Robot Workcell Planning to Cut Waiting and Duplicate Tasks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial robotics systems face inefficiencies due to nonvalue-added steps in manufacturing processes, such as waiting times and duplicate tasks, which lead to increased energy use, machine breakage, and reduced productivity.
Innovation Solution
A computer-implemented method using machine learning to analyze industrial activity data and robotic machine configuration information to generate a production plan that optimizes step assignments and reduces nonvalue-added tasks, thereby improving the efficiency of robotic machine collaboration on an industrial floor.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If robotic machines perform multiple industrial activities, then productivity increases, but nonvalue-added steps (waiting times, duplicate tasks) increase leading to energy waste and machine breakage
Solution Approach 1:
The patent segments industrial activities into discrete steps and assigns them to specific robotic machines based on capability matching. This segmentation allows the system to eliminate nonvalue-added steps by ensuring each step is performed by the most suitable machine, reducing waiting times and duplicate tasks while maintaining high productivity.
Solution Approach 2:
The patent implements dynamic assignment of steps to robotic machines based on real-time capability assessment and performance data. The system continuously adapts the allocation of tasks to match current machine states, capabilities, and workloads, optimizing energy utilization and eliminating wasteful operations while maximizing productivity.
2Productivity
If robotic machines perform multiple industrial activities, then productivity increases, but nonvalue-added steps (waiting times, duplicate tasks) increase leading to machine breakage
Solution Approach 1:
By segmenting activities into discrete steps and assigning them to specialized robotic machines, the system reduces the frequency of machine idle waiting and duplicate operations. This specialized assignment decreases unnecessary start-stop cycles and reduces wear and tear, thereby improving reliability and reducing machine breakage while maintaining productivity.
Solution Approach 2:
The patent incorporates feedback mechanisms that monitor machine performance, workload, and operational status in real-time. This feedback enables the system to dynamically adjust task allocation to prevent overloading machines, balance workloads evenly, and avoid conditions that lead to excessive wear and machine breakage, thereby improving reliability.
3Productivity
If machine learning model analyzes industrial activity data and configuration information, then step assignment optimization improves, but computational complexity and data processing requirements increase
Solution Approach 1:
The patent segments the complex optimization problem into manageable components: activity step identification, robotic machine capability profiling, and step-to-machine assignment. The machine learning model processes data in these segmented stages, analyzing industrial activity data and configuration information separately before integrating results. This segmentation reduces computational complexity by breaking down the overall problem into smaller, more tractable sub-problems while still achieving optimal step assignments.
Data Source
AI summary
Described are techniques for optimizing collaborative work performed by robotic machines in an industrial environment. The techniques include obtaining industrial activity data comprising steps of industrial activities performed by robotic machines on an industrial floor. The techniques further include obtaining robotic machine data comprising configuration information of the robotic machines associated with performing the steps of the industrial activities. The techniques further include inputting the industrial activity data and the robotic machine data to a machine learning model to analyze the steps of the industrial activities in view of the configuration information of the robotic machines to generate a production plan that aggregates performance of selected steps by the robotic machines, and configuring the robotic machines on the industrial floor according to the production plan generated by the machine learning model.