In-Production Robot Parameter Optimization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing robotic assembly systems with force control require tedious and time-consuming offline optimization of parameters, which may not accurately reflect production environment variations, leading to suboptimal assembly performance.

Innovation Solution

A system that uses an industrial robot and a computing device to continuously optimize assembly parameters during production by learning new starting positions and parameters through predefined runs, allowing for real-time adaptation and verification.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If offline parameter optimization is performed prior to production, then parameter selection can be completed before continuous assembly begins, but the optimization results do not accurately reflect production environment variations and manufacturing differences

Engineering Contradiction:

Improveaccuracy of optimization resultsVSAvoidtime for parameter optimization

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary teaching of starting positions for parts before continuous production begins. This preliminary action captures the actual production environment characteristics and manufacturing variations, enabling the optimization algorithm to learn from real data while minimizing disruption to ongoing production.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The robotic assembly system performs self-optimization by automatically collecting assembly results during continuous production and using this data to refine its own parameters. The system serves itself by learning from its own operational data without requiring external intervention or separate optimization experiments.

Inventive Principle:

Principle #25Self-service

2Manufacturing precision

If traditional force control assembly is used without in-production optimization, then assembly process is simpler to implement, but assembly accuracy is suboptimal due to inability to adapt to manufacturing variations

Engineering Contradiction:

Improveassembly accuracyVSAvoidcomplexity of optimization system

Core Design Contradiction:

Manufacturing precisionVSDevice complexity

Solution Approach 1:

The system implements feedback by continuously monitoring assembly results during production and using this information to adjust force control parameters. The feedback loop compares actual assembly outcomes with expected outcomes and automatically refines parameters to improve accuracy while maintaining production continuity.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The optimization parameters are made dynamic rather than static. The system continuously adapts force control parameters based on real-time production data, allowing the assembly process to dynamically respond to manufacturing variations in parts rather than relying on fixed pre-determined parameters.

Inventive Principle:

Principle #15Dynamics

3Adaptability or versatility

If offline optimization experiments are conducted with limited parts, then experimentation resources are conserved, but the optimization results cannot account for production-related parameters such as assembly starting position variations

Engineering Contradiction:

Improveability to handle production variationsVSAvoidtime for learning runs

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system performs optimization continuously during production rather than interrupting production for separate optimization experiments. The learning runs are integrated into the continuous assembly process, allowing parameter optimization to occur concurrently with production without stopping the assembly line.

Inventive Principle:

Principle #20Continuity of useful action

Solution Approach 2:

The robotic system performs multiple functions simultaneously: it conducts optimization experiments and maintains continuous production assembly. The same robotic assembly cell serves dual purposes of manufacturing parts and learning optimal parameters, eliminating the need for separate dedicated experimentation resources.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS9108316B2Method and system for in-production optimization of the parameters of a robot used for assembly

Publication Date: 2015.08.18 ABB RES LTD

AI summary

A robot is used to repeatedly assemble parts during a continuous production run of parts to be assembled. There are parameters of the robot associated with the assembly. These parameters are used to assemble the parts. Simultaneously with that repeated assembly the robot parameters are optimized. The parts to be assembled have a starting position for the assembly and the simultaneous optimization of the robot assembly parameters also includes the learning of the starting position. The robot assembly parameters can be optimized in a predefined manner. The optimized parameters can then be verified and the optimized and verified robot assembly parameters may then be used in place of the parameters of the robot associated with the parts assembly along with the learned starting position.