high inspection costs and limited budget, only a small proportion of sewer systems may be inspected. Tools are therefore required to help target inspection efforts and to extract maximum value from the condition data collected. Owing to the difficulty in modeling the complexities of sewer condition deterioration, there has been interest in the application of artificial intelligence-based techniques such as artificial neural networks to develop models that can infer an unknown structural condition based on data from sewers that have been inspected. To this end, this study investigates the use of support vector machine (SVM) models to predict the condition of sewers. The results of model testing showed that the SVM achieves good predictive performance. With access to a representative set of training data, the SVM modeling approach can therefore be used to allocate a condition grade to sewer assets with reasonable confidence and thus identify high risk sewer assets for subsequent inspection.     

Condition Rating Model for Underground Infrastructure Sustainable Water Mains

One of the greatest challenges facing municipal engineers is the condition rating of buried infrastructure assets, particularly water mains. This is because water mains are typically underground, operated under pressure, and usually inaccessible. Condition rating is a mandatory process to establish and employ management strategies for any asset. To assess the condition of water mains, current research considers physical, environmental, and operational factors and their effect on different types of mains (i.e., cast iron, ductile iron, and asbestos). A condition rating model is developed to assess and set up rehabilitation priority for water mains using the artificial neural network (ANN) approach. Data are collected from different municipalities to train the developed model. The ANN input factors incorporate pipe type, size, age, breakage rate, Hazen-Williams factor, excavation depth, soil type, and top road surface; however, the output is pipe condition. The trained ANN shows robust performance (learning rate = 0.005, R2 = 0.931, correlation coefficient r = 0.9653). Results show that the breakage rate has the highest relative contribution factor among the others. The developed model is relevant to researchers and practitioners (municipal engineers, consultants, and contractors) in order to prioritize pipe inspection and rehabilitation planning for existing water mains.     

Key Assessment Indicators for the Sustainability of Infrastructure Projects

Infrastructure projects have major effects on implementing the principles of sustainable development. Infrastructure projects will continue to be developed in the coming years, particularly in developing countries such as China and India; therefore, it is important to find methods and solutions for improving the sustainability of them. Although existing studies have suggested various methods for practicing sustainable development principles in the process of implementing infrastructure projects, effective assessment indicators are unavailable, which presents a barrier to the effective assessment of infrastructure project sustainability. This study introduces key assessment indicators (KAIs) for assessing the sustainability performance of an infrastructure project. The research data used for analysis were collected from a questionnaire survey given to three groups of experts, including government officials, professionals, and clients in the Chinese construction industry. The fuzzy set theory was used to establish KAIs. A procedure for using the KAIs is demonstrated by a case study. These research findings provide an alternative solution to appraise the sustainability of infrastructure projects.     

Dimensionless Approach for the Design of Flushing Gates in Sewer Channels

The various hydraulic and environmental problems related to the accumulation of solids have recently drawn increasingly attention to deposits in the management of sewer systems. Among the mechanical and hydraulic devices used for deposit removal, hydraulic flushing gates have proved to be a cost-effective solution and have been adopted in several sewer networks. This paper reports the results of an investigation on the scouring performance of flushing waves produced by hydraulic flushing gates. A numerical model based on the De Saint Venant–Exner equations in dimensionless form was validated by using data derived from laboratory experiments and was then utilized in this investigation. Simulations were carried out considering various values of the dimensionless parameters involved in the analysis, in order to obtain indications for the design and positioning of flushing devices in sewer channels. The problem of optimal flushing frequency was also investigated.     

Multivariate Polynomial Time-Series Models and Importance Ratios to Qualify Fecal Coliform Sources

Sensitivity analysis using importance ratios was applied to multivariate polynomial regression (MPR) models to make inferences about the nature and magnitude of fecal coliform (FC) sources in a combined sewer overflow-impacted stretch of the Passaic River at Paterson, New Jersey. The predictor variables in this study were temperature, discharge, precipitation, and upstream concentrations. The MPR models are applicable only for the current conditions with respect to pollutant sources. New models should be developed in case of any change in pollutant sources, by location or magnitude. This is a limitation that MPR models have in common with any empirical modeling approach, including multilinear regression or artificial neural networks. The performance of the MPR models using R2 was significantly better than simple linear models using the same variables. The importance ratio, a dimensionless measure of model sensitivity, was used for comparison of the effects of different variables. Because model sensitivities, and therefore importance ratios, are not constant in nonlinear models, this work examines their distributions and relates them to system behavior, for example by showing under what conditions dilution does or does not affect FC concentrations in the stream. The analysis showed that MPR models and importance ratios can be used to provide significant information to better understand pollutant sources at a site and the relative importance of various predictor variables in explaining the variability in the FC concentrations.     

Dynamic Regression Models for Prediction of Construction Costs

Accurate prediction of construction costs in the market is essential to effectively estimate costs for construction projects. In the construction industry, cost indexes that are reported in series are often used to explain the change of construction costs. By tracking the trend of such quantitative contemporaneous cost index and making frequent and regular forecasts of the future values of the index, one can develop a deeper understanding of prices of resources used for construction. Incorporating such an understanding and prediction into estimating will help practitioners manage construction costs. This paper proposes two dynamic regression models for the prediction of construction cost index. Comparison of the proposed models with the existing methods proves that the new models provide several advantages and improvements.     

Systematic Evaluation of One-Dimensional Unsteady Friction Models in Simple Pipelines

In this paper, basic unsteady flow types and transient event types are categorized, and then unsteady friction models are tested for each type of transient event. One important feature of any unsteady friction model is its ability to correctly model frictional dissipation in unsteady flow conditions under a wide a range of possible transient event types. This is of importance to the simulation of transients in pipe networks or pipelines with various devices in which a complex series of unsteady flow types are common. Two common one-dimensional unsteady friction models are considered, namely, the constant coefficient instantaneous acceleration-based model and the convolution-based model. The modified instantaneous acceleration-based model, although an improvement, is shown to fail for certain transient event types. Additionally, numerical errors arising from the approximate implementation of the instantaneous acceleration-based model are determined, suggesting some previous good fits with experimental data are due to numerical error rather than the unsteady friction model. The convolution-based model is successful for all transient event types. Both approaches are tested against experimental data from a laboratory pipeline.     

Green Building and Sustainable Infrastructure: Sustainability Education for Civil Engineers

This paper discusses a framework for incorporating sustainable design/thinking as a new civil engineering course and experiences from the pilot offering. Important areas are outlined to aid all engineers in understanding sustainability in context with traditional engineering principles. Green-building rating systems were used to introduce the concepts of sustainability in buildings and infrastructure, highlighted by presentations from green-building professionals. By providing a better understanding of sustainability through education, civil engineers can provide proactive solutions to a growing global infrastructure.     

Comparative Analysis of Life-Cycle Costing for Rehabilitating Infrastructure Systems

Metro systems usually offer an attractive alternative for mass transit transportation system in most large cities. Such infrastructures require proper maintenance and rehabilitation (M&R) programs to maintain them within an acceptable level of operational and safety performance. The Markov decision process (MDP) has been widely used to find the optimal M&R decision policy for situations that deal with uncertainties. A drawback of the traditional MDP approach is that it uses discrete number of states in the analysis as well as a stationary transition probability matrix (TPM). Also the MDP is based on the Markovian or “memory-less” property, which is not necessarily the fact for all aging infrastructures. This research presents a case study on a deteriorating slab in a Montreal metro. The traditional MDP is employed with linear programming to determine the optimal rehabilitation profile. Three different methods are employed for calculating life-cycle cost: (1) the average expected discount cost per time period that is normally used with the traditional MDP; (2) continuous rating approach; and (3) dynamic or time-dependent TPM. Results revealed that the continuous rating approach provides lower values compared to the traditional approach. Dynamic TPM reflects better the infrastructure behavior but necessitate additional data gathering. This research mainly benefits metro management agencies and enhances the MDP practice by overcoming some downsides of the traditional methodology.     

Application of a Sustainability Model for Assessing Water Main Replacement Options

Sustainable development, conceived as a new and multidisciplinary paradigm, is receiving much attention throughout the global community. The purpose of this paper is to apply the sustainability assessment model (SAM), an assessment and decision making methodology, to a water main replacement project in an urban environment to determine the most sustainable project alternative among three possible options. This case study presents the use of SAM in considering various multicriteria sustainability indicators while working towards achieving sustainability enhancement. Objectives of sustainability enhancement include: (1) minimizing environmental impact; (2) maximizing economical benefit and output; (3) social and cultural conservation and promotion; and (4) satisfying basic requirements such as structural soundness and capacity. Six assessment methods including the analytic hierarchy process, cost, pollution, energy, time estimation, and natural resource depletion analysis are used for both qualitative and quantitative sustainability indicators. The weighted sum model is then utilized to integrate the six independent assessment results to elicit the final decision.     

Wavelet-Based Vibration Sensor Data Compression Technique for Civil Infrastructure Condition Monitoring

Civil infrastructure condition monitoring generates large volumes of sensor data. Huge data size impedes fast and reliable distribution of sensor data, especially for wireless sensor networks. Vibration sensor data plays an important role in many useful structural health monitoring methods. This paper presents a vibration sensor data compression technique based on the lifting scheme wavelet transform (LSWT). Real sensor data from a nine-story building as well as a steel truss bridge was used to examine the compression performance of the LSWT-based vibration sensor data compression technique. It is found that the LSWT-based vibration sensor data compression technique can achieve a very high compression ratio while retaining the basic waveform properties of original sensor data. Additionally, LSWT has a feature that supports progressive compression and thus allows for multiresolution data transmission and retrieval.     

Visual Pattern Recognition Models for Remote Sensing of Civil Infrastructure

As-built models have been proven useful in many project-related applications, such as progress monitoring and quality control. However, they are not widely produced in most projects because a lot of effort is still necessary to manually convert remote sensing data from photogrammetry or laser scanning to an as-built model. In order to automate the generation of as-built models, the first and fundamental step is to automatically recognize infrastructure-related elements from the remote sensing data. This paper outlines a framework for creating visual pattern recognition models that can automate the recognition of infrastructure-related elements based on their visual features. The framework starts with identifying the visual characteristics of infrastructure element types and numerically representing them using image analysis tools. The derived representations, along with their relative topology, are then used to form element visual pattern recognition (VPR) models. So far, the VPR models of four infrastructure-related elements have been created using the framework. The high recognition performance of these models validates the effectiveness of the framework in recognizing infrastructure-related elements.     

Identifying and Assessing Influence Factors on Improving Waste Management Performance for Building Construction Projects

Environmental sustainability has become one of the key drivers for continuous growth in the construction industry. Many project practitioners face challenging circumstances in finding an effective way to prevent pollution and minimize wastes by making the best use of the increasingly scarce natural resources. However, most of these efforts are focused on planning and/or design strategies; therefore, they fail to thoroughly cover the environmental issues based on the construction execution level. Further, there is a lack of quantitative measurement system and management-level guidance. To overcome these limitations, this paper proposes a new methodology that assists project managers to assess the performance level of a project in terms of waste management practice. This study is based on a two-pronged approach. One is the identification of the waste management influence factors that play an important role in decreasing waste and increasing recycled materials on construction sites. The other is the development of an assessment tool to measure the level of waste management performance for a particular project. As a result of this work, 59 factors were identified and an assessment tool was developed based on quantification of these factors. The tool has been proved to effectively measure waste management performance throughout four real-case validity tests. From the industry perspective, this paper contributes to establishing the environmentally sustainable production systems by providing the project stakeholders with an established set of influence factors and with a diagnosis tool for measuring their current performance. Additionally, project owners can use the output of the tool, especially the total index score, as a measure to benchmark the level of waste management for continuous improvement.     

Lean Processes for Sustainable Project Delivery

Facility owners and project teams often struggle to engage “green” or “sustainable” requirements on building projects and can incur additional project costs as a result. Although “investments” in high performance building features can be paid back through operational savings, the project delivery methods currently adopted by most teams are laden with process waste. Lean production principles have been proven to reduce waste and improve process performance in highly complex development and production environments. Adopting these lean principles, this paper reports a study that identified the presence of value and waste in a sustainable building project. Through an empirical investigation of the Real Estate and Facilities Division of Toyota Motor Sales, Toyota’s capital facility delivery process was mapped to identify both the steps in project delivery critical for success (value) and those that are waste. The investigation focused on the South Campus Facility, which received U.S. Green Building Council’s Leadership in Energy and Environmental Design Gold certification at a project cost equivalent to a conventional facility. Through post hoc process-based analysis, insight about what added value and waste in sustainable project delivery at Toyota was obtained. The results also identify further improvement opportunities to Toyota’s delivery process. For corporate facility owners and the Architecture Engineering Construction industry, the results unearth insights about how to successfully and economically deliver sustainable facilities.     

Artificial Intelligence-Based Inductive Models for Prediction and Classification of Fecal Coliform in Surface Waters

This paper describes the use of inductive models developed using two artificial intelligence (AI)-based techniques for fecal coliform prediction and classification in surface waters. The two AI techniques used include artificial neural networks (ANNs) and a fixed functional set genetic algorithm (FFSGA) approach for function approximation. While ANNs have previously been used successfully for modeling water quality constituents, FFSGA is a relatively new technique of inductive model development. This paper will evaluate the efficacy of this technique for modeling indicator organism concentrations. In scenarios where process-based models cannot be developed and/or are not feasible, efficient and effective inductive models may be more suitable to provide quick and reasonably accurate predictions of indicator organism concentrations and associated water quality violations. The relative performance of AI-based inductive models is compared with conventional regression models. When raw data are used in the development of the inductive models described in this paper, the AI models slightly outperform the traditional regression models. However, when log transformed data are used, all inductive models show comparable performance. While the work validates the strength of simple regression models, it also validated FFSGA to be an effective technique that competes well with other state-of-the-art and complex techniques such as ANNs. FFSGA comes with the added advantage of resulting in a simple, easy to use, and compact functional form of the model sought. This work adds to the limited amount of research on the use of data-driven modeling methods for indicator organisms.     

Prediction Models for Annual Break Rates of Water Mains

Annual break rates are often used by municipalities as one of the most important criteria in rating the condition of water mains. This paper presents the development of deterioration models that predict the annual break rates of water mains considering pipe material, diameter, age, and length. The data used in this paper are collected from a Canadian municipality that has a large water distribution network. The collected data cover 15-year pipe break records of 432?km of water mains. Five multiple regression models are developed, which show robust statistical analysis. Twenty percent of break data were randomly selected for validation in which the developed models demonstrate satisfactory results. The research presented in this paper is expected to be useful to academics and practitioners (municipal engineers, consultants, and contractors) in analyzing deterioration trends of water mains.     

Flight Optimization Algorithms for Aerial LiDAR Capture for Urban Infrastructure Model Generation

Aerial light detection and ranging (LiDAR) offers the potential to autogenerate detailed, three-dimensional (3D) models of the built environment in urban settings. Autogeneration is needed as manual generation is not economically feasible for large areas, and such models are needed for a wide range of applications from improved noise and pollution prediction to disaster mitigation modeling and visualization. Current laser scanning hardware and the dense geometry of urban environments are two major constraints in LiDAR scanning. This paper outlines the difficulties related to effective surface data capture, with emphasis on vertical surfaces, in an urban environment for the purpose of 3D modeling. A flight planning strategy to overcome these difficulties is presented, along with a case study of a data set collected with this strategy. The main conclusions of this study are that an appropriate amount of strip overlap, together with a flight path diagonal to the underlying street grid produces a vastly enhanced level of detail on vertical surfaces, beyond what has been previously available.     

Sensitivity Analysis for Hydraulic Models

Sensitivity analysis is well recognized as being an important aspect of the responsible use of hydraulic models. This paper reviews a range of methods for sensitivity analysis. Two applications, one to a simple pipe bend example and the second to an advanced Shallow Water Equation solver, illustrate the deficiencies of standardized regression coefficients in the context of functionally nonlinear models. Derivatives and other local methods of sensitivity analysis are shown to give an incomplete picture of model response over the range of variability in the model inputs. The use of global variance-based sensitivity analysis is shown to be more general in its applicability and in its capacity to reflect nonlinear processes and the effects of interactions among variables.     

Selecting Infrastructure Delivery Modalities: No Time for Ideology or Semantics

Developing and developed countries need to increase their investments in infrastructure to support economic growth, productivity, and the competitiveness of their economies to enhance the well being of their populations. Some of these investments, being long term, illiquid and considered public services, tend to be undertaken by the public sector. Nevertheless, in some sectors and at different points in history, there has been considerable participation by the private sector. For the purposes of enhancing these investments, all possible options of private and public participation must be considered and the needs are such that ideology and semantics should not get in the way. From the very extensive experience in developing countries, it has been learned that selecting the proper modalities can enhance the long term viability of the investments, can increase the number of bankable projects, attract investments and reduce backlash from failures. These lessons can be applied to developed countries as well. This paper presents a model for the selection of the most suitable service delivery modalities adapted to the prevailing local conditions of the country.     

General Education for Civil Engineers: Sustainable Development

The ABET criteria for engineering programs no longer has a requirement for humanities and social sciences but instead requires a general education component that complements the technical component of the curriculum. Achievement of the outcomes called for in the ABET criteria and the ability to apply the constraints listed in ABET Criterion 3 can be facilitated by a well-designed general education component. The old humanities and social science components that many programs still have would probably allow most programs to meet the current criteria but the requirement for general education offers an opportunity to improve the overall educational experience for all civil engineers. One approach to general education for civil engineers would be to incorporate a theme and a case is made that sustainability and sustainable development is a good theme for a civil engineering program.