Cao, Bo

Dr. Bo Cao is a Water/Wastewater Assistant Project Manager at STV and a licensed Professional Engineer in Texas, with five years of specialized...

Joined:

About Cao, Bo

Dr. Bo Cao is a Water/Wastewater Assistant Project Manager at STV and a licensed Professional Engineer in Texas, with five years of specialized experience in the water and wastewater sector. He has been instrumental in developing advanced infrastructure analytical platforms for the Consent Decree as part of the wastewater digital transformation. Dr. Cao's expertise includes wastewater system master planning, risk-based asset management for lift stations, wastewater treatment plants, and collection systems. He excels in wastewater hydraulic modeling, data analysis and management, treatment plant process analysis, and lift station design. For the past five years, Dr. Cao has been an integral part of the City of Houston planning group as a staff augmentation, where he has been acknowledged as a key contributor to projects tied to the Consent Decree.

Cao, Bo

Titles from this speaker

Data Centric "Smart" Digital Platform for Wastewater Treatment Plant Proactive Optimization and Maintenance

Abstract

Managing utilities operations effectively in the era of big data involves application of emerging technologies, tools, and modern practices. Houston's in-house Wastewater Infrastructure Planning team incorporates technological advancement in its daily operations. The City of Houston (COH) is the largest city in the state of Texas and the fourth largest city in the United States of America. Houston Water owns and operates 38 Wastewater Treatment Plants (WWTPs) with a combined permitted capacity of 564 MGD. The wastewater collection system includes approximately 6,000 miles of sewer pipes, 133,000 manholes, and approximately 380 lift stations spread out over 665 square miles area to serve about 2.3 million customers. Wastewater treatment plants (WWTPs) have long played a crucial role in safeguarding both the environment and public health. The conventional practices of operation and maintenance (O&M) within WWTPs have been predominantly reactive in nature. This reactive approach has created challenges for site staff operating in the field, as they grapple with noisy Supervisory Control and Data Acquisition (SCADA) systems and information overload. This often results in decisions being based on gut instinct rather than data-driven insights. In this context, plant operators typically become aware of issues only when equipment fails or performance reviews uncover underperformance, leading to a reliance on lagging performance indicators and a heavy focus on troubleshooting rather than proactive modeling and operations. To ensure the long-term sustainability and effectiveness of wastewater treatment plants, decision-makers require real-time visibility into plant operations with leading performance indicators that can enable them to optimize performance in a proactive manner. The harnessing of near real-time data from sensors, SCADA systems, IoT devices, and Work Order Management Systems presents an opportunity for WWTP operators to comprehensively understand their systems' performance using innovative digital tools that simplify rather than complicate their daily tasks. Over the past decade, COH has undergone a digital transformation of its wastewater management system. COH has developed an Advanced Infrastructure Analytics Platform (AIAP) which includes all data and analytics needed for wastewater infrastructure planning. This presentation discusses an early initiative by the planning team of COH aimed at developing a Data-Centric 'Smart' Operations and Maintenance platform. This approach begins with the essential step of integrating multiple databases or systems to gain a holistic understanding of the entire WWTP operation and maintenance landscape. In line with the City's Strategic Asset Management framework, this integration brings together the WWTP SCADA, HachWims, Work Order Management System, and Asset's Physical Attributes and Conditions into a unified system. This fundamental integration enables analysts to empower stakeholders to comprehend the status of WWTP operations and maintenance from multiple perspectives. The next critical step involves the development of comprehensive O&M Key Performance Indicators (KPIs) that serve as vital metrics for monitoring system performance. These KPIs, derived from the integrated databases, enable operators and decision-makers to assess the overall health of the WWTP system accurately. To transition towards a proactive mode of operation, advanced analytics and predictive machine learning algorithms are deployed to forecast influent characteristics. These forecasts, combined with real-time data from sensors and the SCADA system, allow for dynamic adjustments to energy consumption, chemical usage, and other operational KPIs. This dynamic approach ensures compliance with environmental regulations while enhancing operational efficiency. Moreover, a machine learning model developed based on the Work Order Management System enables predictive maintenance. It anticipates equipment failures, enabling maintenance teams to address issues before they escalate into costly breakdowns. By embracing proactive operation and maintenance, the integrated approach optimizes resource allocation across the board. This would eventually include personnel scheduling, chemical dosing, and various other aspects of WWTP operations, resulting in substantial cost savings. In conclusion, this presentation underscores the transformative potential of data-centric O&M for WWTPs. By adopting proactive strategies grounded in real-time data and predictive analytics, WWTPs can significantly enhance their efficiency, reduce operational costs, and bolster environmental stewardship. The transition towards data-centric O&M is a crucial step towards ensuring the long-term sustainability and effectiveness of wastewater treatment plants, positioning them as integral components of smart, forward-thinking cities. The tasks identified below are some examples of lesson learned:

*Collaborate with the WWTPs operation team to grasp the challenges and requirements for proactive optimization and maintenance.

*Understand, structure, and establish data systems to facilitate data modeling and integration.

*Utilize Business Intelligence tools such as Power BI and Python for exploratory data analysis and visualization.

*Develop data pipelines for seamless automatic data updates and document procedures to enhance digital transformation effectiveness.

Houston's wastewater planning adopts a data-driven approach, integrating various systems for a comprehensive operational view. Key Performance Indicators (KPIs) are utilized for precise performance evaluation. A machine learning model predicts influent characteristics, enabling proactive WWTP operations. This data-centric strategy optimizes resource use, enhances efficiency, and reduces costs.

SpeakerCao, Bo

Presentation time

14:30:00

15:00:00

Session time

13:30:00

15:00:00

SessionAutomation and Analysis: Data-Driven Strategies Improve Utility Processes

Session number610

Session locationRoom 349

TopicAsset Management, Business Organization and Technology Transformation, Intelligent Water, Intermediate Level

Author(s)

Cao, Bo, Paudel, Pratistha, Baldwin, Jennifer, Rabbi, Fazle

Author(s)B. Cao1 P.P. Paudel2, F. Rabbi3, J.D. Baldwin4, F. Rabbi3, P.P. Paudel2

Author affiliation(s)1STV, TX, 2Burns & McDonnell, TX, 3City of Houston, TX, 4Jacobs Solutions Inc., TN

SourceProceedings of the Water Environment Federation

Document typeConference Paper

PublisherWater Environment Federation

Print publication date Oct 2024

DOI10.2175/193864718825159675

Volume / Issue

Content sourceWEFTEC

Word count14

Base text size -

Cao, Bo

Site admin

About Cao, Bo

My Recent Activity