Infrastructure Condition Prediction Models for Sustainable Sewer Pipelines

The Federation of Canadian Municipalities reported that approximately 55% of sewer infrastructure in Canada did not meet current standards. Therefore, the burden on Canadian municipalities to maintain and prioritize sewers is increasing. One of the major challenges is to develop a framework to standardize the condition assessment procedures for sewer pipelines. Lack of detailed knowledge on the condition of sewer networks escalates vulnerability to catastrophic failures. This research presents a proactive methodology of assessing the existing condition of sewers by considering various physical, environmental, and operational influence factors. Based on historic data collected from two municipalities in Canada, structural and operational condition assessment models for sewers are developed using the multiple regression technique. The developed regression models show 82 to 86% accuracy when they are applied to the validation data set. These models are utilized to generate deterioration curves for concrete, asbestos cement, and polyvinyl chloride sewers in relation to traffic loads, bedding materials, and other pipe characteristics. The developed models are expected to assist municipal engineers in identifying critical sewers, prioritizing sewer inspections, and rehabilitation requirements.     

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.     

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.     

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.     

Integrated Decision Support System for Optimal Renewal Planning of Sewer Networks

Municipalities are under increasing pressure to adopt proactive and optimized renewal strategies to reduce the risks, life-cycle costs, and resources needed to maintain acceptable performance and service levels of their infrastructure assets. A new integrated approach for optimal renewal planning of municipal infrastructure systems has been developed. This paper discusses the application of the proposed approach to implement a GIS-based decision support system (DSS) to support the renewal planning of sewer networks. Condition rating, risk assessment, and prioritization techniques are described. A procedure for identifying and selecting the most suitable renewal technologies is also presented. A genetic algorithm-based multiobjective optimization technique is used to find a Pareto front of feasible solutions, each comprising a set of sewers to be renewed each year, along with the associated costs and expected benefits in terms of condition improvement and risk reduction. The paper also presents an example application of the prototype DSS on the sewer network in Regina, Canada.     

Hydraulic Deterioration Models for Storm-Water Drainage Pipes: Ordered Probit versus Probabilistic Neural Network

A decrease in discharge capacity of storm-water drainage pipes is the result of the so-called hydraulic deterioration which reduces the cross sectional area of pipes and increases the pipe roughness. Hydraulic deterioration is caused by tree root intrusion, sediment accumulation, and encrustation, and is affected by many influential factors such as pipe size and pipe location. Predicting hydraulic deterioration is important for effective management of drainage pipes. An ordered probit deterioration model (OPDM) and a probabilistic neural network deterioration model (PNNDM) were developed in this study using the influential factors as model inputs and the hydraulic condition as model output. Their predictive performances were compared against each other using a case study from Melbourne, Australia with a sample of 417 storm-water drainage pipes subjected to closed circuit television inspection. The results show that the PNNDM is more suitable for predicting the hydraulic deterioration and outperforms the OPDM. Several input factors such as pipe size and pipe age are found significant to the hydraulic deterioration.     

Forecasting the Remaining Useful Life of Cast Iron Water Mains

Effective asset management strategy of civil infrastructure systems requires integration of technical and financial plans. This is particularly true in managing water mains, which requires knowledge of their current condition and their forecasted remaining useful life. This paper presents a model designed to forecast the remaining useful life of cast iron water mains. The model is easy to use and its generated results are utilized in determining condition rating of the water mains being considered. The model considers factors related to pipe properties, its operating conditions, and the external environment that surrounds the pipe. In addition, it overcomes limitations associated with existing models. Three different data-driven techniques are considered in the model development; each is used to study the relationship between remaining useful life and a set of deterioration factors, and to forecast remaining useful life of cast iron water mains. These techniques are multiple regression and two types of artificial neural networks: multilayer perceptron; and general regression neural network. The data used in model development were acquired from 16 municipalities in Canada and the United States. The results produced by the developed models correlate well with the actual conditions.     

Neuro-Fuzzy Approaches for Sanitary Sewer Pipeline Condition Assessment

Recent advances in optical sensors and computing technologies have led to the development of inspection systems for underground facilities such as water lines, sewer pipes, and telecommunication conduits. It is now possible for inspection technologies that require no human entry into underground structures to be fully automated, from data acquisition to data analysis, and eventually to condition assessment. This paper describes the development of an automated data interpretation system for sanitary sewer pipelines. The interpretation system obtains optical data from the Sewer Scanner and Evaluation Technology (SSET), which is known to be the current leading-edge technology in inspecting sanitary sewer pipelines. The proposed system utilizes artificial neural networks to recognize various types of defects in sanitary sewer pipelines. The framework of this system includes modification of digital images for preprocessing, image feature segmentation, utilization of multiple neural networks for feature pattern recognition, and the fusion of multiple neural networks via the use of fuzzy logic systems.     

一种结合模拟退火算法的BP网络冷连轧参数预报模型

 用神经网络模型代替传统的数学模型,达到提高轧制参数预报精度的目的。在分析了轧制原理的基础上设计了神经网络冷连轧参数预报模型,并针对前向网络反向传播算法（BP）收敛速度缓慢和易陷入局部极小点的缺点,将有全局寻优特性的模拟退火算法（SA）与之结合得到具有较快收敛速度和较高逼近精度的神经网络轧制参数预报模型,提高了网络的快速性和精确性。最后以轧制力预报为例,证明了该方法收敛速度快,稳定性好,可信度高,具有较好的应用前景。     

Optimization Modeling for Sewer Network Management

Due to their low visibility, sanitary sewers' condition assessment and rehabilitation are frequently neglected until a catastrophic failure occurs. Neglecting regular maintenance of these underground utilities adds to life-cycle costs and liabilities, and in extreme cases causes stoppage or reduction of vital services. A systematic approach for the determination of deterioration of sewer systems and an integrated management system are necessary to fully understand the complete status of this underground infrastructure system. This paper discusses the major aspects of integrated management for sewer systems, namely, the development of network identification, sewer classification and sewer condition rating systems, sewer deterioration mechanisms, prediction modeling, and the use of optimization techniques for maximizing benefit∕cost ratios over a planning horizon. A case study, based on large combined sewers from the city of Indianapolis, has been used to demonstrate the use of the framework of this integrated life-cycle based sewer management system. Deterministic dynamic programming is employed to identify appropriate sewer rehabilitation techniques at different stages during the planning horizon adopted for the sewer systems.     

Hydraulic Performance Index of a Sewer Network

An objective methodology is proposed for evaluating the hydraulic performance for possible rehabilitation of sewer systems. It involves assigning a hydraulic performance index to each pipe section. This hydraulic index reflects both the local surcharge in a pipe and the surcharge induced at upstream sections of the same branch in a sewer network. The hydraulic index also takes into account the vulnerability and the retention capacity of each pipe section. This index may be used directly to establish the rehabilitation priority of different sections to maximize hydraulic performance for the entire network. This methodology was successfully applied to the sewer system of the city of Laval in Canada. The results show how pipe dimensions and locations have the effect of surcharging or relieving a pipe network and how the hydraulic performance index adequately rates the contributions of sewer network components.     

Comparison of Statistical Deterioration Models for Water Distribution Networks

The use of water main break history as a proxy for condition has become common practice because of the high costs associated with direct assessments. Statistical deterioration models predict future water main breaks on the basis of historical patterns. Many municipalities are beginning to understand the value of utilizing water pipe break histories to manage their noncritical distribution networks via deterioration models. This paper presents a generic IDEF0 process model for developing water main deterioration models. Two common statistical deterioration models for water pipes are compared: rate-of-failure models (ROF) and transition-state (TS) models. ROF models extrapolate the breakage rate for a particular cohort of pipes and do not differentiate between the times between successive failures. On the other hand, transition-state models attempt to model the time between successive failures for pipes. This paper presents a comparison and analysis of ROF models and transition-state models by using a single data set for cast- and ductile-iron pipes in the City of Hamilton, Ontario, Canada. The paper compares the models’ ability to support breakage forecasting, long-term strategic planning, and short-term tactical planning. Best practices for pipe segmentation in support of water main deterioration models are presented.     

Validation of Existing Bed Load Transport Formulas Using In-Sewer Sediment

Granular sediment in pipe inverts has been reported in a number of sewer systems in Europe. Given the range of flow conditions and particle characteristics of inorganic sewer sediments the mode of transport may normally be considered as bed load. Current commercial software for modeling the erosion and transport of sediments in sewer pipes still utilizes well-known, or modified versions of transport equations that were derived for transport of noncohesive sediment in alluvial streams. In this paper the performances of the equations of Ackers and White (originally developed for the transport of river sediments) and of May (derived from laboratory pipe experiments) are examined against two separate data sets. One set is from laboratory erosion experiments on sewer sediment obtained in Paris. A second data set has bed load transport rate measurements recorded in a sewer inlet pipe. The formulas were selected because of their widespread use in the prediction of in-sewer sediment transport both in commercial software and in the latest United Kingdom design guidance for new sewers. The results indicated that both the relationships performed poorly, even in such well-controlled conditions. These formulas have significant difficulties in predicting the erosion thresholds and fractional transport rates for non-uniformly sized in-sewer sediments. An empirical formula to adjust the threshold of motion for individual grain size fractions was developed which significantly improved predictions. Although such techniques have been used in gravel bed rivers, the threshold adjustment function for in-sewer deposits was significantly different from these previously published for fluvial gravels, indicating that a direct transfer of fluvial relationships to sewers may be inappropriate without further research.     

Load Rating and Reliability Analysis of an Aerial Guideway Structure for Condition Assessment

Aerial guideways are elegant transportation structures that are seen at airports, theme parks, and crowded urban areas. The guideways generally consist of continuous, prestressed concrete beam spans, precast concrete columns, and steel beam-column connections. Although there are guidelines prepared as a supplement to conventional highway and railway bridge design codes, aerial guideways form a different class, relatively less studied compared to common highway bridges. The primary objective of this paper is to present a study to better understand the structural behavior and capacity used in an existing guideway structural system which has been in service for about 35?years. The load demand on the guideway system has increased by about 50% over the years. The structural system is composed of six-span continuous prestressed concrete bridge segments. In order to develop models that bound the possible existing condition of the structure, several models are developed by changing the most critical parameters. The critical parameters are categorized as material properties, prestress losses, boundary conditions, and continuity conditions. Sensitivity studies are conducted using eight parametric models for simulations with moving loads for the two different train types. The load rating and reliability indexes are computed for all the cases under different loading conditions. The parameters that have the most influence on the load rating and reliability are also presented. The information generated from these analyses can be utilized for better-focused visual inspection and can also be used for developing a long-term structural monitoring plan.     

Financial Outlay Modeling for a Local Sewer Rehabilitation Strategy

Modern infrastructure systems are highly developed, with considerable capital funding invested in them. While capital is spent on new infrastructure initiatives, the maintenance of the present infrastructure must not be neglected. Increasingly, public agencies are being urged to develop improved systematic methodology for allotting their period budgets more appropriately so that the capacity of the installed infrastructure is more fully utilized and sustained. When planning the allocation of investment funds, multiple objectives may exist that are dependent on the constraints, resources available for construction, and the interrelationships and dependencies among all of the alternatives. This makes the task of planning, prioritizing, and allocating funds a complex exercise. This paper presents a financial outlay model called PRISM, Proactive Rehabilitative Sewer Infrastructure Management, which uses linear programming to optimize allocation of funding for the local sewer network maintained by the City of Edmonton, Canada. By grouping sewer pipes into categories based on parameters of age, diameter, material type, waste types, and average depth of cover, the model provides a mechanism for determining the most appropriate allocation or appropriation of funding given a planning horizon and budgetary constraints.     

Erosion of Sediment Beds in Sewers: Model Development

The problems created by sediment deposits in combined sewer systems (sanitary and storm) are internationally recognized. The loss in conveyance due to these deposits contributes to hydraulic overloading, leading to flooding and premature operation of combined sewer overflows. The washout of sediments through combined sewer overflows into urban water courses during times of storm and the associated pollution caused by this phenomenon may be a factor affecting many urban ecosystems. Based on field observations, coupled with sampling and analysis of combined sewer sediment deposits, it has been found that in the invert of pipes there is often coarse, loose, granular, predominantly mineral material overlain by a mobile, fine-grained deposit. The erosion of the latter type of deposit is considered to be the source of the “first foul flush” of pollution, which is observed in many sewerage systems in response to storm events. This paper describes an experimental laboratory investigation of the erosion and subsequent suspended sediment transport of an in-pipe, fine-grained, organic, cohesive-like sediment deposit analogous to those found in sewers. The development of the laboratory system, the test program, the results of the study, and the development of a new approach to model the erosion and transport of cohesive-like sediments in pipes are described. Conclusions regarding the importance of the structure of the bed and its erosional behavior under a wide range of time-varying hydraulic conditions are presented.     

Effect of Biofilm Formation on Roughness Coefficient and Solids Deposition in Small-Diameter PVC Sewer Pipes

The purpose of a sanitary sewer is to carry the peak discharge at the end of the design period, and to transport suspended materials under all flow conditions to prevent deposition of solids, and hence, sewer blockages. To accomplish the latter, the liquid must provide for sufficient shear stress to suspend and transport the particles along the sewer. Published design criteria for critical shear stress in sanitary sewers vary significantly. However, the effect of biological film development on the internal pipe surface has been neglected. Experiments conducted utilizing a pilot-scale sanitary sewer installed in the Hydraulics Laboratory at the University of New Orleans, La., provide evidence that the shear stress to move particles of a given size is independent of slope and pipe diameter, but does depend on the effect of biological film on increasing the roughness coefficient. This critical shear stress, to achieve self-cleansing in sanitary sewers, was found to be in the range of 1.1–1.4?N/m2, depending on the integrity of the biofilm. Based on this principle, a design procedure applicable to small-diameter PVC pipes with slopes between 0.1 and 0.5% was developed.     

高炉小模块非金属冷却壁设计参数

小模块冷却壁是将性能优异的耐火材料直接浇铸在平行排列的冷却水管上而形成的一种新型冷却设备。采用ANSYS软件建立了小模块冷却壁温度场计算模型,利用该模型计算了炉气温度为1200~1600℃、冷却水流速为0.5~2.5m/s条件下壁体材质导热系数、水管材质、水管直径、水管间距、冷却水流速及工作环境温度等条件变化时小模块冷却壁的温度分布状况。结果表明,小模块冷却壁对炉气温度变化的适应能力较强,壁体材质导热系数、水管间距、壁体厚度对小模块冷却壁传热性能影响较大,而水管直径、水管材质及水流速的影响较小。     

Focal calvarial bone lesions. Comparison of logistic regression and neural network models

RATIONALE AND OBJECTIVES: To assess the accuracy of logistic regression (LR) and artificial neural networks (NN) in the diagnosis of calvarial lesions using computed tomography (CT) and to establish the importance of the different features needed for the diagnosis. METHODS: One hundred sixty-seven patients with calvarial lesions as the only known disease were enrolled. The clinical and CT data were used for LR and NN models. Both models were tested with the leave-one-out method. The final results of each model were compared using the area under receiver operating characteristic curves (Az). RESULTS: Of the lesions, 73.1%, were benign and 26.9% were malignant. There was no statistically significant difference between LR and NN in differentiating malignancy. In characterizing the histologic diagnoses, NN was statistically superior to LR. Important NN features needed for malignancy classification were age and edge definition, and for the histologic diagnoses matrix, marginal sclerosis, and age. CONCLUSION: NNs offer wide possibilities over statistics for the study of calvarial lesions other than their superior diagnostic performance.     

Loading of a Gravel-Buried Steel Pipe Subjected to Rockfall

Increasing rockfall activity in the European Alps has raised the need for designing protection systems for Alpine infrastructure. This paper is concerned with protection of steel pipelines by a gravel overburden of height H. Rockfall-induced loading of such pipes is estimated by means of a three-dimensional, quasi-static, elasto-plastic finite-element (FE) model. Maximum impact forces F and corresponding penetration depths w are estimated based on dimensionless formulas, related to real scale impact tests onto gravel layers. The forces F are applied as surface loads onto the FE model, at a distance (H?w) from the pipe. Material behavior of gravel is represented by a cap model, which is based on pressure-independent linear elasticity and associated plasticity. Related material parameters are identified from acoustic and static material tests. The structural FE model is validated by comparing FE-predicted stresses in the pipe with stresses determined in a real-scale structural experiment. This is reasonable only because the real-scale test is independent of the experiments used for identification of the material parameters used as input for the structural FE model. Satisfactory FE predictions motivate use of the FE model for estimating the loading of the steel pipe in untested scenarios, concerning, e.g., different heights of overburden, or different impact intensities. These estimates show some efficiency of gravel protection systems for modest rockfall, with impact energies well below 3,500?kJ.