Water supply systems in the United States connect raw water sources to hundreds of millions of water consumers through humongous infrastructure that include approximately one million miles of buried water mains and service connections and thousands of treatment facilities and appurtenances. This enormous set-up is currently operated by more than 170,000 public water systems. Sustainability of the water supply system faces several imminent challenges such as: 1) increasing water main breaks, 2) decreasing fresh water resources, 3) untraceable non-revenue water use, and 4) increasing water demands. However, current water supply management practices are not capable of providing fundamental solutions to the issues identified above. Big Data is a new technical concept to collect massive amounts of relevant data from sensors installed to monitor structural condition, usage, and system performance. This Big Data concept can be realized by deploying Internet of Things (IoT) technology throughout the water supply infrastructure and consumers’ usage. This paper presents a schematic development of IoT application for Big Data collection through a myriad of water clients. The scheme consists of downstream and upstream data collection using Wireless Sensor Network (WSN) technologies connecting to IoT. Downstream data shall provide water usage and performance data to clients and upstream data is similar to traditional SCADA and Automated Meter Reading (AMR) systems. Ultimately, all data will be converged to build a Big Data collection system where data mining identifies 1) local and system performances including pressure and flow, 2) non-revenue and illegitimate water consumption, and 3) locations and quantity of water breaks and water losses. The goal of this development is to enable both utilities and consumers to proactively manage their water usage and achieve higher levels of sustainability in water supply

With the accelerated construction and aging of underground oil and gas pipelines, trenchless technology (TT) has developed rapidly in recent years. This paper briefly introduces the trenchless installation, repair (rehabilitation), replacement, and cleaning technologies that can be used for oil and gas pipelines. Advantages, limitations, technical features, and application scopes are summarized to provide a basis for construction method selection. In addition, this paper collects twenty standards related to trenchless construction technology for oil and gas pipes, so as to quickly identify the standards to be referenced before construction. Finally, this paper analyzes the market for TT and presents key technical gaps.

For the residual strength prediction of corroded pipelines, the existing standard has a small application range, and the finite-element method has too many assumptions. This paper proposes a new data-driven prediction framework. Firstly, principal component analysis (PCA) is used to reduce the dimensions of the existing data to determine the input-output structure of the prediction model. Secondly, support vector machine (SVM) based on multiobjective optimization is employed to predict the pipeline’s residual strength. Compared with the traditional estimation methods, the model proposed in this paper is data-driven and combines data dimension reduction, multiobjective optimization, and a machine learning model. In addition, the accuracy and stability of the model are considered in the multiobjective optimization. The proposed framework is tested in a pipeline burst pressure data set. The results indicate that the mean absolute percentage error of the proposed models ranges from 1.353% to 3.220%, which has good prediction accuracy and stability. This paper also discusses the influence of the multiobjective optimization algorithm and dimension reduction on the prediction model. The following primary conclusions are drawn: (1) SVM optimized by multiobjective optimizer performs better than SVM optimized by the single-objective optimizer, and the original SVM performs worst, and (2) reducing the raw data dimensions can improve the residual strength prediction performance for corroded pipelines reduce the complexity of the model, and shorten the calculation time.