Gear Tooth Contact Adjustment Using ML-Based Shim Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for adjusting tooth contact position in gear assemblies, such as bevel and worm gears, are inefficient and time-consuming, particularly for inexperienced workers, as they require trial and error with shims to correct dimensional errors, leading to productivity losses and potential wear issues.
Innovation Solution
A machine learning-based system that estimates the optimal tooth contact position adjustment amount by learning from dimensional data of gear parts, allowing for pre-assembly determination of shim thickness or number, thereby streamlining the assembly process and reducing worker load.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If trial and error method with shims is used to adjust tooth contact position, then tooth contact can be optimized, but it takes much time and reduces productivity
Solution Approach 1:
The system performs preliminary calculation of the optimal shim thickness or number before assembly by using a learned model that processes dimensional data of parts. This allows the tooth contact position adjustment amount to be determined in advance, eliminating the need for time-consuming trial and error adjustments during the assembly process.
2Manufacturing precision
If tooth contact adjustment is performed after assembly, then accurate tooth contact can be achieved, but assembly productivity decreases due to disassembly and reassembly steps
Solution Approach 1:
The adjustment amount (shim thickness or number) is calculated and determined before the assembly process begins. By using the learned model to process dimensional data and predict the optimal adjustment, the system enables workers to prepare the correct shim in advance, allowing assembly to proceed smoothly without subsequent disassembly and reassembly operations.
3Manufacturing precision
If experienced workers determine tooth contact adjustment manually, then accurate adjustment can be achieved, but unexperienced workers require much more time
Solution Approach 1:
The system enables self-service by using the learned model to automatically calculate and determine the optimal shim thickness or number based on dimensional data of parts. This eliminates the need for workers to rely on personal experience or expertise, as the system provides accurate adjustment recommendations that any worker can follow, thereby standardizing the quality of adjustment across different skill levels.
Solution Approach 2:
The system replaces the mechanical decision-making process of experienced workers with an automated information processing system. The learned model processes dimensional data and outputs the optimal adjustment amount, substituting human expertise with an automated computational approach that provides consistent and accurate results regardless of worker experience.
4Manufacturing precision
If iterative shim insertion and adjustment is performed, then optimal tooth contact can be achieved, but the process becomes time-consuming and complex
Solution Approach 1:
The system performs the complex calculation and optimization process in advance by using the learned model to process dimensional data and directly output the optimal shim thickness or number. This eliminates the need for iterative adjustment cycles, as the correct adjustment amount is determined before assembly begins, thereby simplifying the overall process while maintaining optimization accuracy.
Data Source
AI summary
A tooth contact position adjustment amount estimation device that performs processing with respect to estimating a tooth contact position adjustment amount for dimensional data of parts constituting a power transmission mechanism according to the present invention, comprising: a machine learning device that performs processing with respect to estimating the tooth contact position adjustment amount for the dimensional data of parts constituting the power transmission mechanism, wherein the machine learning device observes part dimensional data, which is the dimensional data of parts constituting the power transmission mechanism, as a state variable indicating a current state of an environment, and performs processing with respect to estimating the tooth contact position adjustment amount for the dimensional data of parts constituting the power transmission mechanism in assembling the power transmission mechanism by performing processing with respect to machine learning based on the observed state variable.