A team of PCL Construction employees has been recognized as finalists in the 2025 Manufacturing Leadership Awards based on their research that transforms industrial and manufacturing construction through artificial intelligence.

The research is part of an initiative called Evolution of Model Data-Driven Planning. This initiative builds on PCL’s long-standing commitment to Manufacturing 4.0 — the integration of smart technologies leveraging AI, the Internet of Things (IoT), automation, data analytics and more to make manufacturing facilities and construction sites more efficient and connected. As a finalist in the Engineering and Production Processes category, this team is being celebrated for how it’s embracing new design and production approaches to drive game-changing process improvements.

The Evolution of Model Data-Driven Planning initiative began by recognizing the need for more innovative and repeatable planning tools. A team from PCL — including Brian Gue, manager of data science, Travis Zubick, manager of construction engineering, and Andrew Ahrendt, director of national manufacturing — developed a digital model-based planning approach to streamline project delivery.

“Our industry often deals with fragmented data — data from equipment suppliers to engineers and designers, to some we produce ourselves,” says Ahrendt. “With this digital model-based planning initiative, we’ve created a data pool, conditioned the disparate data into one platform and made it accessible and value-added for our clients.”

Think of this technology like Google Maps: When you enter a destination, Google Maps suggests the best routes based on traffic, road conditions and stops along the way. Model-based planning analyzes all available data to recommend the most effective plant layout, tailored to the project’s unique constraints and goals.

To test their approach, the team behind the initiative applied the technology on a PCL industrial project to identify the most efficient plan to route electrical raceways and cabling — the connective tissue of modern facilities. The team leveraged engineering data from tens of millions of hours to develop custom algorithms and integrate intelligent tools for logistics and scheduling. These innovations powered an advanced digital model of the industrial facility. The model used machine learning to optimize site layout, improve visualization and planning workflows, and enable digital twin functionality. It evaluated hundreds of millions of variables and constraints at once, generating the best possible plan along with clear, high-quality visual instructions for field crews — all while reducing the burden on project engineers.

This approach led to more streamlined engineering workflows and construction processes, improved labor efficiency and reduced overall costs.

The team also received positive feedback from project personnel. “We’ve found that when we give field crews a single visual that brings all the data together, it gives them real confidence in what they’re doing — buy-in from the human element is key with process improvements,” says Zubick. “Instead of trying to piece things together in their heads, our teams get everything they need right in front of them. It takes the burden of planning off their shoulders and lets them jump straight into execution.”

A key innovation behind this success is PCL’s model conditioning workflow. As Gue explains, many engineering and construction decisions — like equipment installation and cable and pipe routing — are typically made in the field during construction. By pulling these decisions into the front-end planning phase, the team can visualize and validate installation details early, which reduces risk, improves safety and increases productivity.

“Anyone can develop an algorithm,” says Gue. “What sets PCL apart is our model conditioning workflow — how we enrich and enhance the digital models of the facilities we’re constructing. These enhanced models enable the algorithmic planning of decisions that are traditionally handled in the field, solving issues long before they occur.”

This enriched modeling allows for greater certainty in planning: how long tasks will take, how much material is needed and how many labor hours are required. It also improves the quality of digital twins by visualizing scopes of work that are not typically prioritized during the planning phase, providing valuable data that can be carried into the facility’s operational life cycle.

Another differentiator for PCL is being able to develop, augment and integrate this technology in-house.

“We’ve worked hard to build the organizational muscle to execute on these types of initiatives. We use best-in-class textbook algorithms to handle some problems,” says Gue. “But we also build our in-house AI tools to reconstruct and link information from drawings and models. These are custom-built for a perfect fit with our modeling workflows, and that’s a big part of what makes this approach so effective.”

One of the most valuable outcomes of the Evolution of Model Data-Driven Planning initiative is the ability to streamline and standardize planning processes across projects.

Rather than reinventing the wheel for each new project, the PCL team is focused on identifying repeatable processes that can be supported by digital tools and enhanced through automation. This approach not only saves time but also improves consistency, quality and cost-efficiency.

“Wherever there’s repetition, we can automate,” says Ahrendt. “That leads to downstream efficiency in work packaging, planning and installation, which means higher-quality and more cost-effective projects.”

While the initial case study focused on electrical elements, the team sees much broader potential. “We’re just scratching the surface,” says Gue. “Because our digital models are enhanced and on our own algorithmic platform, we can apply similar approaches to other scopes of work.” 

Ultimately, the goal is to deliver greater value to clients by reducing waste, improving planning accuracy and enabling faster, more predictable project execution with lower risk. With each project, the system gets smarter, bringing PCL one step closer to a fully integrated, data-driven future.

The innovative approach to advanced digital model-based planning is now being expanded across PCL’s industrial and manufacturing projects. The team’s goal is to standardize and replicate this data-driven process across future builds. “PCL has had to challenge the process to help our clients, our people and the industry,” says Ahrendt. “We’re always looking for tools and processes to make the industry better and increase value to our clients and stakeholders.”

By turning inconsistent, incomplete data into a repeatable, intelligent system, PCL is enabling life cycle-spanning models that support everything from master planning to predictive analysis and digital twins for plant operations. It’s all part of a commitment that delivers exceptional value for clients — and one that keeps PCL on the cutting edge of construction innovation.