crystal track at the cutting edge: the nextevents.cleantech.com/wp-content/uploads/2017/02/...at the...

Post on 20-May-2020

2 Views

Category:

Documents

0 Downloads

Preview:

Click to see full reader

TRANSCRIPT

#cleantechSF

Thank you

CRYSTAL TRACK

At the Cutting Edge: The Next Disruptors of Sustainable Innovation

#cleantechSF

At the Cutting Edge: The Next Disruptors of Sustainable Innovation

02

Joe Madden CEO, Xpansiv Data

Janos Veres Program Manager, PARC (a Xerox company)

Micah Winkelspecht CEO, Gem

Moderated by: Jules Besnainou, Director of Product Development, CTG

Usman Shuja Vice President of Market Development SparkCognition

#cleantechSF 03

A new type of coverage

What cutting-edge technologies will have an impact on energy, industry and agriculture in the next 10 years?

Where are they today? What are early applications in our world of energy and data?

#cleantechSF 04

A new type of coverage

What cutting-edge technologies will have an impact on energy, industry and agriculture in the next 10 years?

Where are they today? What are early applications in our world of energy and data?

#cleantechSF

TM

Cognitive Analytics and Artificial Intelligence for Renewable Energy

Usman Shuja @kshuja

Processes Information Draws Conclusions Codifies Instincts & Experience into Learning

Enables machines to penetrate the

complexity of data to identify associations

and reason

Presents powerful techniques to handle

unstructured data and infer

Continuously learns not only from previous

insights, but also for new data entering the system

Provides Natural Language Processing

support to enable human to machine and machine

to machine communication

Does not require rules, instead relies on

hypothesis generation built on analyzed data

Like the human brain, A.I. turns data into insight

Success of AI 3.0 in other fields

What is Cognitive – Beyond Machine Learning

Natural language processing

• Enables recall of answers, in context • Analysis of human readable text for clues, insights

and evidence

Deep Learning and Reasoning algorithms

• Improves accuracy • Learns complex patterns • Scales efficiently: High speed, large data

implementations

Automated Model Building and Infinite Learning

• Watches data and derives rules • Incorporates human feedback to strengthen or

dismiss conclusions • Automatically learns from feedback and greater

volumes of data • More data = more accuracy, capability & insight.

Powerful Visualization with Evidential Insights

• Provides transparency and evidence about what the cognitive system is learning and proposing

• Presents data elegantly – Analyst friendly interface, easy feedback

• Elevates evidence / reasoning for machine decisions

Powerful advancements in state of the art

Cognitive Analytics is Essential to the Future of Energy

By better understanding the ideal operating

states of solar, wind, and battery assets, the

efficiency of those generating units can be increased, resulting in

more energy production and lower maintenance

costs.

Keeping equipment profitable over the amortization period

means keeping efficiency as high as

possible.

Identifying the types of solar inverter failures

automatically will minimize human error,

and reduce time to remediation for wind and

solar assets.

Data to Insight Variable Integration Cognitive for Competitive Edge

Correlation with external variables such as

weather patterns can be incorporated to ensure false positives are not

generated, and the overall predictions for

operating state and efficiency are kept

accurate.

Advanced Analytics can adapt to thousands of

different environments and conditions to

optimize models for the operating conditions of various wind and solar

plants.

A.I. failure prediction and condition monitoring yields massive value for energy generation companies

• Failure Mode based condition monitoring system

• Automated model building, selection & management

• Automate detection of asset operating states

• Estimated increase in productivity of 25% – 30%

• Predictive “Intelligent Maintenance” of heavy machinery optimizes repair & prevention costs, while minimizing unnecessary downtime

• Clients report 50X ROI on the cost of SparkCognition products and services

Detailed Evidence • Provide evidence behind the insights • Provide tools for expert analysis

System Optimization • Optimize not at local but at a global level • Plug insights into platforms such as BI,

Inventory mgmt., PLM etc.

Actionable Insights • Extend asset life • Avoid downtime • In-field, real-time recommendations • Cyber Security Threats

Data Collection

Output

Analytics Platform

Assets

For example, SparkCognition has successfully delivered end-to-end asset health visibility for leading wind operators

Some relevant applications of Cognitive for wind

Predictive Prognostics for Gearboxes, Main Bearings, Blades, Pitch Bearings

Yaw Drive Misalignment

Safety Applications using NLP

Predicting Icing on Wind Turbine Blades

Wind Farm Optimization

Benefits of Machine Learning

The integration of machine learning provides many different benefits

External Factors

Can incorporate external factors (e.g. environmental and weather data)

Scalability

Automated model building capability does not require manual model building of every asset/component

In-context Remediation

IBM Watson advisor that understands natural language to help technical teams

Security

Out-of-band, symptom-sensitive approach beyond IT security

Adaptability

Adapts to new and changing conditions automatically

Feature Enhancement

Automated feature enrichment and extraction

Empowering the end-user to improve business operations

SparkCognition and the client developed an IBM Watson powered “Advisory” application for maintenance

Application enables Directors of maintenance and technicians to:

• Conduct machine to human dialog to troubleshoot with high accuracy

• Speedy identification to map the right fault codes and troubleshooting tips using Natural Language Processing (NLP) queries

• Optimize work flow and deliver relevant documentation for a faster turnaround of planes

Lowered the cost of maintenance and improved asset availability for operators by up to 10%

Cognitive Search of free natural language text

Smarter search to include different and holistic terms Keyword search: Lower body injuries in free form results in 534 incidents

Semantic search: Lower body injuries in free form results in 1027 incidents (leg, foot, toe etc. injuries and non-injuries)

Cognitive Search: Lower body injuries result in 347 which is more accurate

Remove incorrect references to body parts: “foot” as a measurement, “toe of a board”

Focus on references to body parts in the context of injuries

Example Search: “Find incidents involving employees driving into animals” Picked the incident with the following text without any mention of driving or animals

Coming to work in the dark and icy conditions , a deer ran in front of my vehicle. Was difficult to stop without sliding off the road.

1

2

TM

@SPARKCOGNITION

WWW.SPARKCOGNITION.COM

Confidential

#cleantechSF 019

A new type of coverage

What cutting-edge technologies will have an impact on energy, industry and agriculture in the next 10 years?

Where are they today? What are early applications in our world of energy and data?

#cleantechSF

+

Hello, Cleantech. Let’s explore blockchain tech and sustainable supply chains.

+

What’s a blockchain?

C

B

B

A

A

A B C Power

consolidation

Single point

of failure

Growing fees

Attack target

B

B

A

A

B B A B Reconciliation

Complexity

Coordination

A A

A

B

B

A

A

C

B

Let’s combine the best peer-to-peer…

Peer to Peer

No fees

Resilient

No single point of failure

Distributed power

Freedom to innovate

No large attack target

A

A

A

C

And the best of centralization…

C

A

A

A

B

B

B Central Counterparty

Increased reliability

Reduced reconciliation

Single connection

Universal system of record

Reduced complexity

Transaction safety

A

To create the best of both worlds…

A

A

C

C

A

A

A

B

B

B

Central Counterparty

A

A

B

B

A

A B

Peer to Peer

A

B B A

C

A

A blockchain built on integrity

Blockchain Solution

C

A purely peer-to-peer version of electronic

cash would allow online payments to be

sent directly from one party to another

without going through a financial institution.

A B

Alice wants to send money to Bob.

How does a blockchain work?

The transaction is posted to a block along

with other transactions.

A B C D E F

G H

M N

I J

O P

K L

Q R

The block is sent to all validators in the network

A B C D E F

G H

M N

I J

O P

K L

Q R

Node A

Node B

Node C

Node D

Node E

The network approves the valid transactions.

A B

N

C D E F

G H

M

I J

O P

K L

Q R

Node A

Node B

Node C

Node D

Node E

The block is added to the blockchain

A B

Block 432568

+ 10 Transactions

Block 432567 117 Transactions

Block 432566 117 Transactions

Block 432568 + 10 Transactions

Block 432567 117 Transactions

Block 432566 117 Transactions

As the chain

builds, the

transaction

becomes

immutable.

Block 432568 + 10 Transactions

Block 432567 117 Transactions

Block 432566 117 Transactions

Block 432569 112 Transactions

As the chain

builds, the

transaction

becomes

immutable.

Block 432568 + 10 Transactions

Block 432567 117 Transactions

Block 432566 117 Transactions

Block 432569 112 Transactions

Block 432570 38 Transactions

As the chain

builds, the

transaction

becomes

immutable.

Block 432568

+ 10 Transactions

Block 432567 117 Transactions

Block 432566 117 Transactions

Block 432569 112 Transactions

Block 432570 38 Transactions

Block 432571 96 Transactions

As the chain

builds, the

transaction

becomes

immutable.

Blockchain is not FinTech

It’s data management

A financial transaction is just a

data type…

A financial transaction is just a

data type…

Energy Data

Oil Production

Storage Tank

Levels

Pipeline

Leakage

Carbon

Emissions

Pressure Meter

Solar

Conversion Coal Mined

Power

Consumption

Valve Flow

Rates

Interactions, not just transactions

A sends gas producer sensor data to Xpansiv

Interactions, not just transactions

A sends gas producer sensor data to Xpansiv

select identity select data select identity.

Federated Blockchain

select identity select data select asset

Federated Blockchain

Interactions, not just transactions

analyzes Xpansiv sensor data to issue Digital Feedstock

select identity

Federated Blockchain

Interactions, not just transactions

sends Xpansiv to

.

gas producer

select identity select asset

Digital Feedstock

GemOS helps

companies build

collective

intelligence through

collaborative

blockchain networks

Xpansiv is powered by GemOS

We’re unlocking the next wave of innovation & investment in a sustainable future.

Xpansiv’s mission is to standardize, quantify, verify, value and deliver

environmental and social impact information so that:

• Producers can differentiate products

• Investors can make smarter decisions about the impact & risk of their

investments

• Corporations can manage & communicate the impact of their supply

chains

• Consumers can be assured that their purchases are contributing to a

just and verdant world

We’re focused on commodities

Commodities:

• Represent more than 7% of annual GDP on a global basis

• Generate ~40% of annual

global GHG emissions from their production alone*

• Linked to decline in climate, water, deforestation, labor conditions

Sustainable Brands, April 2016

The Economist, July 2016

*Global GHG and market size: internal calculations based on data from FAOSTAT, EIA, UNEP, EPA, vertical-specific GHG

assessments and spot prices; https://www.ici.org/pdf/per18-03.pdf; http://www.cnbc.com/commodities/

Digital Feedstock = standardized, quantified,

verified, & encrypted impacts for each unit of

production

All commodities are not “created equal” when it comes to impact, yet they are undifferentiated in markets difficult to analyze for investors

EX. There is an over 80% difference between the highest and lowest GHG-emitting oils*

Xpansiv’s Digital Feedstock enables investors, markets and consumers to “de-commoditize the commodity”

1 barrel

Suncor

Synthetic

H (OSH)

.15

mtCO2e*

700L H20**

20g C6H**6

.03

mtCO2e*

300L H20**

5g C6H6**

1 barrel

US Gulf

Mars

*Carnegie Endowment 2015 report, “Know Your Oil: Creating a Global Oil-Climate Index”

** Illustrative

We generate and deliver Digital Feedstock

Digital Feedstock

Enables differentiated products for markets:

• Low-GHG aviation fuels

• Deforestation-free palm oil

• (Methane) leak-free natural gas

• Sustainable rice

Provides assurance for impact investments:

• Impact funds

• Green bonds

• Climate bonds

Feeds risk assessment and reporting:

• Insurers

• Corporate GHG reporting (CDP, etc)

Federated Blockchain

Natural Gas Today

53

Methane leakage represents a massive environmental challenge. The existing physical infrastructure and the natural gas

markets cannot differentiate natural gas at present.

End users have

no choice and

investors

cannot assess

impact/risk of

their

investments

Producers get

paid for

materials sent

to market

regardless of

impact

Natural gas is

commingled

Producer

2

Producer 3

Processing

plant Local gas

company

Manufacturing

Residential

Commercial

Power plants

Distribution

HUB

Producer 1

2017: Proving the concept

54

Low methane leak Low water use

Low methane leak Low water use

Low methane leak Low water use

?

Our solution delivers 3rd party validated impact metrics (Digital Feedstock)

downstream to natural gas consumers and provides assurance to investors seeking

to maximize impact and minimize risk.

?

?

✔ Low impact

natural gas

Producer

2

Producer 3

Processing

plant Local gas

company

Manufacturing

Residential

Commercial

Power plants

Distribution

HUB

Producer 1

Deliver Digital

Feedstock to:

1. Impact

Investors

2. End users

2018 and beyond: Seamlessly integrating & valuing externalities in global commerce.

Where to from here?

Collecting and

structuring

production data

from natural

gas producers

Apply production

data to 3rd party

standard to

generate quantified

impact metrics

Encrypt impact

metrics in

blockchain

Verify encrypted

metrics

according to

guidance from

standard

2017: Xpansiv and Gem will prove the concept in Natural Gas by….

#cleantechSF

The Future of Electronics

Janos Veres Program Manager

Novel and Printed Electronics

Future electronics

Accessible, low

capital, local,

additive, green

Easy to fabricate,

on-demand

Seamlessly integrate

micro and macro -

sensors, logic, chips,

batteries, MEMS, optics

Flexible, conformal, 3D

Application specific

smart labels

Personalized wearables,

structural electronics

Any form factor,

anywhere

New levels of

complexity

Custom function & form

Personalized

health Transportation

Interactive

Entertain

Educate

Structural

monitoring

Printed

Electronics

Smart

packaging Supply chain

© 2016 Palo Alto Research Center Incorporated; all rights reserved

A customized IOT

Smart labels for supply chain

• Printed sensors, antenna + bare die chip

• Configurable sensors: temperature, chemical, pressure, capacitance, integrity

• 6 months running time

• Smart packaging demos at PE USA

PARC | 62

Gas detectors for energy infrastructures

Energy management for buildings

Up to 30% energy savings with more & better sensors - 1,800 Tbtu/yr

Self-commissioning, remotely-powered wireless sensor systems Reduce costs of hardware, installation, and commissioning

Summary

PARC | 64

• The future of electronics: Customized smart devices – Form + function, connected to the environment

– On demand, low cost, easy to deploy and use

• Customized IOT – Transportation, supply chain

– Homes and offices

– Manufacturing efficiency

– Safety and energy infrastructure

– Healthcare

• Customized analytics – Relevant, specific data

– Informed decisions

Pre-fabbed Metal wire bone structure

Assembled and welded on the fly

Solid, low strength

light weight area

Solid, high

strength area

Plastic structural material

Jetted and cured on the fly

Embedded control/

communication IC

Flexible

area

Embedded

temperature

sensor

Structure heath

monitoring sensor

Optical

transceiver for

Optical encoder

Embedded Ultrasonic

Motor for motion

top related