MkaPEB-AI

MkaPEB-AI for smarter PEMB design.

MkaPEB-AI empowers engineers to identify the lightest code-compliant and practically constructible primary-frame solution for pre-engineered metal buildings within a few minutes.

By identifying efficient primary-frame solutions quickly, MkaPEB-AI enables engineers to evaluate different building geometry alternatives, such as bay spacing, clear height, span arrangement, and other project conditions, in a much shorter time.

The result is a faster path toward identifying an efficient building geometry together with its optimized primary-frame solution.

MkaPEB-AI Impact AI-Assisted Optimization
20%+ Reported primary-frame steel reduction compared with PEMB designs developed using conventional methods.
35%+ Reported primary-frame steel reduction compared with CSB designs developed using conventional methods.
99%+ Reported design-time reduction compared with conventional design methods.
Minutes PEMB primary-frame alternatives can be optimized and reviewed within a few minutes.
Hours Different building geometry alternatives can be evaluated and reviewed within a few hours.
Days Design reports, drawings, and bid submission documents can be prepared within a day or a few days.
The Core Problem

PEMB design includes two main connected challenges.

In PEMB projects, design efficiency depends on both the selected building geometry and the primary-frame configuration. A geometry that appears suitable may still lead to a heavy frame, while a code-compliant frame may still not be the lightest feasible solution.

Finding the most efficient main-frame design

One major challenge in PEMB design is identifying the most efficient main-frame design. A PEMB main frame includes several design variables, such as side-column section dimensions, middle-column section dimensions, rafter section dimensions, flange width, web height, flange thickness, web thickness, and geometric compatibility parameters. Each variable can have many possible candidates.

Finding a light, code-compliant, and practically constructible solution manually can require several days or even weeks. Even after this effort, there is no guarantee that the design found by the engineer is the lightest solution among all feasible options.

Evaluating different building geometries

Another major challenge in PEMB design is evaluating different building geometry conditions. Building geometry properties, such as span length, eave height, bay length, roof slope, mid-column arrangement, and support assumptions, can lead to different structural demands and different steel quantities.

Because finding a light, code-compliant, and practically constructible main-frame design is already highly time-consuming, engineers often do not have enough time to evaluate different geometry alternatives in detail. In conventional practice, usually only one geometry condition, or rarely a few alternatives, is evaluated, and there is no guarantee that the evaluated building geometry is the most efficient one.

MKA Software Solution

AI-Assisted Framework developed by MKA Software.

To deal with the main challenges in PEMB design, MKA Software developed MkaPEB-AI, an AI-assisted framework for the optimal design of pre-engineered metal building primary frames.

MkaPEB-AI empowers engineers to identify the lightest code-compliant and practically constructible primary-frame solution for a given PEMB project within a few minutes. Instead of relying only on manual trial-and-error, the system systematically searches through a large number of possible frame configurations and identifies efficient design alternatives.

By identifying efficient primary-frame solutions quickly, MkaPEB-AI also enables engineers to evaluate different building geometry alternatives, such as bay spacing, clear height, span arrangement, roof slope, mid-column arrangement, and support conditions, in a much shorter time.

As a result, engineers can move beyond evaluating only one or a few geometry conditions. MkaPEB-AI provides a faster path toward identifying an efficient building geometry together with its optimized primary-frame solution.

Identify lighter primary-frame solutions

MkaPEB-AI systematically searches through many possible primary-frame configurations to identify light, code-compliant, and practically constructible solutions that may be difficult to find through manual trial design.

Eliminate manual trial-and-error

MkaPEB-AI replaces repetitive manual trial design with automated AI-assisted optimization. Engineers no longer need to test numerous primary-frame configurations one by one; the software performs the search and presents efficient alternatives for professional review.

Evaluate more building geometry alternatives

Because MkaPEB-AI can optimize the primary frame within a few minutes, engineers can evaluate more geometry conditions, such as bay spacing, clear height, span arrangement, roof slope, and support assumptions, in a much shorter time.

Accelerate decisions while keeping engineering control

By reducing the time required for modeling, checking, revision, and comparison, MkaPEB-AI helps engineers, project managers, fabricators, and investors compare alternatives earlier. The engineer remains responsible for final review, validation, and approval.

1

Import efficient cross-section database

MkaPEB-AI begins with a database of cross-sections prepared using efficient dimensions. This helps avoid starting the search from unrealistic or inefficient section combinations.

2

Import geometry and loading properties

The system reads the building geometry, loading conditions, material properties, and relevant project parameters that affect the main-frame design.

3

Determine optimum parameter ranges

A rule-based expert system developed by MKA Software determines suitable ranges for cross-section parameters based on the project conditions. This reduces the search space before optimization begins.

4

Generate appropriate scenarios

Using the selected parameter ranges, the system generates practical main-frame design scenarios and filters unsuitable combinations.

5

Identify near-optimal solutions using RRSHC

The Random Restart with Selective Hill Climbing (RRSHC) algorithm developed by MKA Software searches for near-optimal main-frame solutions using wide-field scanning followed by narrow-field deep scanning.

For investors and owners

MkaPEB-AI helps investors and owners compare safer, more economical structural options before the project direction is fixed. By identifying efficient primary-frame solutions quickly, it supports lower steel quantities, better cost control, code-compliant decisions, and more confident selection of building geometry alternatives.

For steel structure fabricators

MkaPEB-AI helps steel structure fabricators reduce primary-frame steel tonnage by finding lighter, code-compliant, and constructible alternatives among many possible configurations. This can improve material efficiency, production planning, labor usage, energy consumption, bid competitiveness, and profit margin.

For general contractors

MkaPEB-AI helps general contractors strengthen bids through engineering value rather than only reducing profit margin or choosing the lowest-price supplier. Faster optimized alternatives support earlier pricing decisions, better coordination with fabricators and engineers, and more competitive project proposals.

For structural engineers

MkaPEB-AI helps structural engineers eliminate repetitive manual trial-and-error and identify efficient primary-frame alternatives within minutes. Engineers can evaluate more project conditions, compare geometry alternatives faster, and focus their expertise on validation, design judgment, and final approval.

White Papers

Four strategic perspectives on AI-driven PEMB optimization.

These white papers present MkaPEB-AI from different business angles: margin recovery, market expansion, engineering capacity, and bidding speed.

Reclaiming Margin: How AI-Driven Optimization Is Revolutionizing Competitive Bidding in Steel Construction

For steel fabricators, bidding is a high-stakes balance between competitiveness and profitability. This white paper explains how specialized AI optimization can help reduce material tonnage and transform bidding from margin pressure into engineering-led market advantage.

#Fabricators#Bid margin#Tonnage reduction
Read White Paper

Shattering the Monopoly: How AI-Driven Cost Optimization Is Positioning Steel as the Low-Cost Leader

This white paper discusses how AI-optimized steel buildings can compete more strongly in low-rise industrial and commercial markets where precast concrete is often perceived as the cost leader.

#Market strategy#Steel vs. precast#Expansion
Read White Paper

The Strategic Amplification of Engineering Talent: Leveraging AI as a Force Multiplier

This white paper presents MkaPEB-AI as a way to amplify engineering expertise, reduce repetitive trial design, and allow senior engineers to focus on higher-value judgment, innovation, and project leadership.

#Engineering teams#Productivity#Growth
Read White Paper

The First-Mover Advantage in PEB Bidding: Win More Projects with Speed and Precision

In competitive PEB bidding, speed can decide who wins. This white paper explains how fast, optimized, and compliant design alternatives can help fabricators submit stronger bids before competitors react.

#Bidding speed#First mover#Precision
Read White Paper

From manual trial design to AI-assisted main-frame optimization.

MkaPEB-AI transforms PEMB main-frame design from a slow trial-and-revision process into a structured AI-assisted optimization workflow. By combining engineering knowledge, a rule-based expert system, and RRSHC optimization, it helps engineers identify economical, code-compliant, and practically constructible main-frame alternatives in a much shorter time.

Request 60-Minute Demo Back to Top