Unpacking the Black Box: Understanding and Using Advanced Data - - PDF document

▶
unpacking the black box understanding and using advanced
SMART_READER_LITE
LIVE PREVIEW

Unpacking the Black Box: Understanding and Using Advanced Data - - PDF document

May 15, 2023 187 likes •687 views

7/23/2020 1 Unpacking the Black Box: Understanding and Using Advanced Data Analytics to Optimize Operations Thursday July 23, 2020 1:00 3:00 PM ET 2 1 7/23/2020 How to Participate Today Audio Modes Listen using Mic

slide-1
SLIDE 1

7/23/2020 1

Unpacking the “Black Box”: Understanding and Using Advanced Data Analytics to Optimize Operations

Thursday July 23, 2020 1:00 – 3:00 PM ET

1 2

slide-2
SLIDE 2

7/23/2020 2

How to Participate Today

  • Audio Modes
  • Listen using Mic &

Speakers

  • Or, select “Use

Telephone” and dial the conference (please remember long distance phone charges apply).

  • Submit your questions

using the Questions pane.

  • A recording will be

available for replay shortly after this webcast.

Today’s Presenters

  • Mark Harris, Town of Hillsborough, Ca. (Moderator)
  • Dr. Andrew Shaw, Black & Veatch
  • Advanced Data Analytics
  • Richard Loeffler IV

, EmNet

  • Case Study: Real Time Decision Support Systems (RT-DSS)
  • Ryan Sanford, P.E., DHI
  • Digital Twin Solution & Case Study
  • Andy Crawford, Woodard & Curran
  • Operator Rounds: Real Time Analytics To Give Perspective

3 4

slide-3
SLIDE 3

7/23/2020 3

Global Practice & Technology Leader

  • Dr. Andrew Shaw

Advanced Data Analytics

Introduction

5 6

slide-4
SLIDE 4

7/23/2020 4

Outline

  • Get M.A.D.
  • Data Integration
  • Digital Twins

Get M.A.D.

8

7 8

slide-5
SLIDE 5

7/23/2020 5

Get M.A.D.

Measure Decide Analyze

9 10

The important thing about

measuring is

to give you feedback

9 10

slide-6
SLIDE 6

7/23/2020 6

The important thing about analysis is to make sure you understand deeply

Without it you are roaming in the dark Without it you decide poor things To many it seems difficult When you succeed in solving the puzzle it is a great sentiment

11 12

The important thing about decisions is that you make them before you must To lead is to make right-minded decisions To react is to wait until only one option is available Your largest obligation is to make good decisions that are serving the common good

11 12

slide-7
SLIDE 7

7/23/2020 7

DATA INTEGRATION

13

Strategic level Plant‐wide control level Unit control level Control loop level

Automatic control Automatic or manual control Operational decision making Strategic decision making

Seconds/minutes Minutes/hours Hours/weeks Years/decades

DIFFERENT TIMESCALES FOR DECISIONS

14

13 14

slide-8
SLIDE 8

7/23/2020 8

Seconds Minutes Hours Days Months Years

Single signal analysis

  • Filtering
  • Outlier detection
  • Repairing datasets
  • Statistical process control

Mathematical models

  • Linear regression
  • Multivariate regression
  • Diagnosis
  • Simple dynamic models
  • Hydraulic models
  • Biological reaction models

Performance indicators

  • KPI
  • Benchmarking

ANALYTICAL TOOLS

15

BUILDING AN INTEGRATED APPROACH

  • Leverage same assets

across more than one application, especially for: – Connectivity – Analytics

  • Data layer and analytics

capabilities aggregated in center of solutions

DATA HUB

LIMS SCADA CMMS MODELING ENERGY NOAA GIS MDM BUSINESS SYSTEMS 16

15 16

slide-9
SLIDE 9

7/23/2020 9

BRAINSTORMING DATA SILOS

17

17

  • Gathers, filters and

analyzes plant data

  • Identifies

emerging issues

  • Quantifies the cost

and risk

  • Makes

recommendations for corrective action

MONITORING & DIAGNOSTIC CENTER

18

17 18

slide-10
SLIDE 10

7/23/2020 10

19

DIGITAL TWINS

20

Digital Twins in the Water Sector

“A Digital Twin can be defined as an integrated accurate digital representation of our physical assets, systems and treatment processes. It will unlock value by enabling improved insights that support better decisions, leading to better outcomes in the physical world”.

19 20

slide-11
SLIDE 11

7/23/2020 11

21

User based decision support via a digital twin

22

Example Use Cases Across the Asset Lifecycle

21 22

slide-12
SLIDE 12

7/23/2020 12

+1 913-980-63187 ShawAR@bv.com @AndyRShaw2000 AndyRShaw

  • Dr. Andrew Shaw

Case Study:

Real Time Decision Support Systems (RT-DSS)

23 24

slide-13
SLIDE 13

7/23/2020 13

Beth Goldstein

  • Principal
  • HydroConsult Engineers

Speakers

  • Client Solutions Manager
  • EmNet, a Xylem brand

Richard Loeffler IV

What’s RT-DSS

Computer-based information system that assists in decision-making activities in real time.

  • process collection system and watershed data,
  • approximate the impact of rainfall,
  • evaluate and optimize operational strategies

Combined, these can provide real-time operational recommendations to operators.

25 26

slide-14
SLIDE 14

7/23/2020 14

What’s RT-DSS What’s RT-DSS

Data Model GUI

Human

Self Learning Hydraulic Model Level and Flow Rainfall WQ Ultimate Decision Maker Data becomes Information

27 28

slide-15
SLIDE 15

7/23/2020 15

“Glass Box” Implementation “Glass Box” Implementation

  • Co-design and Collaboration
  • Open Modular Architecture
  • Sensor/Model Agnostic
  • Operations focus
  • Leverages Investments
  • Real Time Decision

Support Framework

29 30

slide-16
SLIDE 16

7/23/2020 16

Turn on the Lights!TM Data + Model Integration

31 32

slide-17
SLIDE 17

7/23/2020 17

Data + Model Integration = Predictions

20 40 60 80 100 120 3/22/2018 0:00 3/22/2018 6:00 3/22/2018 12:00 3/22/2018 18:00 3/23/2018 0:00 3/23/2018 6:00 3/23/2018 12:00 3/23/2018 18:00 3/24/2018 0:00 Flow (mgd)

Measured Upstream Flow Forecasted Upstream Flow

Recommend + Act

33 34

slide-18
SLIDE 18

7/23/2020 18

Applications:

  • Enhance information re: what’s happening in the

collection system

  • Reduce sewer overflows (wet & dry weather)
  • Maximize storage and conveyance in collection system
  • Predict peak WWTP flow timing to balance out diurnal

flows

  • Provide operational decision recommendations

Coordinated Decision Support

CSO 30: “I’m about to overflow! I need to buy capacity!” Storage Tank: “I’ve got lots of room. My price is $2 per gallon” . Interceptor: . “I’m about half full. I’ve got capacity at $3 per gallon” . Storage Tank: “I’m filling up quickly. I’ve got capacity at $3.50 per gallon”

35 36

slide-19
SLIDE 19

7/23/2020 19

Coordinated Decision Support

CSO 30: “Done!” Storage Tank: “Deal!”

Outcomes – South Bend, IN

37 38

slide-20
SLIDE 20

7/23/2020 20

Automated Systemwide Storage

Selected 16 inline storage facility sites based on volume of sewer, impact on overflow reduction, constructability, and LEAF as possible All sites communicate via SCADA and DCS system ~$145M in capital project savings

Automated Systemwide Storage

39 40

slide-21
SLIDE 21

7/23/2020 21

Enhance Data Use + Optimize WWTPs

  • Eliminate SSOs, manage peak flows across 3 main WWTPs
  • Leverage data from 700+ installed sensors and meters
  • Minimize time plants operate near peak capacity (adapt to seasons, capacity)
  • Reduce/eliminate major CIP projects
  • I/I reduction
  • Load balancing for indirect potable reuse system implementation

Wet Weather Storage Activation

  • Full model+data engine
  • Runs 100 sims every 15 minutes
  • Current conditions +/- 12 hours
  • Probabilistic estimage of future flows
  • Comprehensive situational awareness
  • Provides high-level recommendations

Outcomes:

  • Increased continuity of operations
  • Operational knowledge aggregator
  • Training tool for new recruits
  • Forensic analysis

41 42

slide-22
SLIDE 22

7/23/2020 22

Summary

  • RT-DSS represents an open, extensible framework that uses

existing utility assets and information to put more data in front of operators and decision makers.

  • Co-design ensures operations provides critical feedback

necessary for to develop the most impactful tools.

  • Enhanced collection system knowledge can have

watershed scale impacts for collections and treatment assets.

  • Involving all stakeholders in RT-DSS development ensures

the entire team designs the system, and identifies/mitigates all possible challenges and needs.

Thanks for your time!!

Beth Goldstein, PE bgoldstein@hydroce.com Richard Loeffler richard.loeffler@xyleminc.com

43 44

slide-23
SLIDE 23

7/23/2020 23

We’re on a quest

to help solve the world’s toughest challenges in water environments

Mines Groundwater Oceans Coastlines Cities Rivers

Water & Environment, Inc.

Ryan Sanford, P.E. Wastewater Process Engineer

DHI Digital Twin Solution

  • 1. What is DHI’s Digital Twin?
  • 2. Case Study – Viby WWTP
  • Problem
  • Methodology
  • Solution
  • Solution in action
  • Results
  • 3. Enabled by Data Analytics

45 46

slide-24
SLIDE 24

7/23/2020 24

Digital Twin

Three Dimensional Interactions: 1) Company performance models 2) Asset database(s) 3) Model simulations physical systems

Digital Twin- Integration of Cyber and Physical System

47 48

slide-25
SLIDE 25

7/23/2020 25

Digital Twin

Integration of Cyber and Physical System

WWTP Capacity Expansion for under $2M

Advanced Modelling, Real-time Control, and Densified Activated Sludge ______________________________________________________________

Viby WWTP

case study

49 50

slide-26
SLIDE 26

7/23/2020 26

Influent load is rapidly increasing by 33%

Viby WWTP – The Problem

90,000 PE to 120,000 PE

We think it might be possible.

WWTP to be consolidated in 10yrs Tight nitrogen & phosphorus limits

Aarhus Water: “Can the short-term capacity expansion be done for $2M?”

Project Approach

51 52

slide-27
SLIDE 27

7/23/2020 27

Project Approach

WEST Modeling

53 54

slide-28
SLIDE 28

7/23/2020 28

Sidestream Hydrolysis (Bio-P) vs. Extra N/dN Volume (Chem-P)

The solution

55 56

slide-29
SLIDE 29

7/23/2020 29

The solution The solution

57 58

slide-30
SLIDE 30

7/23/2020 30

The solution The solution

59 60

slide-31
SLIDE 31

7/23/2020 31

The solution The solution

61 62

slide-32
SLIDE 32

7/23/2020 32

The solution The solution

63 64

slide-33
SLIDE 33

7/23/2020 33

The solution The solution

65 66

slide-34
SLIDE 34

7/23/2020 34

The solution The solution

67 68

slide-35
SLIDE 35

7/23/2020 35

The solution

Viby WWTP – original design

Denitrification Tanks 4 3 2 1

Sidestream Hydrolysis

Nitrification Tanks 3 2 1

Nitrate Recycle

PE

RAS

69 70

slide-36
SLIDE 36

7/23/2020 36

Viby WWTP – optimized design

Denitrification 4 3 2 1 Nitrification 3 2 1

Nitrate Recycle

PE 5 Carbon N/dN Swing Post Denitrification External and internal NH4 loads determine aeration in N/DN tanks

NH4 load (g/min)

Aeration threshold

71 72

slide-37
SLIDE 37

7/23/2020 37

Post DN Tank nitrate concentration ammonium concentration 73 74

slide-38
SLIDE 38

7/23/2020 38

75 76

slide-39
SLIDE 39

7/23/2020 39

Results!

2019 2020

(13.7 MGD) (30.8 MGD) (5.7 MGD)

Nitrate Profile 2019 2020

77 78

slide-40
SLIDE 40

7/23/2020 40

Ammonium Profile 2019 2020

DIMS.CORE – Advanced Controllers

  • Data assimilation
  • Data Validation

NH4

+

NO3

  • PO4

3-

NH4

+-Set

PI-reg signal nRT Fosfor frigivelse Høj belastning NH4

+

NO3

  • PO4

3-

NH4

+-Set

PI-reg signal nRT Fosfor frigivelse Høj belastning

  • Automated reporting

79 80

slide-41
SLIDE 41

7/23/2020 41

Thank you

Ryan Sanford, PE, Wastewater Process Engineer rkes@dhigroup.com

Water & Environment, Inc.

Andy Crawford Woodard & Curran

  • 10 years experience
  • MS Env. Engineering
  • Licensed Operator; NY, NJ

Asset Management Services Manager

81 82

slide-42
SLIDE 42

7/23/2020 42

Operator Rounds: Real Time Analytics To Give Perspective

Andy Crawford Woodard & Curran

Agenda

  • Rounds – What is it REALLY?
  • Rounds Design
  • Data Collection Tools – Form Applications
  • Leveraging Data – Do more with less

83 84

slide-43
SLIDE 43

7/23/2020 43

About Us

  • Woodard & Curran is an integrated engineering,

science, and operations company servicing public and private clients nationwide.

PEOPLE

45 1,000+

PLANTS

Rounds – What is it REALLY?

  • Appearance, Color, Smell
  • Measure
  • Trust but Verify
  • Inspection
  • Maintenance
  • Process

85 86

slide-44
SLIDE 44

7/23/2020 44

Data Collection Tools – Form Applications Key Ideas – Rounds/Form Design

  • QA/QC
  • Expand
  • Real-Time Analytics
  • Embed Experience
  • Follow up
  • Integrate!

87 88

slide-45
SLIDE 45

7/23/2020 45

Collect Key Features

QA/QC Data Collection

  • Structured Data Types
  • Required Fields
  • Min/Max Constraints
  • Pick List / Radio Options

Indicates Required !

Explore/Transform

Real Time Analytics

  • Historical Comparison
  • Embedded Calculations
  • Alert on bad entry

Actual Reading Vs Real – Time Calculation

89 90

slide-46
SLIDE 46

7/23/2020 46

Learn / Optimize

  • Conditional Questions
  • Automated Follow Up

Learn/Review

Leverage Data – Do More with Less

  • Digitize
  • Integrations to..
  • BI Platforms
  • CMMS
  • GIS
  • Financial
  • Anything….

91 92

slide-47
SLIDE 47

7/23/2020 47

Our people are our best decision-makers.

Ultimately, we trust them to interpret data best.

Process Control & Compliance

Decision Time Scale:

Daily

93 94

slide-48
SLIDE 48

7/23/2020 48

DMR Dashboards

Decision Time Scale:

Monthly

Asset Management Data

Decision Time Scale:

Monthly / Yearly

95 96

slide-49
SLIDE 49

7/23/2020 49

Conclusion

  • Advance Rounds Design
  • Integrate Business

Systems

  • Leverage Data

Questions?

97 98