Multi-Core Numerical Controller Load Balancing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Numerical controllers for machine tools face challenges in executing a high volume of moving instruction creation processes within a short time frame, leading to increased heat generation and costs with high-frequency or multi-core processors.

Innovation Solution

A numerical controller with a multi-core processor that includes a moving instruction creation processing time estimation unit and a division unit to allocate moving instruction creation processes across cores, ensuring timely execution and improving processing performance.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If a processor with high operating frequency is employed to increase processing capacity, then processing performance is improved, but heat generated by the processor increases causing malfunction

Engineering Contradiction:
Improveprocessing capacityVSAvoidheat generated
Core Design Contradiction:
ProductivityVSTemperature

Solution Approach 1:

The invention divides the moving instruction creation process into multiple segments and assigns them to different cores of a multi-core processor. This segmentation allows parallel processing of instruction creation tasks, increasing overall processing capacity without requiring a single high-frequency processor that would generate excessive heat. Each core operates at a lower frequency while collectively achieving higher throughput.

Inventive Principle:
Principle #1Segmentation

2Productivity

If a processor with a large number of cores is employed to increase processing capacity, then processing performance is improved, but the processor becomes expensive causing overall cost increase

Engineering Contradiction:
Improveprocessing capacityVSAvoidcost
Core Design Contradiction:
ProductivityVSEase of manufacture

Solution Approach 1:

The invention implements dynamic load distribution mechanisms that adaptively assign processing tasks to available cores based on current system state and task requirements. This dynamic approach allows the system to achieve high processing capacity when needed while efficiently utilizing a moderate number of cores, avoiding the need for an excessively large core count that would increase cost. The system can scale processing capacity dynamically without linearly increasing hardware cost.

Inventive Principle:
Principle #15Dynamics

3Speed

If more moving instruction creation processes are executed within a shorter time period, then machining speed and accuracy are improved, but processing time constraints make it difficult to complete all processes

Engineering Contradiction:
Improvemachining speedVSAvoidprocessing cycle time
Core Design Contradiction:
SpeedVSLoss of time

Solution Approach 1:

The moving instruction creation process is segmented into multiple independent sub-tasks that can be executed in parallel across different cores. This segmentation enables the system to process multiple axes and paths simultaneously, completing a greater amount of processing work within the same cycle time or reducing the cycle time required, thereby achieving higher machining speed without sacrificing completeness of processing.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The invention ensures continuous utilization of all processor cores through efficient task distribution and load balancing mechanisms. By keeping all cores actively engaged in processing tasks throughout the cycle, the system maximizes processing throughput and maintains continuous useful action, enabling completion of extensive processing requirements within tight time constraints.

Inventive Principle:
Principle #20Continuity of useful action

Data Source

PatentUS9715226B2Numerical controller with multi-core processor
Publication Date: 2017.07.25 FANUC LTD
  • US9715226B2 patent drawing
  • US9715226B2 patent drawing
  • US9715226B2 patent drawing

AI summary

A numerical controller with a multi-core processor estimates moving instruction creation processing time required for creation of a moving instruction that is to be executed in a predetermined cycle on the basis of a machining instruction obtained from a machining program and divides a process for creating the moving instruction with respect to cores of the multi-core processor on the basis of the estimated processing time. Consequently, processing performance for the moving instruction creation process is improved.