Efficient leak detection and localization in water distribution networks (WDNs) are essential for mitigating disastrous losses from leak incidents. Current unsupervised learning-based methods excel in detecting single leaks but struggle with multi-leak scenarios, limiting their practical applicability. Additionally, leak localization methods relying on simulation optimization can be computationally intensive for large-scale WDNs. Meanwhile, purely data-driven approaches struggle to leverage network topology and hydraulic characteristics, hinde ring accurate leak localization. To address these challenges, we propose a leak detection and localization framework that employs online change-point detection and leak sensitivity modeling to achieve real-time detection and localization in multi-leak scenarios. For leak detection, the framework utilizes an unsupervised One-dimensional Convolutional Auto-encoder (1D-CAE) to reconstruct the pressure data collected from sensors deployed over a WDN. The residuals between the reconstructed values and the observed values, also known as reconstruction errors, are then analyzed using a Sequentially Discounting Normalized Maximum Likelihood (SDNML) change-point detector. Equipped with a customized scoring function designed for robust multi-leak detection, this detector computes anomaly scores in real-time at each time step, facilitating effective leak detection. Furthermore, we simulate leaks at different nodes of the WDN to quantify their impact on the sensor nodes using pressure residuals-based leak characteristic factors. By comparing reconstruction errors with these factors, we identify the nodes that best match the current leak event, achieving precise leak localization. An evaluation on the L-Town dataset demonstrates the superior performance of our method for multi-leak detection and localization.

Internet-based control is a way of using the internet as a platform for remote monitoring and control operation. The obvious benefit is to enable remote monitoring and maintenance of process plants and to initiate global collaboration and data sharing between operators from geographically dispersed locations. However, connection to an open network and the use of universal technology present high safety and security risks to the new generations of control systems. Are we opening up our internet-enabled control systems for trouble since a number of malicious hackers continually attack web servers on the internet? The new type of control systems will never be accepted by industries if people do not have enough confidence in their safety and do not feel secure by using the system. This paper presents a framework of security and safety checking, used in the design of internet-based control systems. Based on the existing measures of physical and network securities, such as firewall and comprehensive user-authorised access control, the framework proposed in this paper focuses on the security of control commands transferred over the internet, responding actions to malicious attacks and system safety. An internet-based control system for a process rig is used as a case study to illustrate the implementation of the framework.

One of the major challenges in Internet-based control systems is how to overcome the Internet transmission delay. In this paper, we investigate the potential of using the multirate control scheme and the time-delay compensation to overcome the Internet transmission delay. A two-level hierarchy is used for the Internet-based control systems. At the lower level, a local controller is implemented to control the plant at a higher frequency. At the higher level, a remote controller is employed to remotely regulate the desirable set-point at a lower frequency for the local controller. A compensator located at the feedback channel is designed to overcome the time delay occurring in the transmission from the local site to a remote site. Another compensator in the feedforward channel is designed to compensate the time-delay occurring in the control action transmission. The simulation and experimental application results illustrate that the multirate control scheme with the time delay compensation offers a promising way to efficiently reduce the effect of Internet time delay on control performance

This paper explores the idea of determining the sink node location in wireless sensor networks by applying genetic algorithms. Sink nodes play an important role in and are cluster centers of wireless sensor networks. Optimal location of sink nodes can save transmission energy and improve the transmission speed. Many obstacles in the application scene may prevent the sink nodes to be located in certain places. By applying a genetic algorithm the location optimization problem of the sink nodes is formed with the obstacles in the scene as a constraint. The simulation results show that employing multiple sink nodes in a sensor network would significantly increase the lifetime of the sensor network and the environment of the application scene can be properly considered in the determination of the sink node locations.

Intelligent home environments are one of the major application areas of pervasive computing. Safety and security are two most important issues in the remote monitoring and control of intelligent home environments. This article takes safety and security into consideration together and proposes a phone-out-only policy for ensuring security and virtual home environments for safety. A remote monitoring and control system for a security camera is used to illustrate the new methodologies for safety and security. By using the demonstration system people are able to easily monitor and control a security camera, central heating, microwave oven and washer from anywhere by using mobile phones. Our system distinguishes from the existing DTI (Department of Trade and Industry in the UK) next wave technologies and a few of on-going EU projects in the ways of dealing with safety and security and its simplicity. Remote monitoring and control of intelligent home environments can be of great benefits to the working families and holiday makers and has a great commercial potential.

Abstract This paper describes an approach for the integration of control system software design, testing, and implementation over the Internet using the Java and Jini technologies. Process models and control systems are remotely designed and tested in a virtual laboratory (also called the virtual world), and then implemented in a physical plant (also called the real world) through an integrated environment. Although control system and process model designers and real‐site operators are geographically dispersed they work together as a team over the Internet to provide the maintenance support to all the authorized industrial processes. As a consequence, time and money can both be saved because there is no need for an expert of the control software supplier to travel to the site of the real plant and conduct on‐site implementation. A generic control system life cycle model is presented first in this paper. Then three enabling technologies including Java, Jini and WWW are briefly introduced. Taking advantage of the Java, Jini and WWW technologies, an Internet‐based general infrastructure is proposed to remotely facilitate process modelling, control system design, simulation, validation and on‐site implementation. An integrated environment is established to implement the infrastructure. A water tank with a liquid level control system is refereed as a case study to illustrate how the prototype of the integrated environment works over the Internet. Further work and the conclusions are given at the end. Copyright © 2003 John Wiley & Sons, Ltd.