Weld Impact Quality Recognition Using Ultrasonic Acoustic Signals

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for determining the quality of ultrasonic impact treatment on welds struggle to accurately quantify the stress relief and quality due to the complexity of acoustic signals generated during the process, leading to inconsistent results and potential weld deformation or cracking.

Innovation Solution

A method utilizing smart acoustic information recognition, involving an ultrasonic impact gun, strain-gage measurement, and a multi-weight neural network to analyze acoustic signals, calculates stress relief ratios and determines impact quality by constructing neuron models to differentiate between qualified and unqualified treatment based on acoustic feature extraction and filtering.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional methods are used to measure and quantify ultrasonic impact treatment parameters (processing speed, pressure, angle, steel type, thickness), then direct control of treatment parameters is possible, but measurement and quantification during operation become difficult and inaccurate

Engineering Contradiction:
Improvemeasurement precision of treatment parametersVSAvoiddifficulty of measuring treatment parameters during operation
Core Design Contradiction:
Measurement precisionVSDifficulty of detecting and measuring

Solution Approach 1:

The patent replaces direct mechanical measurement of treatment parameters (pressure, speed, angle) with acoustic signal analysis. By substituting the mechanical measurement system with an acoustic detection system, the patent achieves indirect measurement that is easier to implement during operation and provides more consistent results. The acoustic signals generated during ultrasonic impact treatment contain information about the treatment parameters, allowing for non-contact, real-time monitoring without the complexity of direct mechanical sensors.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces acoustic signals as an intermediary to measure treatment parameters. Instead of directly measuring difficult-to-quantify parameters like pressure and speed, the system measures the acoustic signals generated during treatment, which serve as a mediator containing information about these parameters. This intermediary approach transforms the measurement problem from directly measuring hard-to-access physical quantities to analyzing audible acoustic characteristics.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If acoustic signal analysis is used to determine impact quality, then non-contact and damage-free quality assessment is achieved, but the complexity of acoustic signal processing increases

Engineering Contradiction:
Improvereliability of quality assessmentVSAvoidcomplexity of acoustic signal processing system
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent extracts specific feature parameters from the complex acoustic signals, such as energy, zero-crossing rate, and spectral characteristics. By taking out only the most relevant features from the full acoustic signal spectrum, the system reduces processing complexity while maintaining assessment reliability. This selective extraction approach filters out redundant information and focuses computational resources on the most diagnostic signal characteristics.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent transforms the acoustic signals from time-domain waveforms into frequency-domain representations through Fourier transform and other signal processing techniques. By changing the parameter domain from time to frequency, the patent makes the signals more amenable to analysis and pattern recognition. This parameter transformation simplifies the detection of treatment quality indicators that are more apparent in the frequency domain than in the raw time-domain signals.

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If comprehensive acoustic signal features are analyzed to improve quality determination accuracy, then recognition accuracy reaches 95% or more, but the computational complexity and processing time increase

Engineering Contradiction:
Improvequality determination accuracyVSAvoidprocessing time for quality assessment
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary processing of acoustic signals during the treatment process itself, extracting features and preparing data for analysis in real-time. By conducting signal processing operations as the ultrasonic impact treatment proceeds, rather than waiting until after treatment completion, the patent reduces the overall assessment time. This preliminary action ensures that when quality determination is needed, the processing is already substantially complete or can be rapidly finalized.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent implements a multi-level analysis approach where basic quality assessment can be performed using a subset of acoustic features for rapid evaluation, while more comprehensive analysis using all features is available when higher accuracy is needed. This partial action approach allows the system to provide timely results using only the most critical features when speed is paramount, while achieving 95%+ accuracy when full analysis is performed, thus balancing time and accuracy requirements.

Inventive Principle:
Principle #16Partial or excessive action

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

This approach allows for quick and accurate judgment of stress treatment quality without damaging the weldment, significantly improving the reliability and quality of the welding process by achieving a recognition accuracy of 95% or more.

Implementation Method 1

Ultrasonic impact equipment uses high-power energy to push the impact head at a rate per second the frequency of about 20,000 times impacts the surface of metal objects, and the high-frequency, high-efficiency and large energy under focus make the metal surface produces a large compression plastic deformation

Methodology Applied
Scientific EffectUltrasonic vibration: Ultrasonic Vibration

Implementation Method 2

a resistance strain-gage is used as a sensitive element for measurement, and an indentation is made at a center of a strain rosette by impact loading; the strain-gage records the change of strain increment in an elastic area outside an indentation area, so as to obtain a true elastic strain corresponding to a residual stress

Methodology Applied
Scientific EffectStrain measurement: Elasticity

Implementation Method 3

Because the time-frequency domain characteristics of the ultrasonic shock sound signal during operation contain a lot of information, these sound signal characteristics are a comprehensive manifestation of external factors during the operation and determine the quality of ultrasonic shock

Methodology Applied
Scientific EffectAcoustic emission: Acoustic Emission

Data Source

PatentUS11927563B2Smart acoustic information recognition-based welded weld impact quality determination method and system
Publication Date: 2024.03.12 NANTONG UNIV
  • US11927563B2 patent drawing
  • US11927563B2 patent drawing
  • US11927563B2 patent drawing

AI summary

A smart acoustic information recognition-based welded weld impact quality determination method and system, comprising: controlling a tip of an ultrasonic impact gun (1) to perform impact treatment on a welded weld with different treatment pressures, treatment speeds, treatment angles and impact frequencies, obtaining acoustic signals during the impact treatment, calculating feature values of the acoustic signals, and constructing an acoustic signal sample set including various stress conditions; marking the acoustic signal sample set according to impact treatment quality assessment results for the welded weld; establishing a multi-weight neural network model, and using the marked acoustic signal sample set to train the multi-weight neural network model; obtaining feature values of welded weld impact treatment acoustic signals to be determined, inputting the feature values into the trained multi-weight neural network model, and outputting determination results for welded weld impact treatment quality to be determined.