Skip to content
CauseNex

CAUSENEX

Stop Guessing Why Machines Fail.

CAUSENEX connects industrial data, causal AI, and targeted sensing to identify what is driving failures, quantify their impact, and recommend what operators should change next.

Reduce downtime. Reduce energy waste. Make better operational decisions.

EU-Hosted · Secure by Design · Hardware + Software

Constructor UniversityUniversität BremenConstructor StartHochschule BremerhavenDigital Hub IndustryBRIDGEStarthaus Bremen & BremerhavenStartup Migrants

Scroll to explore

The Problem

The €18,000 Downtime Problem

A machine failure is rarely just the cost of the repair. Lost production, urgent spare parts, labor, and operational disruption can turn a €4K repair into an €18K event.

The machine gets repaired. The reason it failed often does not.

€18K

Estimated total impact per failure

€4K repair + €14K consequential loss (3.5×)¹

¹ Cost multiple: acatech 2015, cited in Fraunhofer IPK Instandhaltung white paper, DOI 10.24406/publica-4969.

Existing Factory Data

Start With the Data You Already Have

Factories already generate valuable information. The problem is that it often lives in separate systems.

CMMS

Maintenance history and repair outcomes

ERP

Parts, labor, and financial impact

SCADA / MES

Operating conditions and process data

Existing condition monitoring

Machine-health signals

CAUSENEX connects these sources into one operational decision layer.

When existing data is not enough, CAUSENEX NERVE fills the gap.

How CAUSENEX Works

One Architecture. One Decision Layer.

CAUSENEX is designed as an integrated system so machine condition, maintenance history, operational context, and causal analysis work together instead of living in separate silos.

Existing Factory Data

ERP · CMMS · SCADA · Existing Sensors

+

Targeted NERVE Sensing

Only where additional visibility is needed

CAUSENEX Platform

Causal reasoning · Root-cause ranking · Impact analysis

Recommended Action

Causal Intelligence

Not Just What Happened — Why It Happened

CAUSENEX combines causal AI, engineering models, operational data, maintenance history, and cost information to rank likely root causes and show the evidence behind each recommendation.

Instead of just

“Motor 7 is abnormal.”

CAUSENEX helps answer

  • What is driving the problem?
  • What is it costing?
  • Did the last intervention solve it?
  • What should change next?

From anomaly detection to operational decision-making.

CAUSENEX NERVE

Targeted Sensing Where It Adds Value

CAUSENEX NERVE mounts in minutes with minimal disruption and provides high-quality machine-condition data where existing factory systems do not provide enough visibility.

Magnetic MountFast InstallationWirelessNon-Invasive

Condition Monitoring for Critical Rotating Equipment

CAUSENEX GATEWAY

One Gateway. Connected Industrial Monitoring.

The CAUSENEX Gateway securely connects deployed sensors across the site and transfers condition data to the CAUSENEX platform for analysis.

Designed for fast industrial deployment with minimal infrastructure changes.

Plug & PlaySecure Connectivity4G or LANMinimal IT Changes

Why It Is Different

From Correlation to Evidence-Backed Decisions

Traditional monitoring can detect changes in machine behavior.

CAUSENEX goes further by combining causal reasoning with engineering knowledge, historical maintenance data, and operating conditions to identify and rank likely drivers of failure.

Explainable

Evidence behind every recommendation.

EU-Hosted

Industrial data processed and hosted in the EU.

Vendor-Independent

Designed to work across manufacturers and existing industrial systems.

Research-Tested

Evaluated on controlled bearing-fault research data.

Who This Is For

Built for Industrial Teams That Need Answers, Not More Alerts

You already have data — but it is fragmented.

ERP, CMMS, SCADA, maintenance records, and condition data do not tell one coherent story.

The same failures keep returning.

Parts are replaced, but the underlying operating condition may remain unchanged.

Critical rotating equipment still lacks visibility.

Targeted sensing can fill the gaps where existing data is not enough.

Whether your factory is highly digitized or still relies on manual maintenance, CAUSENEX starts with the data and systems you already have.

Progress

Where We Stand

Causal methodology evaluated on controlled bearing-fault research data.

First NERVE hardware prototype tested on real rotating equipment.

Factory discovery interviews underway.

Design Partner Program

Become a Design Partner

CAUSENEX is currently in development, and we are working with manufacturers to validate the platform on real industrial problems.

Design partners:

Share real maintenance and operational challenges

Help shape the platform around industrial workflows

Receive priority access to pilot deployments

No cost. No commitment. A 30-minute conversation to start.

Become a Design Partner

Team

Who Is Behind CAUSENEX

Pouria Seyedi

Pouria Seyedi

Founder & CEO

M.Sc. candidate in Data Engineering at Constructor University Bremen · B.Sc. in Electrical Engineering

Leads CAUSENEX across technology and business — from causal AI and product architecture to customer discovery, partnerships, fundraising, and go-to-market strategy.

Background in electrical engineering, data engineering, and causal AI.

"Building CAUSENEX to move industrial maintenance from predicting failures to understanding what drives them and preventing recurrence."

LinkedIn
Saeid Jafariyazdi

Saeid Jafariyazdi

Hardware & Industrial Systems

M.Sc. candidate in Wind Energy Engineering, Bremerhaven University of Applied Sciences · B.Eng. Instrumentation Technology

Brings hands-on experience in industrial electrical systems, wind EPC projects, solar PV, energy storage, control engineering, sensing, and hardware development.

Focus: industrial hardware, sensing, energy systems, and CAUSENEX's expansion into the wind industry.

LinkedIn
Nasim Emami

Nasim Emami

Head of Research

M.Sc. Marine Biology, University of Bremen · Published in Scientific Reports, Nature Portfolio

Leads scientific validation, research methodology, and quantification of energy and emissions impact from CAUSENEX interventions.

Focus: scientific rigor, impact validation, and research partnerships.

LinkedInNature publication
Hosna Gholizadeh

Hosna Gholizadeh

Research Collaborator

M.Sc. Bioinformatics, University of Birmingham

Supports statistical validation, large-dataset analysis, computational research, and R-based analysis.

LinkedIn

Contact

Let Us Talk About Your Factory.

If you are dealing with recurring failures, unexpected downtime, fragmented maintenance data, or limited visibility into critical equipment, we want to hear from you. Fill out the form, and we will schedule a 30-minute discovery call to understand your challenges.

Prefer email? pouriaseyedi@causenex.com

Every repeated failure is telling you something.

CAUSENEX helps you understand what is driving it, quantify the impact, and decide what to change next.

We respond within 24 hours.