Intelligent weld flaw detection detector based on ultrasonic waves

Abstract

The invention discloses an ultrasonic-based intelligent weld flaw detection detector which comprises a detector, an operation button, an image display screen and a result display screen, wherein a controller is arranged in the detector; a probe; a detection system and an analysis system are arranged in the controller; the detection system is based on an ultrasonic probe and comprises an ultrasonic transmitting and receiving device; the analysis system comprises an acquisition and conversion module, a data processing module, an intelligent diagnosis module, a data storage and management module, an image generation and labeling module, a sharing module and a system self-inspection and calibration module. Compared with the prior art, the method has the advantages that intelligent diagnosis is coordinated with a database, defects are efficiently distinguished, and manual dependence is reduced; all the modules cooperate accurately, and defect details are positioned accurately; data management is convenient, and storage and sharing are orderly; the visualization is strong, and the image annotation is clear and visual. And the reliability is high, and stable operation is ensured through self-checking calibration.

Description

Technical Field

[0001] The present invention relates to the technical field of weld detection, and specifically refers to an intelligent weld flaw detector based on ultrasonic waves. Background Art

[0002] In modern industrial production, welding is an extremely common and crucial connection process, widely used in many industries such as machinery manufacturing, construction engineering, petrochemical industry, etc. The quality of welds is directly related to the safety, reliability, and service life of the entire structure or product. Traditional weld detection methods mainly include visual inspection, radiographic testing, magnetic particle testing, etc. Visual inspection can only detect obvious surface defects; although radiographic testing can detect internal defects, it has radiation hazards, expensive equipment, and complex operations; magnetic particle testing is only applicable to the weld detection of ferromagnetic materials and has certain limitations.

[0003] Ultrasonic testing occupies an important position in the field of weld detection due to its non-invasive, harmless to the human body, high detection sensitivity, relatively low cost, etc. However, there are still many deficiencies in the use of traditional ultrasonic flaw detectors. For example, the analysis of detection data mostly relies on manual experience, requires high professional qualities of detection personnel, and manual judgment is prone to errors and subjective judgments. At the same time, the data processing and storage functions are relatively single, making it difficult to meet the efficient management and subsequent analysis needs of large-scale detection data. In addition, traditional flaw detectors also lack in the visual display of detection results and data sharing with other devices, which is not conducive to the construction of an intelligent and automated welding quality control system. Summary of the Invention

[0004] The present invention aims to solve the above technical problems and provides an intelligent weld flaw detector based on ultrasonic waves, which can be widely applied to many fields involving weld quality detection such as industrial manufacturing, construction, pipeline installation, etc.

[0005] To solve the above technical problems, the technical solution provided by the present invention is: an intelligent weld flaw detector based on ultrasonic waves, including:

[0006] A detector, having a rectangular structure, with operation buttons, an image display screen, and a result display screen, and a controller is provided inside, and a connector is provided above the detector;

[0007] A probe head, used to contact the weld to be detected, and one end is connected to a wire, and the other end of the wire is provided with a plug for connecting to the connector;

[0008] The controller includes a detection system and an analysis system;

[0009] The detection system based on the ultrasonic probe includes:

[0010] An ultrasonic transmitting and receiving device is used to transmit ultrasonic waves to a weld and receive the reflected echo signals;

[0011] The analysis system described above includes:

[0012] An acquisition and conversion module is used to acquire the echo signals received by the ultrasonic probe and convert them into digital signals;

[0013] A data processing module filters, amplifies, and extracts features from the converted digital signals;

[0014] An intelligent diagnosis module diagnoses weld defects based on the feature parameters extracted by the data processing module, using a pre-trained intelligent algorithm model, and can automatically identify the types of defects.

[0015] Furthermore, the analysis system also includes a data storage and management module, which is used to store the original data obtained by the detection system, the data during the processing of the intelligent analysis system, and the final diagnostic result data;

[0016] Furthermore, it also includes an image generation and annotation module, which generates a weld cross-section image based on the detection results, directly displays it on an image display screen, and accurately marks the position, shape, and size information of the defects on the image after passing through the analysis system. The annotation information uses a standardized graphic and text format and is displayed on the result display screen.

[0017] Furthermore, a sharing module is also included in the controller, which transmits to a remote terminal or other related devices in a wireless or wired manner.

[0018] Furthermore, a system self-check and calibration module is also included in the controller, which is used to automatically detect and calibrate each component and function of the system before detection or regularly, including the performance of the ultrasonic transmitting and receiving device, the signal conversion accuracy, and the accuracy of the data processing algorithm.

[0019] Furthermore, it also includes a support frame, specifically a U-shaped structure, which is rotatably connected to both sides of the detector, and an anti-slip silica gel pad is provided at the bottom of the detector.

[0020] The advantages of the present invention compared with the prior art are as follows:

[0021] 1. High degree of intelligence

[0022] The intelligent weld flaw detector of the present invention adopts an intelligent diagnosis module, which can automatically identify the types of defects, reduces the dependence on manual experience, improves the accuracy and objectivity of the detection results. Through the pre-trained intelligent algorithm model, it can quickly and accurately analyze weld defects, greatly improving the detection efficiency. At the same time, the introduction of the database module further enriches the basis for intelligent diagnosis and improves the accuracy of diagnosis.

[0023] 2. High detection accuracy

[0024] The ultrasonic transmitting and receiving device of the detection system can accurately control the transmitting parameters of ultrasonic waves. After receiving the echo signal, through the fine processing of the acquisition and conversion module and the data processing module, accurate characteristic parameters are extracted, and then diagnosed by the intelligent diagnosis module, so as to accurately determine the position, shape and size of the defect, providing a reliable basis for the weld quality assessment.

[0025] 3. Convenient data management and sharing

[0026] The data storage and management module can effectively manage a large amount of detection data, facilitating data query, statistics and analysis. The sharing module realizes the rapid transmission and sharing of detection data and results, facilitating integration with other devices or systems, which is conducive to building an intelligent welding quality control network and improving the coordination and efficiency of production management. The historical data and standard data stored in the database module also provide more dimensional support for data management and analysis.

[0027] 4. Good visualization effect

[0028] The weld cross-section image generated by the image generation and annotation module and the annotated defect information are intuitively displayed on the display screen, enabling the detection personnel to quickly and clearly understand the weld quality situation. Even non-professional technical personnel can relatively easily understand the detection results, facilitating on-site operation and decision-making.

[0029] 5. Strong reliability

[0030] The system self-check and calibration module regularly detects and calibrates the instrument to ensure the normal operation of each component and function of the instrument, promptly discovers and solves potential problems, improves the reliability and stability of the instrument, and reduces the risk of detection errors or delays caused by instrument failures. Description of the drawings

[0031] Figure 1 It is a schematic structural diagram of an intelligent weld flaw detector based on ultrasonic waves of the present invention.

[0032] Figure 2 It is a schematic system diagram of an intelligent weld flaw detector based on ultrasonic waves of the present invention.

[0033] As shown in the figure: 1. Detector; 101. Operation button; 102. Image display screen; 103. Result display screen; 104. Connector; 105. Anti-slip silicone pad; 2. Probe; 201. Wire; 202. Plug connector; 3. Support frame. Detailed implementation manners

[0034] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0035] I. Working principle of the present invention:

[0036] 1.1 Overall structure

[0037] The ultrasonic-based intelligent weld flaw detector of the present invention mainly consists of a detector 1, a probe 2 and a support frame 3. The detector 1 has a rectangular structure, and its surface is provided with operation buttons 101, an image display screen 102 and a result display screen 103, and a controller is provided inside. A connector 104 is provided above the detector 1, and an anti-slip silica gel pad 105 is provided at the bottom to increase the stability of the instrument when placed. The support frame 3 has a U-shaped structure and is rotatably connected to both sides of the detector 1 to facilitate adjusting the angle and position of the detector 1 in different detection scenarios.

[0038] 1.2 Detection system

[0039] The detection system is based on an ultrasonic probe and mainly includes an ultrasonic transmitting and receiving device. Under the control of the controller, this device can emit ultrasonic waves with a specific frequency and intensity to the weld. When the ultrasonic waves encounter defects or different medium interfaces in the weld, reflected echo signals will be generated, and the ultrasonic transmitting and receiving device will then receive these echo signals. Its working principle is based on the differences in the propagation speed and reflection characteristics of ultrasonic waves in different media. For example, when there are defects such as pores and cracks in the weld, the reflection situation of ultrasonic waves at the defects is different from that in the normal weld metal. By analyzing the reflected echo signals, it is possible to preliminarily determine whether there are defects in the weld and the approximate location of the defects.

[0040] 1.3 Analysis system

[0041] Acquisition and conversion module

[0042] This module is responsible for collecting the echo signals received by the ultrasonic probe and converting them into digital signals. It has a high sampling accuracy and sampling frequency and can accurately obtain the detailed information of the echo signals. During the signal acquisition process, it is necessary to ensure the effective capture of weak echo signals, and converting them into digital signals is convenient for subsequent computer processing and analysis.

[0043] Data processing module

[0044] The converted digital signal is processed in multiple aspects. First, a filtering algorithm is used to remove noise interference in the signal. For example, an adaptive filtering algorithm is adopted to dynamically adjust the filtering parameters according to the real-time characteristics of the echo signal to improve the signal-to-noise ratio. Then, the signal is amplified to enhance the strength of the useful signal. Finally, feature extraction is performed to extract feature parameters such as echo amplitude, echo time, and echo frequency. These feature parameters can reflect relevant information about the internal structure and defects of the weld. For example, the magnitude of the echo amplitude may be related to the size of the defect, and the echo time can be used to calculate the depth position of the defect, etc.

[0045] Intelligent diagnosis module

[0046] Based on the feature parameters extracted by the data processing module, a pre-trained intelligent algorithm model is used to diagnose weld defects. The intelligent algorithm model can be a neural network model based on deep learning. Through the training of a large number of sample data of different types of weld defects, it is enabled to have the ability to automatically distinguish the types of defects. For example, the extracted feature parameters are input into the trained neural network, and the neural network calculates according to the internal weights and thresholds and outputs the corresponding defect types, such as pores, slag inclusions, cracks, etc.

[0047] Database module

[0048] The database module stores a large amount of data related to weld detection, including standard weld data under different materials and different welding processes, as well as feature data samples of various defects, etc. These data provide basic data support for the intelligent diagnosis module, enabling the intelligent diagnosis module to refer to more standard and sample information when making defect judgments, thereby improving the accuracy and reliability of the diagnosis. For example, when detecting a weld of a specific material and welding process, the database module can provide the corresponding standard echo feature data range, and the intelligent diagnosis module compares the detected echo feature data with it to more accurately judge whether there are defects and the type of defects. At the same time, the database module can also store the detection history data for subsequent data analysis, statistics, and quality traceability.

[0049] Image generation and annotation module

[0050] Based on the detection results, a weld cross-section image is generated and displayed on the image display screen 102. After passing through the analysis system, the position, shape, and size information of the defects are accurately marked on the image. The annotation information adopts a standardized graphic and text format and is displayed on the result display screen 103. Image generation can be based on the processing and analysis results of the echo signal, and a visual image of the weld cross-section is constructed through specific image processing algorithms. The annotation information is marked on the image according to the defect information determined by the intelligent diagnosis module, making the detection results more intuitive and understandable.

[0051] Sharing module

[0052] The detection data and results are transmitted to a remote terminal or other relevant devices in a wireless or wired manner. Wireless transmission can adopt technologies such as Wi-Fi and Bluetooth, and wired transmission can adopt interfaces such as Ethernet. Through the sharing module, it is convenient to realize remote monitoring of detection data, multi-device collaborative work, and further analysis and processing of data. For example, in a large factory, the detection data can be transmitted to the quality control center in real time for timely evaluation and decision-making of welding quality.

[0053] System self-check and calibration module

[0054] Before each detection or regularly, automatic detection and calibration are carried out on each component and function of the system. It includes performance detection of the ultrasonic transmitting and receiving devices, such as transmitting power, receiving sensitivity, etc.; calibration of signal conversion accuracy to ensure the accuracy of the acquisition and conversion module; verification of the accuracy of data processing algorithms, and algorithm verification and adjustment are carried out through specific test signals and sample data. If an abnormality is detected, an alarm is automatically issued and calibration or maintenance information is prompted to ensure that the instrument is always in good working condition.

[0055] II. Implementation method:

[0056] 2.1 Instrument preparation

[0057] The stainless steel weld with a thickness of 8 mm is detected this time. The probe 2 with a frequency range of 2 MHz - 4 MHz and a wafer diameter of 8 mm is properly connected to the connector 104 of the detector 1 through the wire 301. The anti-slip silicone pad 105 at the bottom of the detector 1 ensures stable placement, and the support frame 3 is adjusted to an appropriate angle.

[0058] 2.2 Detection operation

[0059] Turn on the detector 1, and set the ultrasonic emission frequency to 2.5 MHz, pulse width to 40 μs, and amplitude to 180 V through the operation button 101, which is adapted to the detection of this stainless steel weld.

[0060] The probe 2 touches and scans the weld at a speed of 4 cm per second uniformly. The ultrasonic transmitting and receiving devices work, emitting ultrasonic waves and receiving echoes.

[0061] The acquisition and conversion module acquires the echo signal at a sampling frequency of 80 MHz and a sampling accuracy of 10 bits and converts it. The data processing module processes the signal, suppresses the noise to below -35 dB through adaptive filtering, amplifies it by 40 times, and extracts characteristic parameters such as echo amplitude of 0.08 V - 8 V, echo time of 8 μs - 90 μs, and echo frequency of 0.8 MHz - 3.5 MHz.

[0062] The intelligent diagnosis module conducts diagnosis by combining database information. The database stores a large amount of stainless steel weld data, such as the echo amplitude of normal welds being 0.15V - 0.7V and the echo time being 15 microseconds - 70 microseconds. The neural network model of this module is trained with 8,000 samples, and the discrimination accuracy rate for common defects reaches 93%. It can determine the defect location accurately to 0.8 mm and the size accuracy to 0.4 mm.

[0063] 2.3 Result Display and Storage

[0064] The image generation and annotation module generates a weld cross-section image of 600×400 pixels on the image display screen 102, and the result display screen 103 annotates the defect information in 10-point font with 1.5-pixel lines.

[0065] The data storage and management module stores data in JSON format, classifies it according to the weld number and time, and updates the database simultaneously.

[0066] 2.4 Data Sharing and System Maintenance

[0067] The sharing module transmits data to devices within 30 meters using Bluetooth technology.

[0068] The self-check and calibration module runs before detection. The ultrasonic emission power should be between 130V - 230V, the receiving sensitivity should be higher than -55dB, and the signal conversion accuracy error should be ±0.4%. If not, an alarm will prompt calibration and repair. For example, if the emission power is lower than 130V or the conversion error exceeds the limit, technicians will handle it according to the prompt to ensure the normal operation of the instrument.

[0069] This embodiment demonstrates the specific parameter settings and operation procedures of this intelligent weld flaw detector in actual applications, effectively achieving precise detection, data management, and system maintenance of specific stainless steel welds, providing strong support for industrial welding quality control.

[0070] The above describes the present invention and its implementation manners. This description is not restrictive. What is shown in the drawings is only one of the implementation manners of the present invention, and the actual structure is not limited thereto. Generally speaking, if those of ordinary skill in the art are inspired by it and, without departing from the gist of the present invention creation, design structurally similar ways and embodiments to this technical solution without creativity, they shall fall within the protection scope of the present invention.

Claims

1. An ultrasonic-based intelligent weld flaw detector, characterized in that: Including: A detector (1), which is of a rectangular structure, with an operation button (101), an image display screen (102) and a result display screen (103). There is a controller inside, and a connector (104) is provided above the detector (1); A detection head (2), which is used to contact the weld to be measured, and one end is connected to a wire (201). The other end of the wire (201) is provided with a plug connector (202) for connecting to the connector (104); The controller includes a detection system and an analysis system; The detection system is based on an ultrasonic probe and includes: An ultrasonic transmitting and receiving device, which is used to transmit ultrasonic waves to the weld and receive the reflected echo signal; The analysis system includes: An acquisition and conversion module, which is used to acquire the echo signal received by the ultrasonic probe and convert it into a digital signal; A data processing module, which filters, amplifies and extracts features from the converted digital signal; An intelligent diagnosis module, which is based on the characteristic parameters extracted by the data processing module, and uses a pre-trained intelligent algorithm model to diagnose weld defects and can automatically distinguish the types of defects.

2. The intelligent weld flaw detector based on ultrasonic waves according to claim 1, wherein: The analysis system also includes a data storage and management module, which is used to store the original data obtained by the detection system, the data during the processing of the intelligent analysis system and the final diagnostic result data.

3. The intelligent weld flaw detector based on ultrasonic waves according to claim 2, characterized in that: It also includes an image generation and annotation module, which generates a weld cross-section image according to the detection result, directly displays it on the image display screen (102), and accurately marks the position, shape and size information of the defect on the image after passing through the analysis system. The annotation information adopts a standardized graphic and text format and is displayed on the result display screen (103).

4. The intelligent weld flaw detector based on ultrasonic waves according to claim 3, characterized in that: The controller also includes a sharing module, which transmits to a remote terminal or other related devices in a wireless or wired manner.

5. An ultrasonic-based intelligent weld flaw detector according to claim 4, characterized in that: The controller also includes a database module, which is used to store weld detection-related data, including standard weld data under different materials and different welding processes, and characteristic data samples of various defects.

6. The intelligent weld flaw detector based on ultrasonic waves according to claim 4, wherein: The controller also includes a system self-check and calibration module, which is used to automatically detect and calibrate each component and function of the system before detection or regularly, including the performance of the ultrasonic transmitting and receiving device, the signal conversion accuracy, and the accuracy of the data processing algorithm.

7. An ultrasonic-based intelligent weld flaw detector according to claim 1, characterized in that: It also includes a support frame (3), which is specifically of a U-shaped structure and is rotatably connected to both sides of the detector (1). The bottom of the detector (1) is provided with an anti-slip silica gel pad (105).

Images