Feedback loop design and tuning
PID, cascade, feedforward and ratio control — structured loop design, identification, tuning and commissioning for stable, responsive and robust closed-loop operation.
Industrial AI and Advanced Process Control
Replace drifting loops and conservative setpoints with model-based predictive control — APC/MPC, soft sensors, digital twins, real-time optimization.
Experience at
CERN · IAV GmbH · SkySails Power · evosoft / Siemens · Assystem
Previous positions, not client endorsements. Tools & Platforms
Python · MATLAB / Simulink · C / C++ · CasADi / acados · WinCC OA
The Industrial AI Stack
Industrial AI is a layered stack — not a single product. Each layer builds on the one below, and each has documented ROI of 6–18 months. A diagnostic call identifies which rung your plant is on and the fastest path to the next one.
Layer 7 Digital Twin
Live virtual replica of your plant — model + state estimation + RTO/MPC integrated. Enables what-if analysis, operator training, and enterprise optimization.
Explore → Layer 6 Real-Time Optimization (RTO / DRTO)
Compute the economically optimal operating point every 30 minutes. $1–15M/year per major process unit. Requires APC as executor.
Explore → Layer 5 APC / MPC / NMPC
Multivariable closed-loop control — track optimal setpoints, handle disturbances, enforce constraints. Payback 3–12 months.
Explore → Layer 4 Predictive Maintenance
Detect bearing wear, fouling, and equipment degradation from vibration, acoustic, and current data. Deployable independently of the process control stack.
Explore → Layer 3 Process Monitoring — SPC / MSPC / FDD
Detect process drift and abnormal events before they become quality failures. Prerequisite to deploying APC.
Explore → Layer 2 Soft Sensors & State Estimation
Estimate unmeasured quality variables and synchronize models with the plant in real time. Enables tight quality control without expensive analyzers.
Explore → Layer 1 Measurement & Data Infrastructure
Sensors, analyzers, historian (AVEVA PI, OPC UA). The foundation — without clean data, nothing above it works.
Which rung is your plant on?
A 30-min diagnostic call maps your current position and the fastest path to measurable ROI.
Book a Diagnostic CallProven Track Record
PhD-level theory combined with 20+ years of live control deployments — across process industry, energy, and autonomous systems.
20+ Years hands-on experience
30+ APC/MPC projects
PhD in Control Systems
5 Languages spoken
- Former MPC engineer at CERN (LHC superfluid helium at 1.9 K), IAV GmbH (wind turbine pitch control), SkySails Power (airborne wind energy), and evosoft (Siemens Corporate Technology)
- 4× MSc in Control Engineering (Grenoble INP, Karlsruhe Institute of Technology, Gdańsk University of Technology) and PhD from University of Valladolid — trained at four top European engineering schools
- Industries covered: particle physics cryogenics (CERN), wind energy (IAV, SkySails), industrial SCADA (evosoft/Siemens), and aerospace HIL simulation (Assystem Group, A400M turbine engine)
Book a Free Consultation
Schedule a 30-minute call to discuss your process challenges and explore potential solutions.
What we will cover:
- Review your current process challenges
- Identify potential for APC/optimization
- Discuss practical next steps
- Answer your technical questions
30 minutes
Video call
EN/DE/ES/FR/PL
Case Studies
Selected project summaries — all under NDA, anonymised by default.
NDA · anonymised Cryogenics · NMPC
Supercritical helium refrigeration
Economic NMPC for a large-scale industrial cryogenic system at 1.9 K. First-principles thermo-hydraulic model, optimisation-based state estimation, and supervisory control.
Energy-efficient autonomous operation of a multi-MW cryogenic installation.
NDA · anonymised Wind Energy · Feedback ControlMulti-MW wind turbine control system
Functional architecture, dynamic simulations, feedback control, Economic NMPC, parameter optimisation, and On-Board Diagnostics for a large wind turbine.
Improved load management, fault detection, and turbine lifetime.
NDA · anonymised Airborne Wind · Trajectory OptimisationKite power — 3D flight automation
Flight automation for an airborne wind energy system: non-linear models, UKF state estimators, feedback control, and online 3D trajectory optimisation for autonomous kite operation.
Autonomous power-generation flights with continuous online re-planning.
NDA · anonymised Avionics · Soft SensorVariometer — sensor fusion for pilots
Non-linear state estimation for a paragliding variometer, fusing barometric and IMU data to deliver low-latency vertical speed and total-energy readout.
Sub-second latency energy display for real-time thermal navigation.
Competence demonstrated in Past Projects
Deep theoretical foundation plus many years of hands-on practice in R&D contexts, developing new types of systems where the solution is not obvious at the start. We adapt language to the audience and deliver key insights in a compact and engaging way.
APC and MPC
Advanced controls enable efficient operation of non-linear systems with strong couplings, operated across a wide range of conditions under strict constraints.
State estimation
Combine models with available sensors to improve accuracy, reduce the need for expensive sensors and estimate non-measurable variables.
Optimization and trajectories
Scheduling, logistics and resource allocation at plant level, and trajectory optimization for machines to increase throughput, reduce wear and lower energy costs.
Show more competences
Modeling and simulation (digital twins)
Evaluate ideas and operating strategies without touching production. Parametric/sensitivity studies guide investment; models enable optimization and operator training.
Operator simulators
Train operators offline to reduce interruptions and waste. Cover standard tasks, complex situations and safety-critical scenarios.
Workshops and courses
PhD-backed teaching and hundreds of public talks. Key knowledge delivered compactly and engagingly, tailored to experts, decision makers or technicians.
Tools and stack
Cutting-edge, industry-standard tools chosen per application. Seamless integration with existing software and collaboration via version control.
Publications
Peer-reviewed papers, conference proceedings, and theses on Model Predictive Control, state estimation, and cryogenics at CERN.
2024 Industry Abstract
Optimization of 3-D flight trajectory of variable trim kites for airborne wind energy production
arXiv:2403.00382
2018 Conference
Super-short Term Wind Speed Prediction based on Artificial Neural Networks for Wind Turbine Control Applications
IECON 2018 - 44th Annual Conference of the IEEE Industrial Electronics Society
2015 Conference
NMPC for superfluid helium cryogenics
5th IFAC Conference on Nonlinear Model Predictive Control (NMPC), Seville. IFAC-PapersOnLine, 48(23), pp. 440-445
2015 Thesis
Non-linear Model Predictive Control for cooling strings of superconducting magnets using superfluid helium
PhD Thesis, University of Valladolid
Show more publications
2014 Conference
Non-linear moving horizon state estimation and control for the superfluid helium cryogenic circuit at the Large Hadron Collider
53rd IEEE Conference on Decision and Control (CDC), pp. 3530-3535
2011 Conference
NMPC for stiff, distributed parameter system: Semi-Automatic Code Generation and optimality condition evaluation
18th International Conference on Process Control, Tatranská Lomnica, Slovakia
2011 Conference
Simulation Study on Application of Nonlinear Model Predictive Control to the Superfluid Helium Cryogenic Circuit at the Large Hadron Collider
18th IFAC World Congress, pp. 3647-3652
2010 Conference
Nonlinear Model Predictive Control for the Superfluid Helium Cryogenic Circuit of the Large Hadron Collider
19th IEEE International Conference on Control Applications (CCA), Yokohama, Japan, pp. 1654-1659
2008 Report
First principles modeling of the Large Hadron Collider's (LHC) Superfluid Helium Cryogenic Circuit
Technical Report, CERN
2007 Thesis
Modeling and control of the String2 LHC Prototype at CERN
MSc Thesis (Joint: Univ. Valladolid, ENSIEG Grenoble, Univ. Karlsruhe, Politechnika Gdańska)
Writing a paper?
Cite our work with properly formatted BibTeX entries.
Products
VFD Pump Tuning Tool
A guided web wizard for complete VFD configuration of booster pump systems. Enter a few on-site measurements — the tool calculates all 30+ VFD parameters tailored to your specific installation. Covers PID settings, analog input scaling, sleep/wake thresholds and motor identification. Free, online, mobile-friendly. No engineering background required.
Your Benefits
Concrete Results
- More throughput and faster cycle times at the same quality
- Lower energy, fuel and raw material cost; reduced waste and emissions
- More stable processes despite disturbances, varying inputs and model uncertainty
- Reduced component wear, actuator fatigue and maintenance cost
- Price-optimal operation — adapt in real time to energy prices, demand and market signals
- Safety-guaranteed automation — force limits, obstacle clearance and collision avoidance by design
- Faster commissioning and shorter trial times
- Transparent, auditable decisions through data, models and simulation
- Lower dependency on scarce specialists — advanced automation handles complex tasks around the clock without requiring expert operators on every shift
Service
Deployment Toolchains for Scalable Automation
When complex control logic must be adapted and deployed across many machine variants or installations, rebuilding it manually is the bottleneck. I build engineering toolchains that turn structured configuration into deployable artifacts: controller settings, PLC code, HMI objects, tests, commissioning checklists, and documentation — consistently, with fewer errors, faster.
The toolchain generates:
- Controller configuration and parameter sets
- PLC code skeletons and deployment packages
- HMI objects, alarm structures, I/O mappings
- Tests, simulation assets, commissioning checklists
- Operator and engineer documentation
Good fit when:
The same engineering pattern repeats across projects; commissioning is slow or error-prone; knowledge is concentrated in a few experts; quality varies between sites or machine variants.
"First stabilize the engineering logic — then industrialize it."
Discuss your engineering workflowCalculate Your Potential Savings
See how much you could save with Advanced Process Control. Enter your approximate annual costs below.
Input your parameters
Potential Annual Savings
Energy reduction €75,000 10-15%
Waste reduction €40,000 15-25%
Throughput increase €100,000 3-8%
Downtime reduction €20,000 15-25%
Total annual savings €235,000
Typical payback period: 6-18 months
Get a personalized feasibility study
We reply with a tailored analysis within 2 business days.
Ranges based on published industrial implementations (steel, cement, HVAC). Results vary by process. See sourced case studies →
Send your historian data for a quick feasibility estimate (NDA-ready) We sign NDAs before receiving any data.
Free 1-Page Process Diagnostic
Send us one week of historian data and we will return a concise 1-page diagnostic report: bottleneck identification, control loop health, and a realistic improvement estimate — at no cost and no commitment.
NDA signed before data exchange. Results delivered within 5 business days.
Industries
Focused on practical results across manufacturing, process industry, energy, robotics, logistics and machine building.
Paraglider & Kite-Based Systems
Flight state estimation and closed-loop control for paragliders and kite-based systems — observer design, stability augmentation, and autonomous guidance, backed by 1,000+ hours of hands-on paraglider flight.
Manufacturing & CNC
Reduce cycle time and raise throughput on CNC machining, robotic milling and assembly lines. Contour error compensation, feed-rate optimization and deflection prediction cut scrap and raise surface quality.
Process Industry
Handle nonlinear batch and continuous processes — chemicals, pharma, cement, steel and food. When large disturbances, operation close to constraints, or model mismatch cause the control system to operate uneconomically during transients — and RTO setpoints lose validity — Economic MPC embeds the economic objective directly into the feedback loop.
Energy, Buildings & Agriculture
Maximize renewable energy yield, dispatch battery storage for price arbitrage, cut building HVAC energy by 17%+, and minimize greenhouse heating cost — with time-varying prices and weather forecasts built into the controller.
Show more industries
Machine Builders
Embed trajectory optimization and model-based control to increase precision, reduce component wear and lower energy draw — with embedded solvers meeting hard real-time budgets on standard PLCs or microcontrollers.
Robotics & Autonomous Systems
Control collaborative robots to ISO 15066 force limits, plan collision-free motions for manipulation and assembly, and operate legged or wheeled robots across unstructured terrain — constraint satisfaction guaranteed by design.
Logistics & Intralogistics
Optimize AGV routing and speed profiles in warehouses, reduce crane sway, synchronize multi-robot fleets and replan paths in real time under uncertainty. Constraint-aware MPC replaces conservative fixed-speed profiles.
Aerospace, UAV & Marine
Guidance and control for drones, UAV swarms, underwater vehicles and ships — from time-optimal trajectories to dynamic positioning and fault-tolerant attitude control under actuator saturation and model uncertainty.
Electric Drives & Power Electronics
Predictive torque and current control for VFDs, switched reluctance and permanent magnet motors. Reduce torque ripple, extend lifetime and meet grid fault ride-through requirements in turbomachinery, oil & gas and industrial drives.
Predictive Maintenance
Detect bearing wear, gearbox degradation, and blocked filters from live sensor data — before failure occurs. Often as simple as a microphone and suitable signal processing.
Ready to improve your process?
Book a free 30-minute consultation to discuss your challenges.
Book a 30-min feasibility call No commitment required
How we work (in 4 steps)
1
Audit & Diagnosis:
Clarify data, goals & constraints; identify quick wins.
2
Simulation & Concept:
Digital twins, first MPC/estimators; prove potential.
3
Pilot & Tests:
Proof-of-concept on process/machine, tune parameters.
4
Scaling & Operation:
Industry-grade implementation, training, tuning & support.
Agile in 2-week sprints – with clear, usable deliverables after each sprint.
Services
Four engagement types with clear scope, high-quality execution and professional standards. Remote or on-site.
Consulting
Uncover bottlenecks and opportunities using data analysis, on-site observations and feedback from your team. From insights to business cases and a practical roadmap.
Software development
20 years across the full lifecycle: requirements, architecture, implementation, testing, deployment and documentation on PCs, industrial systems, SCADA and embedded.
Training & Coaching
Hundreds of talks in five languages. Operator training with digital twins; engineer training in advanced control, state estimation, optimization; team mentoring.
HR services
Provide the technical expertise to assess and hire the right people, leveraging a broad network to find strong candidates.
Approach tailored for SMEs
Tailored + standards
Custom solutions where it matters, and standard tools where they fit best.
Flexibility & quick response
Short reaction times and pragmatic delivery to keep momentum.
Long-term commitment
Maintenance, tuning, support and knowledge transfer to sustain performance.
Hands-on
Data analysis plus workshops with operators and management to uncover real problems.
Show more
Model-based
Use simulation and optimization to save experimental time and reduce risk during development and commissioning.
Risk management
Carefully weigh risks and benefits; enable progress via controlled trials of new parameters and approaches.
Agile development
Two-week sprints with usable results each time; quick adaptation to changing requirements and experimental findings.
Deep theory, applied
Strong foundations in mathematics, physics, computer science, control systems and optimization - applied to real problems.
Practical Model Development
Models as simple as possible — geometry and basic physics for linear control design, minimal nonlinear extensions only when simulation demands it. Complexity is justified by the control problem, not assumed.
Startup Offer: Senior Control & Autonomy Support
Compact, clearly scoped work packages (5–10 days) and light-touch support — so you keep development in-house, protect your IP, and build no long-term external dependencies.
For startups bringing complex dynamic systems to real-world operation: drones, robotics, aerospace, mobile machines, energy tech, industrial automation. Remote-first, occasional on-site possible.
Mini Implementation Packages (5–10 days)
Prototype of an estimator or controller, simulation/test harness (SIL/HIL), critical module refactoring, experiment design + on-site test days + evaluation report.
Technical Sparring Partner
60–90 min review call weekly or biweekly while your team implements. Focus: architecture, controller concept, robustness, estimator design, test design, log analysis. Written notes with decisions, risks, and next steps.
Gate Reviews (milestone-based)
3–5 jointly defined gates (e.g. "before first field test", "after stable closed-loop", "before scaling"). Per gate: review + written findings + Go/No-Go recommendation + risk register.
Enablement / Training
1–2 compact workshops tailored to your system: architecture paths, sensor/IMU integration, observers/filters, vibration damping, loop shaping, test design, KPI definition, tuning workflow. Deliverable: training materials + playbook.
NDA standard. You keep IP ownership and control of development. No hidden licensing. Transparent fixed-price or day-rate billing to match your budget. Always handed over so your team can continue independently.
Goal, constraints, status, risks — then a concrete proposal.
Starter packages
Agile execution in two-week sprints across all packages, including clear deliverables after each sprint.
Diagnostic and analysis
Understand the problem, data and objectives; identify quick wins and a sensible path forward.
Deliverables: analysis report + concise technical proposal.
Get startedSimulation study
Recreate the setup in simulation, build first models/estimators, run realistic studies to assess potential.
Deliverables: simulation study report + draft plan for experimental proof of concept.
Learn moreExperimental proof of concept
Bring simulation into reality, run controlled tests, adapt parameters and validate performance on site.
Deliverables: test plan + on-site report + tuned settings.
Learn moreUser-facing tools
Engineering aides or operator-training tools based on models; designed for non-experts.
Deliverables: working prototype + brief user guide.
Show more packages
Industry-grade development
Harden to industrial standards with documentation, safety and quality gates - ready for scale.
Deliverables: codebase and docs aligned with agreed standards.
Commissioning
Deploy on the machine or process. Operator training, extensive testing and final documentation.
Deliverables: commissioning report, training materials, SOPs.
Support
Maintenance, tuning, adaptations and knowledge transfer - ongoing or punctual.
Deliverables: per-sprint updates and improvement notes.
Customer-requested package
Defined jointly upon agreement to match your specific needs and constraints.
Deliverables: as agreed, per-sprint outcomes and documentation.
Cooperation Models & Pricing
Below you will find typical cooperation models as they are practical in the technical SME sector (engineering/development/plant environment). The daily rates shown are starting prices ("from") net plus VAT and will be specified in the offer based on the specific project context.
1
Model 1 — Initial Development Phase: Full-time On-Site (Ramp-up)
Purpose: Maximum progress in short time (kick-off, system access, fast iterations, on-site tests/integration).
Mode: Full-time, 5 days/week on-site.
from €990/day
2
Model 2 — Hybrid Full-time: Mostly Remote + Scheduled On-Site Weeks
Purpose: High velocity with reduced on-site share; regular, predictable presence for reviews, tests, and acceptance.
Mode: ~80% remote, 1 week on-site every 5 weeks (full-time on-site).
from €790/day
3
Model 3 — Long-term Part-time Support: Topic Ownership & Continuous Improvement
Purpose: Sustainable ownership without full-time headcount; stabilization, continuous improvement, knowledge transfer.
Mode: 20 hrs/week, ~80% remote, 1 full-time week on-site every 10 weeks (e.g., for reviews, tests, integration).
from €490/day
4
Fixed Price / Milestone-based Payment (Work Contract Logic)
Suitable for: Clearly defined deliverables with defined acceptance (e.g., analysis package, model audit, MPC concept, prototype, optimization module).
Billing: Fixed price per milestone/package; acceptance based on clear criteria.
Show more cooperation models
Agile Working Methods & Delivery Cycles (Standard)
Regardless of the billing model, development is agile:
- 2-week cycle with result delivery (demo/review + next priorities)
- Transparent progress (backlog, sprint goals, KPI tracking as needed)
- Early feedback for risk reduction (technology, integration, acceptance)
Additional Models (optional, depending on scope)
Retainer / Service Contingent (optionally with response times)
Suitable for: Plannable capacity, regular reviews, quick support ("keep-the-lights-on" + minor enhancements).
Billing: Monthly contingent (e.g., X days/month), optionally with defined response times.
Scoping Sprint (Workshop → Reliable Offer)
Purpose: Quickly clarify scope, make risks/dependencies visible.
Result: KPI target picture, system boundaries, data/interface list, integration plan, effort estimate, and offer model (T&M or milestones).
Build–Operate–Transfer (Setup → Operation → Handover)
Purpose: Quick external start, then internal anchoring.
Service: Setup, stabilization, knowledge transfer, optionally recruiting support (role profile, interview support) and structured onboarding of internal owner.
A Quick Cost Comparison (Internal FTE vs. External)
An internal FTE with a €100,000 gross salary costs the company (roughly calculated) about ~€720 per productive day.
Internal FTE calculation example:
- Employer costs (simplified): ~€120,000/year (salary + employer contributions)
- + conservative overhead (IT/workplace/management/HR, tools, etc.): +20% ⇒ ~€144,000/year
- Productive days (e.g.): ~200 days/year (working days minus vacation/sick leave/training/other absences)
→ Internal full cost per productive day: 144,000 / 200 = ~€720/day
Price Factors (why "from" pricing makes sense)
The specific conditions typically depend on:
- Geography & travel: Travel, accommodation, expenses
- Urgency / availability: Express start, downtime situations, weekend windows
- Predictability & duration: Contingents/long-term enable better conditions
- On-site share & rhythm: Predictable vs. ad-hoc
- Complexity & criticality: Production risk, safety/quality constraints, commissioning
- Scope clarity: Clearly defined deliverables vs. open R&D questions
- Tooling & compliance: Access, data situation, IT/OT requirements, documentation scope
- Response times / SLA: Agreed response times
- IP/rights arrangements: License, source code, exclusivity
Contract & Compliance Components (typical)
- NDA (confidentiality) as needed
- DPA (Art. 28 GDPR), if personal data is processed
- Clear arrangements for acceptance, change requests, payment terms, travel costs, liability framework (project-specific)
IP, Licensing & Exclusivity Options (on request)
Depending on the project, cooperation can also be structured as Solution-on-Demand:
- Delivery of a ready-to-use solution (e.g., software module/algorithm component/toolchain).
- Typical distinction between customer-specific results (for the customer) and reusable generic IP (methodology, libraries, building blocks).
- Optional: License/usage rights model (e.g., per site/plant/module or enterprise license) incl. maintenance/updates via retainer.
Optional customer protection (competitor restriction):
It can be agreed that we will not sell or license the developed solution to direct competitors of the customer (e.g., as industry/competitor exclusivity for a defined period and/or market), with scope and limits to be precisely defined contractually.
Conclusion
The models above are proven standards — individual structures are also possible. Whether daily rate, milestones, retainer, license model, or exclusivity: We design the cooperation to fit scope, risk, budget, and your procurement/compliance process.
The cooperation possibilities are practically unlimited – we will find a clean, fair way.
Note: This page is for general information and does not constitute legal advice. The specific terms are bindingly regulated in the respective offer and contract.
APC Readiness Assessment
Answer 5 quick questions to evaluate if your process is ready for Advanced Process Control.
How would you describe your current process data collection?
How stable is your current process operation?
What is your process control maturity?
How clear are your optimization objectives?
What is your team capacity for new technology?
Excellent APC Readiness!
Your process shows strong potential for Advanced Process Control.
Your readiness score: 0 /15
Blog
Short and clear: practical notes on control, optimization and digitalization.
From Tribal Knowledge to Scalable Automation: Why Deployment Toolchains Are the Real Productivity Unlock
Many manufacturers don't lose time because the control algorithm is too hard. They lose time because the path from expert knowledge to deployed engineering is too manual. Deployment toolchains fix that — and Siemens, Beckhoff, Rockwell, and MathWorks are already proving it.
Neural Networks in Industrial Control: How Many Are Actually Running?
The AI revolution is real — but how many neural networks are actually running industrial control loops? Analysis of 672 studies, 148 real-world implementations, and 10 confirmed production deployments reveals the gap between hype and hardware.
Something Happened to APC in August 2025
Google Trends shows a 5–10× synchronized jump in searches for advanced process control, digital twin, and soft sensor in August 2025. Here is the timeline that explains it.
MPC in 5 Minutes
Why predictive control delivers robust quality.
5 Signs Your Control Loops Are Costing You Money
Most process plants quietly lose 5–15% of throughput and energy efficiency through poorly tuned loops. Here are the five symptoms to look for — and what each one costs.
Soft Sensor vs. Hard Sensor: When to Use Which
A practical decision framework for choosing between physical analyzers and model-based virtual sensors — with cost ranges, lag times, and the hybrid approach most plants miss.
How to Decide if APC Is Worth It: A 15-Minute Self-Assessment
Before spending on a consultant or a commercial APC platform, run through this checklist. It identifies whether your process has the prerequisites for advanced control.
Frequently Asked Questions
Common questions about Advanced Process Control and working together.
What is Model Predictive Control (MPC)?
MPC is an advanced control strategy that uses a mathematical model of your process to predict future behavior and optimize control actions. It excels at handling multi-variable systems with constraints, delivering better performance than traditional PID control.
How long does an APC implementation take?
Timelines vary by scope. A diagnostic phase typically takes 2-4 weeks. A full proof-of-concept can be completed in 2-3 months. We work in agile 2-week sprints with deliverables at each stage.
What ROI can you expect from APC?
Published reference implementations report: ~17% primary energy reduction in buildings (ETH Zurich / Siemens, IEEE TCST 2016), temperature variability halved in cement kilns (Holcim / ABB, 2008), and slab quality out-of-spec cut from 59% to 12% in steel reheating furnaces (Dillinger, 2011). Reference payback periods: 6–18 months. Every process is different — a 30-minute discovery call is the fastest way to estimate the realistic opportunity for your system.
Do you work remotely or on-site?
Both. Many phases can be done remotely, including data analysis, model development, and simulation. On-site presence is valuable for commissioning, operator training, and initial diagnosis.
What industries do you work with?
Process industry (chemicals, pharma, food & beverage), manufacturing, machine builders, and energy generation. Any industry with complex, multi-variable processes can benefit.
Can you sign an NDA before I share data?
Yes — a mutual NDA is standard practice and we sign before any data or process details are shared. We work comfortably in export-controlled and security-sensitive environments.
What if the project doesn't deliver the expected results?
We structure every engagement in phases with clear deliverables and exit points. If a phase shows the expected benefit is not achievable, we say so — and stop — rather than continuing to invoice. A failed proof-of-concept early is far cheaper than a failed deployment late.
Can you work with our existing SCADA / DCS / ERP?
Yes. We work at the data layer — if your historian or data infrastructure exports standard formats (OPC-UA, CSV, REST), we can interface with it regardless of DCS or SCADA vendor. PLC-level and vendor-specific control system integration requires collaboration with your automation team or vendor.
Who owns the IP and code developed during the project?
The code and models developed remain the intellectual property of Dr. Noga. The client receives a perpetual use license included in the development price. Exclusive licenses and non-compete agreements (NCA) are available and negotiable. Details are defined in the contract.
Do you work alone or with a team?
Primarily alone — which means senior-level attention on every task, no junior handoffs, and no account-manager overhead. For projects requiring additional capacity, I have a trusted network of specialist engineers I can bring in under the same quality and confidentiality standards.
Have more questions?
Ask directly Free Resource
APC Readiness Checklist
Assess if your process is ready for Advanced Process Control. A practical guide with 15 key questions.
- Evaluate your data infrastructure
- Identify quick-win opportunities
- Understand resource requirements
Live Event
Free Webinar: Introduction to APC
Learn how Advanced Process Control can transform your operations
- What is APC and when does it make sense?
- Real-world case studies and ROI examples
- How to evaluate APC readiness
Contact
Send a message
Direct contact
Dr. Rafał Noga
Stay Updated
Get insights on Industrial AI, APC, and process optimization delivered to your inbox.
Verified Credentials
Verifiable excerpts from work certificates and recommendation letters — documenting hands-on experience in optimization, model predictive control, and state estimation.
Note: Company names are for context on previous positions and do not represent client endorsements.
Documented Tasks (verbatim excerpts)
Performance Rating (very good)