Tightening Tool Classification Using Torque Spectrum Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Determining the correctness of tightening results for fasteners using a tightening tool is challenging and time-consuming for human operators and machines, as undesired outcomes like disengage, socket slip, stick slip, thread lock, and high rundown torque can occur, making it difficult to assess the quality of the tightening operation.
Innovation Solution
A method involving the acquisition of time-domain and frequency-domain representations of torque and angle values, training a machine-learning model to identify tightening classes, and providing alerts for incorrect operations, using techniques like FFT and neural networks or random forest-based classification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If human operators or machines manually analyze sensor data to determine tightening results, then measurement can be performed, but the process is difficult, burdensome and time consuming
Solution Approach 1:
The patent replaces manual human analysis with an automated machine-learning-based classification system. The system automatically processes sensor data from tightening operations, classifies tightening results into predefined classes, and provides feedback without human intervention, thereby eliminating the time-consuming and burdensome manual analysis process while maintaining measurement accuracy
Solution Approach 2:
The tightening tool incorporates an integrated classification system that automatically evaluates its own tightening results using sensor data and machine learning models. The system self-diagnoses tightening quality, identifies deviations from desired outcomes, and provides feedback without requiring external human operators, enabling the system to serve itself in the assessment process
2Ease of manufacture
If only time-domain representations are used for training the machine-learning model, then the model can be trained with basic torque data, but frequency-domain characteristics which provide additional insight are not utilized
Solution Approach 1:
The patent combines multiple data representations (time-domain torque data and frequency-domain torque characteristics) into a unified training dataset for the machine-learning model. By merging these complementary information sources, the system captures both the temporal progression of torque application and the spectral characteristics of the tightening process, providing the model with comprehensive features for accurate classification without significantly complicating the manufacturing process
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Facilitates accurate and efficient classification of tightening operations, enabling operators to correct improper tightening, thereby ensuring the durability of fasteners and preventing issues like unscrewing, by providing clear alerts and improving the robustness of classification through frequency-domain analysis.
Implementation Method 1
the acquiring of frequency-domain representations of the observed sets of torque values for the fasteners having been tightened by the tightening tool further comprises acquiring frequency-domain representations of the observed sets of angle values for the fasteners having been tightened
Data Source
AI summary
A method for determining a tightening class of a tightening operation performed by a tightening tool is provided. The method comprises acquiring time-domain representations of sets of observed torque and angle values for fasteners having been tightened by the tightening tool, acquiring frequency-domain representations of the observed sets of torque values, associating a tightening class with each acquired time-domain and frequency-domain representation identifying a tightening operation, training a machine-learning model with the acquired time-domain representations and frequency-domain representations and the tightening class and supplying the trained machine-learning model with a further acquired time-domain representation frequency-domain representation for a fastener having been tightened by the tightening tool, wherein the trained machine-learning model outputs an estimated tightening class for the supplied set of observed torque and angle values.