LG CNS Factova is designed to connect the machines, software and production data already operating inside a factory, giving manufacturers a foundation for predictive maintenance, digital twins and AI-driven decision-making.
For manufacturers considering factory AI, the practical questions begin with the equipment already on the shop floor. Can the platform connect machines from different suppliers? Will it work with existing production software? And how will the factory know whether its recommendations are reliable?
LG CNS brought its Factova smart factory platform to IMTS 2026 with those challenges in view. Its offering includes Factova Control for equipment data integration, Factova Worldworks for digital twin simulation and Factova MES for manufacturing execution.
Bryce Barnes brings extensive experience in the technologies behind that proposition. During a 21-year career at Cisco, he developed its IoT connected machine business, worked with machine builders and supported secure digital CNC programme uploads. He later held principal product and programme management roles at Microsoft, working on Cloud for Manufacturing, Azure IoT and industrial generative AI solutions.
A mechanical engineering graduate and former board member of the MTConnect Institute, Barnes has worked across industrial connectivity, manufacturing data and applied AI. We asked him how Factova works in plants with mixed equipment, established software and production teams who need measurable results.
At IMTS, LG CNS brought Factova to North American manufacturers. What is the biggest difference between deploying the platform inside an LG Group factory and deploying it into an independent plant with a mixed legacy equipment base?
Bryce Barnes:
The biggest difference is not the technology itself. It’s the operating environment.
Within LG Group facilities, there is generally a higher degree of process and system standardization. Independent manufacturers often operate a much more complex environment with equipment, software, and operational workflows accumulated over many years from multiple vendors.
What makes Factova valuable is that it was designed for both scenarios. Our approach is not to replace existing investments. Instead, we connect and integrate heterogeneous environments through ISA-95-based architecture, creating a unified foundation for manufacturing intelligence, digital twins, and AI-driven decision-making.
Manufacturers do not need to replace everything to build a smart factory.
Factova Control standardizes data across equipment from different manufacturers. How difficult is that normalization layer in practice, and is it the foundation that makes the predictive AI possible?
Bryce Barnes:
Absolutely.
In manufacturing, equipment from different suppliers often generates data in different formats, protocols, and structures. Without a common data model, AI cannot reliably identify patterns or generate meaningful recommendations.
Factova Control creates that common operational language across the factory. Once data is normalized and connected, we can apply AI consistently across production lines, equipment types, and manufacturing processes.
Data standardization is not just part of the solution. It is the foundation that makes predictive AI possible.
The platform analyzes current, temperature and vibration to flag early warning signs and predict failures. How do you validate those predictions and control false alarms across more than 100,000 connected pieces of equipment?
Bryce Barnes:
Predictive AI is most effective when combined with operational expertise.
We continuously compare AI-generated insights against real equipment behavior, maintenance records, and operational outcomes. This feedback process helps improve model accuracy over time.
Our objective is not to create more alarms. It is to reduce uncertainty and provide actionable intelligence. Success is measured by helping maintenance teams prioritize the right interventions, reduce unplanned downtime, and improve asset reliability while minimizing unnecessary maintenance activities.
How does Factova Worldworks use the digital twin together with live production data? Can AI test alternative layouts, schedules or process decisions virtually before recommending a change to the real factory?
Bryce Barnes:
That is exactly where we see digital twins creating significant value.
Factova Worldworks synchronizes real factory data with a virtual factory environment, creating a continuously connected digital representation of operations.
This allows manufacturers to evaluate different layouts, production scenarios, logistics flows, resource allocations, and operational strategies before making changes on the factory floor.
We believe the future of manufacturing is moving toward an “optimize before you invest” model, where simulation and AI help validate decisions before physical implementation.
Factova MES applies AI to equipment utilization, workforce activity and material usage. What decisions can it recommend today, and which decisions can it actually execute automatically?
Bryce Barnes:
Today, Factova MES can support decisions related to production planning, resource utilization, production performance, quality management, and operational efficiency.
The level of automation depends on each customer’s environment and governance requirements.
Many manufacturers currently prefer a human-in-the-loop model, where AI provides recommendations while operational teams retain final decision authority.
Over time, we expect AI to play a larger role in orchestrating and optimizing manufacturing operations. However, our focus remains on delivering measurable business value while maintaining operational reliability and governance.
For a manufacturer that already has MES, SCADA and maintenance systems, can Factova sit above the existing stack, or does the strongest value come from replacing and standardizing those systems?
Bryce Barnes:
Factova was specifically designed to work with existing manufacturing environments.
Most manufacturers have already invested heavily in MES, automation platforms, maintenance systems, and operational technologies. We respect those investments.
Our objective is not a “rip-and-replace” strategy. Instead, we help customers create greater connectivity, visibility, and intelligence across existing systems.
In many cases, the fastest path to value comes from integrating and enhancing what’s already in place with AI, Digital Twin, and advanced manufacturing intelligence capabilities.
What does a credible ROI case look like for a North American plant, and how quickly can a customer move from a pilot on a few assets to a factory-wide deployment?
Bryce Barnes:
A successful ROI case typically focuses on measurable operational outcomes.
Examples include reducing unplanned downtime, improving productivity, increasing equipment utilization, enhancing quality performance, and reducing operational inefficiencies.
Most manufacturers begin with a targeted pilot addressing a specific business problem. Once measurable value is demonstrated, they can expand incrementally across additional production lines, facilities, and manufacturing operations.
The key is not implementing technology for its own sake. The goal is achieving business outcomes that justify broader deployment.
Where do you see Factova heading next: more autonomous production control, agentic AI coordinating multiple factory systems, or deeper physical-AI links between software, robots and machines?
Bryce Barnes:
We believe all three areas will play important roles.
Our vision is built around three intelligence layers:
AX (AI Intelligence) to provide orchestration, analytics, and decision support
VX (Virtual Intelligence) to simulate, validate, and optimize operations through digital twins
RX (Robot Intelligence) to enable increasingly autonomous interaction with physical assets
Over the next several years, we expect manufacturing environments to become more connected, more intelligent, and increasingly autonomous. Agentic AI will serve as the coordinator between digital systems, virtual environments, and physical operations.
Ultimately, the future factory will not simply collect data. It will continuously learn, predict, optimize, and take action across the manufacturing ecosystem.
MTN Analysis
Barnes’s emphasis on existing equipment is particularly relevant to machine tool users. Most plants will introduce AI into a manufacturing environment built through years of investment, with different controls, software and ways of collecting production data.
Factova’s ability to integrate that environment will be central to its value. The common data model Barnes describes is what allows information from individual assets to support decisions across production and maintenance.
For machine tool users, LG CNS Factova will ultimately be judged on how effectively it connects existing equipment and turns that data into useful production decisions.
His answers also show where manufacturers will need to get specific during a pilot. The interview provides no fixed rollout timescale, prediction accuracy figure or false-alarm rate. Those measures need to be established against the customer’s equipment and operating conditions, alongside the permissions governing any automated action.
For a machining business, a starting point could be a cell where recurring downtime affects delivery. Demonstrating that the platform helps maintenance teams intervene earlier, with fewer unnecessary interventions, would create a clear case for expanding it.
The longer-term ambition brings agentic AI, simulation and robotics together. The immediate buying decision will rest on how well Factova connects the plant and whether the resulting recommendations improve production.
FAQs
What is LG CNS Factova?
LG CNS Factova is LG CNS’s smart factory platform, combining equipment data integration, digital twin simulation and manufacturing execution capabilities.
Can Factova work with existing machines and factory software?
Barnes says Factova is designed to integrate equipment from different suppliers and work with existing manufacturing systems. The specific compatibility and integration requirements will depend on the plant.
Does Factova operate manufacturing processes autonomously?
The level of automation depends on the customer’s environment and governance requirements. Barnes says many manufacturers currently use AI recommendations while retaining final operational decision authority.
