Article Conveyance Control with Production Mode Switching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In actual production with apparatuses controlled by deep learning, the inflexibility of control parameters hinders the acquisition of sufficient learning data, leading to potential yield deterioration.
Innovation Solution
An article conveyance apparatus and method that generate a learning model using data on article weight, state, and control parameters, allowing selective operation between production and non-production modes to collect and store learning data without affecting yield, enabling flexible parameter changes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If control parameters are kept fixed during actual production, then yield is maintained, but sufficient learning data cannot be acquired
Solution Approach 1:
The system performs preliminary data collection during non-production periods when the apparatus is not actively manufacturing. Learning data is accumulated in advance during these idle periods, so that sufficient training data is available before actual production begins, eliminating the need to compromise yield for data collection purposes.
Solution Approach 2:
The system dynamically switches between production mode and non-production mode. During non-production mode, control parameters can be freely adjusted to collect diverse learning data. During production mode, the system uses the learned parameters to maintain high yield. This dynamic switching resolves the contradiction by separating data collection from production operations.
2Quantity of substance
If control parameters are flexibly changed to acquire learning data, then sufficient learning data can be acquired, but yield deteriorates
Solution Approach 1:
The system implements periodic switching between production mode and non-production mode. During non-production periods, control parameters are flexibly changed to collect learning data. During production periods, stable parameters are used to maintain yield. This periodic alternation allows both goals to be achieved at different times without compromising either.
Solution Approach 2:
The system uses its own idle time (non-production periods) to collect learning data autonomously. The apparatus serves its dual purpose of both manufacturing and self-training by utilizing periods when it is not actively producing, eliminating the need to sacrifice production output for data collection.
3Productivity
If the apparatus operates only in production mode, then yield is maximized, but learning data collection is insufficient
Solution Approach 1:
The apparatus is designed with multi-functionality, serving both as a production system and a learning data collection system. The same hardware infrastructure supports both production mode (for yield) and non-production mode (for data collection), allowing the system to fulfill multiple purposes without requiring separate dedicated equipment.
Solution Approach 2:
The system performs learning data collection in advance during non-production periods before actual production begins or during idle times. This preliminary data gathering ensures that sufficient learning data is accumulated without interrupting or reducing production output, as data collection occurs during otherwise unused time.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method of controlling an article conveyance apparatus (1) includes steps of: (A) generating, with, as learning data, information regarding an amount of charge indicating a weight value of articles that a conveyer (20) conveys to a member disposed on a downstream side, information indicating a state of the articles on the conveyer, and a control parameter for the conveyer, a learning model that estimates the control parameter to be set for conveyance of the articles having a targeted weight; (B) performing conveyance control of the articles, based on the learning model; (C) performing selective switching between a production mode involved in actual production and a non-production mode not involved in the actual production, and causing the article conveyance apparatus to operate; and (D) collecting and storing, when the article conveyance apparatus operates in the non-production mode, as the learning data, the information regarding the amount of charge actually acquired and the control parameter.