|
January 2011
ADMi Develops Advanced Inferential Sensor Software for Real-Time Quality Control of Water-Level Data for the US Geological Survey Everglades Monitoring
The Everglades Depth Estimation Network (EDEN) is an integrated network of real-time water-level gauging stations, ground-elevation models, and water-surface models designed to provide scientists, engineers, and water-resource managers with current (2000–present) water-depth information for the entire freshwater portion of the greater Everglades. The USGS supports EDEN in order to provide quality-assured hydrologic data for the U.S. Army Corps of Engineer’s Comprehensive Everglades Restoration Plan.
A technology often used for industrial applications is the “inferential sensor.” Rather than installing a redundant sensor to measure a process, such as an additional water-level gage, an inferential sensor, or virtual sensor, is developed that makes very accurate estimates of the process measured by the hard sensor. The advantage of an inferential sensor is that it provides a redundant signal to the sensor in the field but without the environmental threats (floods or hurricanes, for example) and the cost of additional sensors. In the event that a gage does malfunction, the inferential sensor provides an accurate estimate for the period of missing data. The inferential sensor also can be used in the quality assurance and quality control of the data. The virtual signal can be compared to the real-time data and if the difference between the two signals exceeds a certain tolerance, corrective action can be taken..
The inferential sensor developed by ADMi provides an automated process for identifying errors in water-level data and provides an estimate for missing or erroneous water-level data. The development and application of inferential sensors is easily transferable to other real-time monitoring networks.
August 2009
The Water Environment Research Foundation recently published, along with the International Water Association, the report, Feasibility Testing of Support Systems to Prevent Upsets. This report was co-authored by Advanced Data Mining working with Black and Veatch and Virginia Tech.
As described in WERF’s Executive Summary: “The goal of this decision support system (DSS) project was to determine the feasibility of support systems to prevent upsets caused by chemical/biological/radioactive contaminants (C/B/R) introduced upstream of the wastewater treatment plant (WWTP). Decision support systems (DSS) are an amalgamation of functions (designed to assist operators) such as monitoring, anomaly detection, machine learning, situational awareness, and remediation. The research team developed and tested a DSS prototype for the prediction of contamination events at WWTPs. They reviewed available technologies and, using examples of DSS software, provided guidance in the development of a DSS module. The research team reviewed upset event support systems and anomaly detection technologies used for industrial and computer network security. Real-time information collected by conventional sensors/analyzers (measuring pH, conductivity, temperature, alkalinity, dissolved oxygen, etc.) was subjected to advanced data mining techniques to predict the experimentally simulated toxic shock. This anomaly detection approach will aid WWTP operators in executing remedial actions following the detection of an upset event.
The report also describes the experimental testing of the DSS on data collected by online sensors and analyzers specific to the wastewater industry.”
An Executive Summary is available from WERF. Due to its sensitive nature, the Final Report will only be available through Water ISAC.
May 2009
ADMi and USGS Contract with Water Research Foundation and Beaufort Jasper Water and Sewer Authority
ADMi, along with the South Carolina Water Resources office of the US Geological Survey, have contracted to perform research on a Tailored Collaboration Project sponsored by the Water Research Foundation and member utility Beaufort-Jasper Water and Sewer Authority (BJWSA). The service area for BJWSA is Beaufort and Jasper Counties along the southeastern coast of South Carolina. The drinking water intake for BJWSA is in the tidally affected portion of the Lower Savannah River.
However, in a broader context, the focus of this project is on assessing the potential impacts of global climate change on salt-water inundation of the water intakes of coastal utilities in South Carolina, and to create an example process to be followed by other coastal utilities for assessing their exposure to this risk. According to the 2001 Southeast Regional Climate Assessment, over the next 30 years the Carolinas are expected to see average air temperatures increase by approximately 1˚C (1.8˚F); overall precipitation levels are expected to increase with seasonal changes within the precipitation regime; and sea levels will increase 11-40 cm.
April 2009
ADMi Contracts with the Water Research Foundation
The Water Research Foundation, the preeminent national research agency for drinking water utilities, award a contract to ADMi for the project “Interpreting Real-Time Online Monitoring Data for Water Quality Event Detection”. The objective of this project is to “develop a universal and reliable system for analyzing and interpreting real-time online monitoring data from drinking water distribution systems. The event detection system will integrate existing water quality sensor and hydraulic data, as well as operational information, to effectively identify water quality abnormalities while minimizing false alarms”. ADMi also successfully completed Water Research Foundation Project 3086 “Decision Support System for Water Distribution System Security”. It focused on protecting distribution systems from inadvertent or deliberate toxic contamination.
The partner utilities represent different source water quality extremes and treatment processes, and together operate 47 real-time, multi-parameter monitoring sites, including many that have operated longer than 5 years. ADMi can leverage this vast amount of data because it is highly expert at large-scale, real-time data mining projects, AI, and commercial software development; and is highly experienced in water systems research.
June 2008
ADMi contracts with Fort Collins, CO Water Treatment Utility
The City of Fort Collins, CO is located about an hour north of Denver and at the foot of the Rocky Mountains. Much of its water is from snowmelt, which can change qualities dramatically over short time periods. Fort Collins has asked ADMi to apply advanced data mining to determine how to optimize water treatment under rapidly changing water quality conditions. As Fort Collins is a member of the Partnership for Safe Water, their goal is to ensure consistently high water quality and optimized chemical addition and filtration.
April 2008
Hydrologics, Inc of Columbia, MD has awarded a research project to Greer, SC-based Advanced Data Mining International, LLC (ADMI). The project will apply artificial neural network models to predict the quality of public water supplies in New York State.
HydroLogics provides worldwide consulting services for water supply and hydroelectric systems, computer-aided dispute resolution, and water marketing. ADMI provides advanced data mining software, artificial intelligence computer programs and research services to utilities, manufacturers, environmental organizations, and oil and gas companies.
March 2008
National Research Foundation Announces Report on Water System Homeland Security Monitoring Prepared by Greenville, SC Firm
American Waterworks Association Research Foundation (AwwaRF), the leading nonprofit water research foundation dedicated to advancing the science of drinking water, announced the publication of a new report on the critical topic of monitoring drinking water systems for homeland security. The principal research for this project was conducted by the engineering firm, Advanced Data Mining International, LLC (ADMi) of Greenville, SC, and funded by AwwaRF and the Charleston (SC) Water System.
Many drinking water utilities face an increasing array of critical challenges, but none more critical as protecting drinking water supplies from either intentional or inadvertent contamination. The advances of this seminal research work include being able to detect chemical contamination in drinking water using a combination of artificial intelligence and conventional sensors such as pH, conductivity and chlorine.
“The objective of this research is to demonstrate to water utilities and their engineering firms advanced technical and cost-effective solutions to homeland security monitoring," stated John B. Cook, CEO and engineer for ADMi. "This research demonstrates that a combination of reliable sensors presently available, when analyzed using artificial intelligence technology, can detect sub-lethal concentrations of toxins," according to Ed Roehl, ADMi's CTO and engineer. Due to the sensitive nature of the subject material, the report is currently available only to subscribers of AwwaRF under a condition of non-disclosure
May, 2006
The American Waterworks Research Foundation to Publish Report by Advanced Data Mining International and Others
The American Waterworks Research Foundation (AwwaRF) will publish in early July of this year a comprehensive research report prepared by ADMi principal investigator’s Ed Roehl and John Cook and co-author and software developer, Ruby Daamen. In addition to ADMi, other participants include the Charleston Water System and Colorado State University, The report will be entitled Distribution System Water Quality Security and Improvement through Data Mining.
The objective of the research was to demonstrate that conventional sensors (or monitors) such as pH, conductivity and chlorine, could be used in conjunction with data mining techniques such as artificial intelligence to alert water treatment plants of potential contamination by highly toxic chemicals. The results of the research, which involved Charleston Water System and other nationally-recognized water utilities, confirmed the research thesis.
This represents a major improvement to water distribution system monitoring for detection of contaminants.
It is expected that AwwaRF will publish the report in July 2007, which will also contain a demo of a computer program to assist operators on how to interpret real-time data from multiple monitoring locations.
December, 2006
ADMi Welcomes John B. Cook as CEO
John B. Cook has joined ADMi as Chief Executive Officer. John has thirty years of environmental engineering and utility experience in the areas of management, water and wastewater operations and process optimization, design and construction, and research. John is a registered Professional Engineer with a Bachelor of Science in Civil Engineering as well as a Master of Science in Structures and Mechanics, and a Master of Science in Environmental Engineering.
| 
