Antenna Path Study Using ML for Reliable Private Network Links

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Traditional path studies in industrial automation systems rely on outdated and incomplete site information, requiring manual human intervention and lacking flexibility in optimizing antenna locations and designs for efficient communication paths.

Innovation Solution

Implementing machine learning to perform automated path studies using site data, allowing data radios or web services to identify optimal communication paths based on network performance requirements and predicted signal quality, eliminating the need for manual tasks and enhancing flexibility.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual path studies are performed by human operators using outdated site information, then the process can be completed with existing resources, but the accuracy and reliability of communication path optimization deteriorates

Engineering Contradiction:
Improvecommunication path reliabilityVSAvoidsite information completeness
Core Design Contradiction:
ReliabilityVSLoss of information

Solution Approach 1:

The system performs preliminary actions by automatically collecting and storing current site information in databases before path study is needed. This includes gathering topographic data, existing infrastructure information, and environmental data in advance, so that when a path study is required, accurate and up-to-date information is already available without relying on outdated manual records.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system enables self-service by allowing automated path studies to be performed without human operator intervention. The machine learning model automatically analyzes site data, evaluates multiple communication path options, and generates optimization recommendations, eliminating the need for manual path studies that are constrained by human availability and outdated information.

Inventive Principle:
Principle #25Self-service

2Productivity

If manual path studies are performed by human operators, then the system can operate with existing manual processes, but the productivity and speed of path study execution deteriorates

Engineering Contradiction:
Improvepath study execution speedVSAvoidpath study automation level
Core Design Contradiction:
ProductivityVSExtent of automation

Solution Approach 1:

The system replaces the mechanical manual process of path studies with an automated computational system. Instead of human operators manually analyzing site information and determining communication paths, a machine learning model automatically performs the analysis by processing site data through algorithms that evaluate signal propagation, identify optimal paths, and generate recommendations, dramatically increasing execution speed and consistency.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system changes key parameters by transitioning from static, outdated site information to dynamic, real-time data collection. The automated system continuously updates site data including environmental conditions, infrastructure changes, and topographic information, allowing path studies to reflect current conditions rather than relying on obsolete manual records.

Inventive Principle:
Principle #35Parameter changes

3Adaptability or versatility

If manual path studies are performed, then the process can follow established manual procedures, but the adaptability to new information and site changes deteriorates

Engineering Contradiction:
Improvepath study flexibilityVSAvoidtime to update path studies
Core Design Contradiction:
Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system implements feedback mechanisms that automatically detect and respond to changes in site conditions. When new information becomes available or site conditions change, the system receives feedback through updated sensor data, modified site records, or changed environmental parameters, and automatically re-evaluates communication paths to provide updated optimization recommendations, maintaining adaptability without manual intervention.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system transitions from static manual path studies to dynamic automated analysis. The machine learning model can continuously or periodically re-run path studies as new site data becomes available, allowing the system to adapt to changing conditions in real-time rather than relying on fixed manual procedures that are difficult to update.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP4440198A1Path study and antenna locating systems and methods
Publication Date: 2024.10.02 SCHNEIDER ELECTRIC SYSTEMS USA INC
  • EP4440198A1 patent drawingFigure 1
  • EP4440198A1 patent drawingFigure 2
  • EP4440198A1 patent drawingFigure 3

AI summary

Method and system for automating a path study to establish a private network between an access point and a remote asset along an optimal path. A predictive model identifies potential communications paths between the access point and the remote asset based on site data. The potential communications paths each specifies at least one antenna parameter. The machine learning also includes selecting the optimal path from the potential communications paths based at least in part on the network performance requirements of the private network and predicted signal quality along the potential communications paths using the antenna parameter.