An online detection system, method, and related equipment for internal defects in hot-rolled steel sheets.

Abstract

This application discloses an online detection system, method, and related equipment for internal defects of hot-rolled sheet metal, relating to the field of intelligent detection technology in metal rolling. The system includes a high-temperature resistant triboelectric roller probe for rolling contact with the surface of the hot-rolled sheet metal to generate a raw electrical signal through the triboelectric effect; a signal processing module connected to the high-temperature resistant triboelectric roller probe for acquiring the raw electrical signal and processing it to obtain a preprocessed signal; and an internal defect detection module connected to the signal acquisition and processing module for receiving the preprocessed signal and detecting it based on a target deep learning model to determine the diagnostic result of internal defects in the hot-rolled sheet metal.

Description

Technical Field

[0001] This application relates to the field of intelligent inspection technology for metal rolling, and in particular to an online inspection system, method and related equipment for internal defects of hot-rolled plates. Background Technology

[0002] With the increasing demands for quality and efficiency in industrial manufacturing of hot-rolled steel sheets, the need for online real-time detection of internal defects is becoming increasingly urgent. Existing defect detection technologies mainly rely on offline methods, which have significant limitations: ultrasonic probes lack sufficient temperature resistance and cannot match the high-temperature conditions of the finishing rolling mill; eddy current detection is severely affected by the strong electromagnetic field interference of the rolling mill, resulting in a low signal-to-noise ratio; and X-ray tomography is slow and cannot meet the needs of high-speed production lines. Therefore, developing an online detection technology that can operate stably in high-temperature and highly interference environments, reflecting real-time changes in the internal microstructure of the steel sheet, and promptly detecting and locating defect areas is a pressing issue to be addressed in the field of intelligent hot-rolled manufacturing. Summary of the Invention

[0003] The embodiments of this application provide an online detection system, method and related equipment for internal defects of hot-rolled steel sheets, which can at least to some extent achieve high-efficiency detection of internal defects of hot-rolled steel sheets.

[0004] The summary section introduces a series of simplified concepts, which will be further explained in detail in the detailed description section. This summary section is not intended to limit the key and essential technical features of the claimed technical solution, nor is it intended to determine the scope of protection of the claimed technical solution.

[0005] This application specifically includes the following aspects:

[0006] Firstly, this application proposes an online detection system for internal defects in hot-rolled steel sheets, comprising: High-temperature resistant triboelectric roller probes are used to make rolling contact with the surface of hot-rolled plates to generate raw electrical signals through the triboelectric effect; A signal processing module, connected to the high-temperature resistant triboelectric roller probe, is used to acquire the raw electrical signal and process the raw electrical signal to obtain a preprocessed signal; An internal defect detection module, connected to the signal processing module, is used to receive the preprocessed signal and detect the preprocessed signal based on a target deep learning model to determine the defect diagnosis result inside the hot-rolled plate.

[0007] In one feasible implementation, the high-temperature resistant triboelectric roller probe includes a cylindrical roller body, a high-temperature alloy drive shaft, a temperature control layer, and an elastic support structure, wherein: The outer circumferential surface of the cylindrical roller body is alternately distributed with at least two sets of high-temperature ceramic composite friction sections and at least two sets of metal conductive sections. The high-temperature alloy drive shaft passes through the center of the cylindrical roller body, providing rotational support and power transmission for the cylindrical roller body; The temperature control layer covers the outside of the high-temperature alloy drive shaft, and the temperature control layer is provided with a cooling channel for introducing a cooling medium to adjust the working temperature of the high-temperature resistant friction electric roller probe. The elastic support structure is disposed inside the cylindrical roller body to provide elastic contact pressure between the cylindrical roller body and the surface of the hot-rolled sheet.

[0008] In one feasible implementation, the signal processing module further includes; The passband frequency determination unit is used to determine the current target passband frequency based on the rotational speed of the high-temperature triboelectric roller probe. A dynamic filtering unit is used to dynamically filter the original electrical signal based on the target passband frequency to obtain a preliminary filtered signal. A dual-parameter compensation unit is used to compensate the preliminary filtered signal based on the temperature data of the high-temperature resistant triboelectric roller probe and the vibration data of the probe support arm system to obtain the preprocessed signal.

[0009] In one feasible implementation, the defect diagnosis result of the hot-rolled sheet includes the type of defect inside the hot-rolled sheet and the position coordinates of the defect along the length direction of the hot-rolled sheet; the internal defect detection module further includes: The feature extraction unit is used to perform wavelet packet transform on the preprocessed signal to extract the joint time-frequency domain feature vector of the preprocessed signal; The model inference unit is used to input the joint time-frequency domain feature vector into the trained target deep learning model to determine the type of defect inside the hot-rolled plate. A spatial positioning unit is used to acquire the rotary encoder signal of the high-temperature triboelectric roller probe, and, if a defect is determined, to determine the position of the high-temperature triboelectric roller probe based on the rotary encoder signal, so as to determine the position coordinates of the defect in the length direction of the hot-rolled plate based on the position.

[0010] In one feasible implementation, the online defect detection system for hot-rolled steel sheets further includes: The probe support arm system is used to control the contact pressure between the high-temperature resistant triboelectric roller probe and the surface of the hot-rolled sheet to remain within a preset pressure range based on the surface height data of the hot-rolled sheet.

[0011] Secondly, this application proposes an online detection method for internal defects of hot-rolled steel plates, applied to the online detection system for internal defects of hot-rolled steel plates described in any of the above embodiments, comprising: The raw electrical signal is acquired; the raw electrical signal is generated by the high-temperature triboelectric roller probe rolling into contact with the surface of the hot-rolled plate through the triboelectric effect. The original electrical signal is processed to obtain a preprocessed signal; The preprocessed signal is detected based on the target deep learning model to determine the defect diagnosis results inside the hot-rolled plate.

[0012] In one feasible implementation, processing the original electrical signal to obtain a preprocessed signal includes: The current target passband frequency is determined based on the rotational speed of the high-temperature triboelectric roller probe. The original electrical signal is dynamically filtered based on the target passband frequency to obtain a preliminary filtered signal. Based on the temperature and vibration data, the preliminary filtered signal is compensated to obtain the preprocessed signal.

[0013] In one feasible implementation, the defect diagnosis result of the hot-rolled sheet includes the defect type inside the hot-rolled sheet and the position coordinates of the defect along the length of the hot-rolled sheet; the step of detecting the preprocessed signal based on the target deep learning model to determine the defect diagnosis result of the hot-rolled sheet includes: A wavelet packet transform is performed on the preprocessed signal to extract the joint time-frequency domain feature vector of the preprocessed signal; The time-frequency domain joint feature vector is input into the trained target deep learning model to determine the type of defect inside the hot-rolled plate. The rotary encoder signal of the high-temperature triboelectric roller probe is acquired, and if a defect is determined, the position of the high-temperature triboelectric roller probe is determined based on the rotary encoder signal, so as to determine the position coordinates of the defect in the length direction of the hot-rolled plate based on the position.

[0014] In one feasible implementation, the online detection method for internal defects of hot-rolled steel sheets further includes: Based on the type of defect inside the hot-rolled sheet and the position coordinates of the defect along the length of the hot-rolled sheet, the human-machine interface is controlled to perform early warning prompts.

[0015] In one feasible implementation, prior to acquiring the raw electrical signal, the method further includes: Based on the surface height data of the hot-rolled sheet, the contact pressure between the high-temperature resistant triboelectric roller probe and the surface of the hot-rolled sheet is controlled to remain within a preset pressure range.

[0016] In summary, the online detection system, method, and related equipment for internal defects of hot-rolled steel plates proposed in this application significantly improve the overall performance of internal defect detection in hot-rolled steel plates. The system employs a high-temperature resistant triboelectric roller probe, combined with a temperature control layer and elastic support structure, effectively solving the applicability problem of traditional detection technologies in high-temperature and strong interference environments, and realizing real-time online detection during the rolling process. The signal processing module, through dynamic filtering and dual-parameter compensation technology, accurately suppresses multi-source interference such as temperature drift and mechanical vibration, providing high-quality signal input for defect diagnosis. The internal defect detection module integrates wavelet packet transform feature extraction and deep learning models, greatly improving the accuracy of defect type identification and location positioning. Combined with the dynamic pressure control of the probe support arm system, the system's operational stability is further enhanced under uneven plate surface conditions. At the detection method level, through real-time signal acquisition, adaptive preprocessing, and intelligent diagnostic processes, a closed-loop control system from defect detection to early warning is constructed. This not only shortens the defect feedback cycle but also helps to adjust production process parameters in a timely manner, reducing the incidence of defective products, and providing an efficient and reliable intelligent solution for the quality control of hot-rolled steel plates.

[0017] The online detection system, method and related equipment for internal defects of hot-rolled plates proposed in this application, as well as other advantages, objectives and features of this application, will be partly apparent from the following description, and partly understood by those skilled in the art through study and practice of this application. Attached Figure Description

[0018] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit this specification. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 A schematic diagram of an online detection system for internal defects in hot-rolled steel sheets provided in this application embodiment; Figure 2 A schematic diagram of an internal defect detection device for hot-rolled steel sheets provided in this application embodiment; Figure 3 This is a structural diagram of a high-temperature resistant triboelectric roller probe provided in an embodiment of this application; Figure 4 A functional structural diagram of an online detection system for internal defects in hot-rolled steel sheets provided in this application embodiment; Figure 5A schematic flowchart illustrating an online detection method for internal defects in hot-rolled steel sheets provided in this application embodiment; Figure 6 This is a schematic diagram of an electronic device for online detection of internal defects in hot-rolled steel sheets, provided as an embodiment of this application. Detailed Implementation

[0019] To better understand the technical solutions provided in the embodiments of this specification, the technical solutions of the embodiments of this specification will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of this specification and the specific features in the embodiments are detailed descriptions of the technical solutions of the embodiments of this specification, rather than limitations on the technical solutions of this specification. In the absence of conflict, the embodiments of this specification and the technical features in the embodiments can be combined with each other.

[0020] In this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, without necessarily requiring or implying any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element. The term "two or more" includes two or more cases.

[0021] Please see Figure 1 This is a schematic diagram of the structure of an online detection system for internal defects in hot-rolled steel plates provided in an embodiment of this application, which may specifically include: The high-temperature resistant triboelectric roller probe 100 is used to make rolling contact with the surface of hot-rolled sheet metal to generate a raw electrical signal through the triboelectric effect.

[0022] For example, the high-temperature resistant triboelectric roller probe 100 adopts a cylindrical structure and converts changes in the microstructure of the material into detectable raw electrical signals through the triboelectric effect. This triboelectric effect enables non-contact detection, avoiding the impact of traditional methods on the surface quality of the material.

[0023] The signal processing module 200 is connected to the high-temperature resistant triboelectric roller probe 100 and is used to acquire raw electrical signals and process them to obtain preprocessed signals.

[0024] For example, the signal processing module 200 includes dynamic filtering and dual-parameter compensation functions to eliminate high temperature and vibration interference in order to obtain a preprocessed signal.

[0025] The internal defect detection module 300 is connected to the signal processing module 200. It is used to receive preprocessed signals and detect the preprocessed signals based on the target deep learning model to determine the defect diagnosis results inside the hot-rolled plate.

[0026] For example, the internal defect detection module 300 uses wavelet packet transform to extract signal features and a hybrid neural network model to achieve defect identification and localization. This determines the diagnostic results of internal defects in the hot-rolled sheet. By combining a deep learning model, the accuracy of defect identification is improved, the false negative and false positive rates are reduced, and online real-time defect detection is achieved with fast response speed, meeting the needs of high-speed rolling production lines.

[0027] In summary, in the high-temperature environment of the finishing mill exit section of a hot rolling production line, the system, integrated above the rolling exit side, uses a high-temperature resistant triboelectric roller probe that contacts the surface of the hot-rolled sheet at temperatures exceeding 800°C. This solves the applicability problem of traditional detection technologies in high-temperature environments, allowing for stable operation at temperatures above 800°C. When lattice defects or microcracks exist within the sheet, the amplitude and waveform of the triboelectric signal change. After filtering and compensating the original signal, the internal defect detection module analyzes the signal characteristics to successfully identify the defect and determine its location. The entire process is completed synchronously during the sheet rolling process, eliminating the need for offline detection.

[0028] In some examples, such as Figure 3 As shown, the high-temperature resistant triboelectric roller probe 100 includes a cylindrical roller body, a high-temperature alloy drive shaft 11, a temperature control layer 6, and an elastic support structure 7, wherein: The outer circumferential surface of the cylindrical roller body is alternately distributed with at least two sets of high-temperature ceramic composite friction sections 8 and at least two sets of metal conductive sections 9; The high-temperature alloy drive shaft 11 passes through the center of the cylindrical roller body, providing rotational support and power transmission for the cylindrical roller body; The temperature control layer 6 covers the outside of the high-temperature alloy drive shaft 11, and the temperature control layer 6 is provided with a cooling channel for introducing a cooling medium to adjust the working temperature of the high-temperature resistant friction electric roller probe 100. The elastic support structure 7 is located inside the cylindrical roller body and is used to provide elastic contact pressure between the cylindrical roller body and the surface of the hot-rolled plate.

[0029] For example, at least two sets of high-temperature ceramic composite friction segments 8 and metal conductive segments 9 are alternately distributed on the surface of the cylindrical roller body, forming a periodic friction-conductivity interaction region. The design of periodically alternating high-temperature ceramic composite friction segments 8 and metal conductive segments 9 improves the identifiability and stability of the triboelectric signal.

[0030] A high-temperature alloy drive shaft 11 passes through the center of the cylindrical roller body, providing rotational support and power transmission. A temperature control layer 6 covers the outer side of the high-temperature alloy drive shaft 11 and has internal cooling channels for regulating the operating temperature of the high-temperature triboelectric roller probe 100. The combination of the high-temperature alloy drive shaft 11 and the temperature control layer 6 ensures the structural stability and operational reliability of the high-temperature triboelectric roller probe 100 in high-temperature environments.

[0031] The elastic support structure 7 is disposed inside the cylindrical roller body, providing elastic contact pressure between the cylindrical roller body and the surface of the hot-rolled plate. The elastic support structure 7 achieves stable contact between the high-temperature triboelectric roller probe 100 and the surface of the hot-rolled plate, reducing signal fluctuations caused by the unevenness of the hot-rolled plate surface.

[0032] In some examples, the signal processing module 200 also includes; The passband frequency determination unit is used to determine the current target passband frequency based on the rotational speed of the high-temperature triboelectric roller probe 100. The dynamic filtering unit is used to dynamically filter the original electrical signal based on the target passband frequency to obtain a preliminary filtered signal. The dual-parameter compensation unit is used to compensate the preliminary filtered signal based on the temperature data of the high-temperature triboelectric roller probe 100 and the vibration data of the probe support arm system to obtain the preprocessed signal.

[0033] For example, the passband frequency determination unit determines the current target passband frequency based on the rotational speed of the high-temperature triboelectric roller probe 100.

[0034] The dynamic filtering unit dynamically filters the original electrical signal based on the target passband frequency to obtain a preliminary filtered signal. Dynamic filtering technology can adapt to changes in signal characteristics at different rolling speeds, improving the adaptability of signal processing.

[0035] The dual-parameter compensation unit compensates for the initial filtered signal based on the temperature data of the high-temperature triboelectric roller probe 100 and the vibration data of the support arm system, obtaining a pre-processed signal. Dual-parameter compensation effectively suppresses the interference of temperature and vibration on the signal, improving signal quality and stability. The signal processing module 200 provides a high-quality pre-processed signal for the subsequent internal defect detection module 300, helping to improve the accuracy of defect identification. The entire processing process has high real-time performance, meeting the time requirements of online detection.

[0036] In some examples, the defect diagnosis results for hot-rolled plates include the type of defect inside the hot-rolled plate and the location coordinates of the defect along the length of the hot-rolled plate; the internal defect detection module 300 also includes: The feature extraction unit is used to perform wavelet packet transform on the preprocessed signal to extract the joint time-frequency domain feature vector of the preprocessed signal; The model inference unit is used to input the joint time-frequency domain feature vector into the trained target deep learning model to determine the type of defects inside the hot-rolled sheet. The spatial positioning unit is used to acquire the rotary encoder signal of the high-temperature triboelectric roller probe 100, and, if a defect is determined, to determine the position of the high-temperature triboelectric roller probe 100 based on the rotary encoder signal, so as to determine the position coordinates of the defect in the length direction of the hot-rolled plate based on the position.

[0037] For example, the feature extraction unit performs wavelet packet transform on the preprocessed signal to extract a joint time-frequency domain feature vector. Wavelet packet transform can effectively extract the time-frequency domain features of the signal, improving the discriminative power of defect features.

[0038] The model inference unit inputs the joint time-frequency domain feature vector into the trained target deep learning model to determine the defect type. The application of deep learning models improves the accuracy and reliability of defect type identification.

[0039] The spatial positioning unit determines the position coordinates of the defect along the length of the hot-rolled sheet based on the rotary encoder signal. This precise positioning of the defect, combined with the rotary encoder signal, provides an accurate basis for subsequent process adjustments.

[0040] The internal defect detection module 300 has a high degree of automation in the entire detection process, which reduces manual intervention and improves detection efficiency.

[0041] In some examples, the online detection system for internal defects in hot-rolled sheets also includes: The probe support arm system is used to control the contact pressure between the high-temperature resistant triboelectric roller probe 100 and the surface of the hot-rolled sheet to remain within a preset pressure range based on the surface height data of the hot-rolled sheet.

[0042] For example, the contact pressure between the high-temperature resistant triboelectric roller probe 100 and the surface of the hot-rolled sheet is controlled by adding a probe support arm system. This system can maintain the contact pressure between the high-temperature resistant triboelectric roller probe 100 and the surface of the hot-rolled sheet within a preset pressure range based on the surface height data of the hot-rolled sheet, through an adjustment mechanism.

[0043] In summary, by improving the stability of the contact between the high-temperature triboelectric roller probe and the surface of the hot-rolled sheet, signal fluctuations caused by changes in contact pressure are reduced. Secondly, the addition of a probe support arm system allows for adaptation to uneven sheet surfaces and thickness variations, improving the system's adaptability to different working conditions. Simultaneously, it reduces wear on both the high-temperature triboelectric roller probe and the hot-rolled sheet surface, extending the probe's lifespan and contributing to improved signal consistency and reliability, thereby enhancing the accuracy of defect detection.

[0044] The technical solution of this application will be further described in detail below through specific embodiments.

[0045] In this embodiment, the entire online detection system for internal defects of hot-rolled steel sheets is integrated into the area above the rolling exit side of the hot-rolling production line. Figure 2 The system is fixed by a frame system, and each module is interconnected with a signal bus via cables to achieve coordinated operation of the entire machine. Figure 4 ).

[0046] The structure of the high-temperature resistant triboelectric roller probe 100 is as follows: Figure 2 and Figure 3 As shown, the main body is a hollow cylindrical roller, which consists of a sensing layer 1, a drive shaft 2, a temperature control layer 6, and an elastic support structure 7.

[0047] The high-temperature triboelectric roller probe 100 has a hollow cylindrical structure. The roller is composed of alternating high-temperature resistant ceramic composite material 8 and metal conductive sections 9. The metal conductive sections 9 are made of Mo-30W alloy. Two sets of high-temperature ceramic composite friction sections 8 and two sets of metal conductive sections 9 are evenly distributed along the circumference of the roller, forming a periodic triboelectric interaction region. When the high-temperature resistant ceramic composite friction section 8 contacts and separates from the surface of the hot-rolled material 10, the change in microstructure directly alters the efficiency and magnitude of charge transfer, thus leading to changes in the macroscopic triboelectric signal characteristics (such as amplitude, waveform, spectrum, and stability). The sensing layer 1 adopts a hollow cylindrical structure, with two sets of high-temperature ceramic composite friction sections 8 and metal conductive sections 9 arranged alternately at equal intervals along the circumference, forming a periodic triboelectric interaction region. This design not only endows the probe with high-temperature and wear-resistant properties, but more importantly, it achieves a continuous "triboelectric generation-charge collection" cycle during rolling, generating a spatially corresponding periodic electrical pulse signal, laying the foundation for subsequent defect localization. A high-temperature alloy drive shaft 11, made of nickel-based high-temperature alloy, runs through the center. Both ends are hinged to the support arm via high-temperature bearing assemblies, enabling synchronous rotation. The high-temperature alloy drive shaft 11 is tightly covered with a high-temperature ceramic composite friction section 8 and embedded in a fixing groove. It is fixed to the housing by an embedded spiral buckle, facilitating disassembly and maintenance.

[0048] The high-temperature resistant triboelectric roller probe 100 has a multi-layered composite structure, including: a temperature control layer 6: the temperature control layer 6 covering the shaft has a spiral flow channel, through which a mixture of silicone oil and perfluoropolyether coolant (flow rate 15L / min) is circulated to maintain a stable contact surface temperature. Controllable cooling medium circulation is guided through pipes to adjust the roller contact surface temperature in real time, preventing high-temperature drift and material degradation in the acquired signal. The cooling medium can be a mixture of high flash point silicone oil, fluorinated liquid, etc., ensuring stable operation of the system in environments above 800℃.

[0049] Elastic support structure 7: including pneumatic cylinder, spring seat and buffer pad, can adjust the height and pressure of the roller in real time according to the height fluctuation of the plate surface, ensuring that the roller and the plate always maintain stable pressure contact, improving signal consistency and reducing the detection of internal lattice structure caused by surface flatness differences.

[0050] During operation, the high-temperature triboelectric roller probe 100 makes periodic sliding contact with the surface of the hot-rolled plate. It generates voltage pulse signals that reflect the microstructure by means of triboelectric effect. The signal response can directly characterize the internal lattice structure, texture direction, microcracks and pores of the plate.

[0051] The probe support arm system is used to precisely position and stabilize the high-temperature resistant triboelectric roller probe 100, and includes the following sub-components: Linkage positioning module: including electric lifting arm 3, horizontal moving platform 4 and rotating bracket 5, to realize the free displacement and angle adjustment of high temperature resistant friction electric roller probe 100, which can quickly adapt to different specifications and thicknesses of plates; Force control feedback system: A force-sensitive resistor array is set at the connection between the bracket and the roller to monitor the contact force distribution in real time. Combined with the closed-loop adjustment of the pressure control cylinder of the control system, the contact force is kept within the optimal range. The pneumatic cylinder is dynamically adjusted through the PID algorithm to eliminate signal fluctuations caused by board warping and improve signal stability and repeatability.

[0052] Signal Processing Module 200: Due to the high-temperature electromagnetic interference environment, the friction signal requires a specially designed anti-interference acquisition system, mainly including: High-temperature charge acquisition electrode: The conductive section extracts the friction charge through integrated micro-electrodes and transmits it to the acquisition host via a high-temperature shielded cable; Dynamic bandpass filter and lock-in amplifier: The system automatically adjusts the passband frequency range to match the real-time friction frequency change, while locking the target frequency phase signal and shielding background noise such as mill frequency and power supply interference; Signal stabilization: Includes a dual-parameter (temperature / vibration) compensation circuit, a drift correction module, and a high-precision A / D sampler.

[0053] Internal defect detection module 300: This application is based on a hybrid deep neural network, integrating time series analysis and frequency domain pattern recognition capabilities. Its workflow includes: Wavelet packet transform and feature extraction: Multi-scale wavelet packet decomposition is performed on the original triboelectric signal to extract feature parameters such as energy ratio, peak amplitude, and kurtosis of each frequency band, enabling accurate signal analysis under different temperature and pressure conditions; Defect location: The rotary encoder signal of the roller is synchronously paired with the detection signal, and the time difference back-calculation algorithm is used to achieve precise location of the defect in the length direction of the plate.

[0054] It should be noted that the above embodiments are merely best examples and are not intended to limit the implementation of this application.

[0055] Furthermore, this application also proposes an online detection method for internal defects in hot-rolled steel sheets, applied to any of the above-mentioned online detection systems for internal defects in hot-rolled steel sheets, specifically as follows: Figure 5 The diagram shown is a flowchart illustrating an online detection method for internal defects in hot-rolled steel sheets proposed in this application, comprising: S110. Acquire raw electrical signals; the raw electrical signals are generated by the high-temperature triboelectric roller probe rolling into contact with the surface of the hot-rolled sheet through the triboelectric effect. S120. Process the original electrical signal to obtain a preprocessed signal; S130. Based on the target deep learning model, the preprocessed signal is detected to determine the defect diagnosis results inside the hot-rolled plate.

[0056] For example, during the production of hot-rolled sheet metal, when the hot-rolled sheet metal passes the detection position, the high-temperature resistant triboelectric roller probe 100 contacts the surface of the hot-rolled sheet metal and generates a raw electrical signal. This signal is then processed through filtering, amplification, and compensation to obtain a pre-processed signal. After receiving the pre-processed signal, a deep learning model is used to analyze and determine whether there are defects inside the hot-rolled sheet metal. If defects are found, the type and location of the defects are determined. The entire detection process is performed synchronously with the sheet metal rolling process without interrupting production.

[0057] In some examples, the raw electrical signal is processed to obtain a preprocessed signal, including: The current target passband frequency is determined based on the rotational speed of the high-temperature triboelectric roller probe 100. The original electrical signal is dynamically filtered based on the target passband frequency to obtain a preliminary filtered signal. Based on temperature and vibration data, the initial filtered signal is compensated to obtain a preprocessed signal.

[0058] For example, during signal processing, the system first calculates the current target passband frequency based on the rotational speed of the high-temperature triboelectric roller probe 100. Then, the original electrical signal is filtered based on this target passband frequency to remove noise interference, resulting in a preliminary filtered signal. Next, based on the collected probe temperature data and support arm system vibration data, the preliminary filtered signal is compensated to eliminate the influence of temperature drift and vibration on the signal, ultimately obtaining a high-quality pre-processed signal to prepare for subsequent defect detection.

[0059] In some examples, the defect diagnosis results for hot-rolled sheets include the type of defect inside the hot-rolled sheet and the position coordinates of the defect along the length of the hot-rolled sheet; the defect diagnosis results for hot-rolled sheets are determined by detecting the preprocessed signal based on a target deep learning model, including: Wavelet packet transform is performed on the preprocessed signal to extract the joint time-frequency domain feature vector of the preprocessed signal; The joint time-frequency domain feature vector is input into the trained target deep learning model to determine the type of defect inside the hot-rolled sheet. The rotary encoder signal of the high-temperature triboelectric roller probe 100 is acquired, and if a defect is determined, the position of the high-temperature triboelectric roller probe is determined based on the rotary encoder signal, so as to determine the position coordinates of the defect in the length direction of the hot-rolled plate based on the position.

[0060] For example, in the defect detection process, the preprocessed signal is first subjected to wavelet packet transform to decompose the signal into different frequency bands. Feature parameters such as energy ratio and peak amplitude of each frequency band are extracted to form a joint time-frequency domain feature vector. This feature vector is then input into a pre-trained deep learning model, which identifies the defect type by analyzing the feature vector. Simultaneously, the system collects signals from the probe's rotary encoder and combines this with the running speed of the sheet material to calculate the precise location of the defect along the length of the sheet, achieving accurate defect localization.

[0061] In some examples, the online detection method for internal defects in hot-rolled sheets also includes: Based on the type of defect inside the hot-rolled sheet and the position coordinates of the defect along the length of the hot-rolled sheet, the human-machine interface is controlled to perform early warning prompts.

[0062] For example, when a defect is detected inside a hot-rolled sheet, the system displays relevant information about the defect on the human-machine interface, including the defect type, severity, and location coordinates, based on the defect type and location information. Simultaneously, the system issues an audible and visual alarm to alert the operator. The operator can then take appropriate measures based on the information displayed on the interface, such as adjusting rolling process parameters or marking the defect location for subsequent processing.

[0063] In some examples, the process of acquiring the raw electrical signal also includes: Based on the surface height data of the hot-rolled sheet, the contact pressure between the high-temperature resistant triboelectric roller probe 100 and the surface of the hot-rolled sheet is controlled to remain within a preset pressure range.

[0064] For example, before the test begins, surface height data of the hot-rolled sheet is collected using devices such as laser displacement sensors. Based on this data, the probe support arm system adjusts the position and orientation of the high-temperature triboelectric roller probe 100, ensuring that the high-temperature triboelectric roller probe 100 contacts the sheet surface with a preset pressure. During the test, the system continuously monitors changes in the sheet surface height and adjusts the position of the high-temperature triboelectric roller probe 100 in real time to ensure that the contact pressure remains within a suitable range, thereby guaranteeing the stable and reliable quality of the collected triboelectric signals.

[0065] like Figure 6 As shown, this application embodiment also provides an electronic device 300, including a processor 310, a memory 320, and a computer program 321 stored in the memory 320 and executable on the processor. When the processor 310 executes the computer program 321, it implements the steps of any of the above-described online detection methods for internal defects of hot-rolled steel plates.

[0066] Since the electronic device described in this embodiment is the device used to implement the online detection method for internal defects of hot-rolled sheet metal in the embodiments of this application, those skilled in the art can understand the specific implementation method and various variations of the electronic device in this embodiment based on the method described in the embodiments of this application. Therefore, how the electronic device implements the method in the embodiments of this application will not be described in detail here. Any device used by those skilled in the art to implement the method in the embodiments of this application falls within the scope of protection of this application.

[0067] In practice, when the computer program 321 is executed by the processor, it can implement any of the embodiments corresponding to the above-mentioned online detection method for internal defects of hot-rolled plates.

[0068] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0069] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-readable program code.

[0070] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0071] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0072] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0073] This application also provides a computer program product, which includes computer software instructions that, when executed on a processing device, cause the processing device to perform a process for online detection of internal defects in hot-rolled steel sheets.

[0074] A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0075] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0076] In the several embodiments provided in this application, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms.

[0077] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0078] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0079] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0080] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

[0081] Although preferred embodiments have been described in this specification, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this specification.

[0082] Obviously, those skilled in the art can make various modifications and variations to this specification without departing from its spirit and scope. Therefore, if such modifications and variations fall within the scope of the claims and their equivalents, this specification is also intended to include such modifications and variations.

Claims

1. An online detection system for internal defects in hot-rolled steel sheets, characterized in that, include: High-temperature resistant triboelectric roller probes are used to make rolling contact with the surface of hot-rolled plates to generate raw electrical signals through the triboelectric effect; A signal processing module, connected to the high-temperature resistant triboelectric roller probe, is used to acquire the raw electrical signal and process the raw electrical signal to obtain a preprocessed signal; An internal defect detection module, connected to the signal processing module, is used to receive the preprocessed signal and detect the preprocessed signal based on a target deep learning model to determine the defect diagnosis result inside the hot-rolled plate.

2. The online detection system for internal defects of hot-rolled steel plates according to claim 1, characterized in that, The high-temperature resistant triboelectric roller probe includes a cylindrical roller body, a high-temperature alloy drive shaft, a temperature control layer, and an elastic support structure, wherein: The outer circumferential surface of the cylindrical roller body is alternately distributed with at least two sets of high-temperature ceramic composite friction sections and at least two sets of metal conductive sections. The high-temperature alloy drive shaft passes through the center of the cylindrical roller body, providing rotational support and power transmission for the cylindrical roller body; The temperature control layer covers the outside of the high-temperature alloy drive shaft, and the temperature control layer is provided with a cooling channel for introducing a cooling medium to adjust the working temperature of the high-temperature resistant friction electric roller probe. The elastic support structure is disposed inside the cylindrical roller body to provide elastic contact pressure between the cylindrical roller body and the surface of the hot-rolled sheet.

3. The online detection system for internal defects of hot-rolled steel plates according to claim 1, characterized in that, The signal processing module further includes: The passband frequency determination unit is used to determine the current target passband frequency based on the rotational speed of the high-temperature triboelectric roller probe. A dynamic filtering unit is used to dynamically filter the original electrical signal based on the target passband frequency to obtain a preliminary filtered signal. A dual-parameter compensation unit is used to compensate the preliminary filtered signal based on the temperature data of the high-temperature resistant triboelectric roller probe and the vibration data of the probe support arm system to obtain the preprocessed signal.

4. The online detection system for internal defects of hot-rolled steel plates according to claim 1, characterized in that, The defect diagnosis results of the hot-rolled sheet include the type of defect inside the hot-rolled sheet and the position coordinates of the defect along the length of the hot-rolled sheet; the internal defect detection module also includes: The feature extraction unit is used to perform wavelet packet transform on the preprocessed signal to extract the joint time-frequency domain feature vector of the preprocessed signal; The model inference unit is used to input the joint time-frequency domain feature vector into the trained target deep learning model to determine the type of defect inside the hot-rolled plate. A spatial positioning unit is used to acquire the rotary encoder signal of the high-temperature triboelectric roller probe, and, if a defect is determined, to determine the position of the high-temperature triboelectric roller probe based on the rotary encoder signal, so as to determine the position coordinates of the defect in the length direction of the hot-rolled plate based on the position.

5. The online detection system for internal defects of hot-rolled steel plates according to claim 1, characterized in that, Also includes: The probe support arm system is used to control the contact pressure between the high-temperature resistant triboelectric roller probe and the surface of the hot-rolled sheet to remain within a preset pressure range based on the surface height data of the hot-rolled sheet.

6. An online detection method for internal defects in hot-rolled steel sheets, applied to the online detection system for internal defects in hot-rolled steel sheets according to any one of claims 1 to 5, characterized in that, include: Acquire raw electrical signals; The original electrical signal is generated by the rolling contact between the high-temperature resistant triboelectric roller probe and the surface of the hot-rolled plate through the triboelectric effect. The original electrical signal is processed to obtain a preprocessed signal; The preprocessed signal is detected based on the target deep learning model to determine the defect diagnosis results inside the hot-rolled plate.

7. The online detection method for internal defects of hot-rolled steel plates according to claim 6, characterized in that, The process of processing the original electrical signal to obtain a preprocessed signal includes: The current target passband frequency is determined based on the rotational speed of the high-temperature triboelectric roller probe. The original electrical signal is dynamically filtered based on the target passband frequency to obtain a preliminary filtered signal. Based on the temperature and vibration data, the preliminary filtered signal is compensated to obtain the preprocessed signal.

8. The online detection method for internal defects of hot-rolled steel plates according to claim 6, characterized in that, The defect diagnosis result of the hot-rolled sheet includes the type of defect inside the hot-rolled sheet and the position coordinates of the defect along the length of the hot-rolled sheet; the detection of the preprocessed signal based on the target deep learning model to determine the defect diagnosis result of the hot-rolled sheet includes: Wavelet packet transform is performed on the preprocessed signal to extract the joint time-frequency domain feature vector of the preprocessed signal; The time-frequency domain joint feature vector is input into the trained target deep learning model to determine the type of defect inside the hot-rolled plate. The rotary encoder signal of the high-temperature triboelectric roller probe is acquired, and if a defect is determined, the position of the high-temperature triboelectric roller probe is determined based on the rotary encoder signal, so as to determine the position coordinates of the defect in the length direction of the hot-rolled plate based on the position.

9. The online detection method for internal defects of hot-rolled steel plates according to claim 6, characterized in that, Also includes: Based on the type of defect inside the hot-rolled sheet and the position coordinates of the defect along the length of the hot-rolled sheet, the human-machine interface is controlled to perform early warning prompts.

10. The online detection method for internal defects of hot-rolled steel plates according to claim 6, characterized in that, Before acquiring the raw electrical signal, the following is also included: Based on the surface height data of the hot-rolled sheet, the contact pressure between the high-temperature resistant triboelectric roller probe and the surface of the hot-rolled sheet is controlled to remain within a preset pressure range.

Images