Expert bottleneck
Operational expertise
Put your operational knowledge to work.
Help teams apply documented operational knowledge across more assets, drawing on operating history, inspection findings and engineering assessments.
A TGU within TTI GmbH · University of Stuttgart
The AI Decision Layer for Renewable Energy Operations
Ventyx brings wind engineering, digital twin research, and AI together to help asset owners unlock more value from renewable energy operations.
>90%
Recommendation accuracy
Offline validation with a pilot customer
10+
Years in wind energy
Turbine engineering & university research
329 MW
Onshore pilot data
69 turbines · real owner operating data
Human-led
Final decision authority
AI recommends. Your team makes the final call.
THE COMPANY
Make human expertise scalable.
Renewable portfolios are growing. Developing experienced teams takes time. We use AI and engineering models to help people apply their knowledge across more assets, with the aim of lowering operating costs and improving long-term asset value.
Meet the team behind Ventyx →OUR PRODUCT · NEXUS
Agent as a Service for renewable energy operations.
Nexus agents investigate operational events, recommend actions and prepare reports using your asset data and documented knowledge. Your team retains final decision authority.
Hidden lifetime impact
Fatigue-life intelligence
See how today’s operation affects asset life.
Use physics-based estimates of fatigue-life consumption to support maintenance and long-term asset planning.
Connected data and clear priorities support both.
Fragmented data → Bring operating information into context.
Reactive operations → Prioritise issues and support earlier planning.
See Nexus in action
What matters. Why it matters. What next.
AI
Nexus AI Agent
Illustrative scenario · Turbine T12
High Priority
Why is Turbine T12 ranked as high priority today?
AI
T12 has repeated vibration warnings. SCADA trends provide operating context, and the digital twin estimates elevated fatigue accumulation. These signals support a closer review; they do not establish the root cause.
SCADA trends
Alarm history
DT load estimate
Should we inspect it now or derate first?
AI
Consider temporary derating and an inspection in the next suitable weather window. Before approving, check operating limits, site procedures, and whether the inspection can safely wait.
Review example action
Proposed task: inspect T12 vibration alerts and review the load estimate. The operator confirms the scope, timing, and any operating changes before creating a work order.
Demo only · no work order is created.
View example evidence
- Alarm history: repeated vibration warnings.
- SCADA trends: operating context for the warnings.
- Digital twin: estimated fatigue accumulation, subject to model assumptions.
Synthetic example · no customer records shown.
Illustrative workflow with synthetic data. Recommendations require operator review.
Put today’s signals in the context of long-term fatigue.
Digital Twin Engine
Illustrative wind farm · 12 turbines
06:00 UTC
Estimated fatigue life consumed · illustrative values
T01
13%
T02
9%
T03
11%
T04
29%
T05
12%
T06
18%
T07
26%
T08
24%
T09
5%
T10
17%
T11
28%
T12
●
48%
20%
Avg consumed
12
Turbines assessed
1
Priority review
AI
In this example, T12 has consumed an estimated 48% of its modeled fatigue life, versus a 40% reference: 8 percentage points higher. Together with vibration alerts, this supports priority review. Model estimates are not a remaining-service-life guarantee.
WIND USE CASE
Nexus in wind operations
Validation context
Operational recommendations
The recommendation accuracy shown above comes from offline validation with an onshore wind pilot customer, using historical operating data. The evaluation included event prioritisation. This result describes that evaluation, rather than live operating performance.
Asset management & operations reports
Nexus also generates data-grounded asset management and operations reports, drawing on operating history, inspection findings and engineering assessments. Your team reviews the findings and conclusions.
Engineering research
Our wind digital twin methods build on University of Stuttgart research validated with data from North Sea and Baltic Sea wind farms. This is separate from the pilot’s recommendation accuracy. Fatigue-life consumption is a model-based estimate; its interpretation depends on the data and modelling assumptions.
Knowledge workflows use records your organisation is authorised to use for this purpose, including operating history, inspection records and engineering assessments.
OUR TEAM
Engineering depth. Product focus.
Dexing (Alex) Liu
Founder & CEO
10+ years in wind energy, spanning turbine engineering and University of Stuttgart research. His PhD research focuses on wind turbine fatigue and digital twins.
LinkedIn ↗Chengqi Zhu
Co-founder & CPO
10+ years in product design at IBM, Twitter and ByteDance. He leads product strategy and user experience at Ventyx.
LinkedIn ↗WHAT’S NEXT
Expanding with asset owners
Next with our pilot customer
Solar
Bring the customer’s solar assets into the decision workflow.
Seeking pilot partners
Offshore wind
Work with offshore asset owners to evaluate Nexus in their operating context.
GET IN TOUCH
Grow your portfolio. Extend your team’s reach.
Explore how Nexus can help your team prioritise actions, use fatigue estimates in asset planning and unlock more value from your assets.