Graphitization damage state evaluation method and device based on multi-feature fusion
By performing dynamic magnetization multi-effect fusion detection of incremental magnetic permeability and tangential magnetic field strength on carbon steel materials, multi-magnetic characteristic parameters are extracted and microstructure damage defect detection is carried out, the cost, long period and destructive problems of graphitized microstructure damage status evaluation in the prior art are solved, and a fast, accurate and non-destructive evaluation effect is achieved.
Patent Information
- Application Number
- CN202510000465.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-02
- Publication Date
- 2025-05-02
AI Technical Summary
The prior art is difficult to quickly, accurately, without damage and without blind spots to evaluate the damage state of graphitized microstructure of carbon steel materials, resulting in high evaluation costs, long cycles and destructive workpieces.
The graphitized damage state evaluation method of multi-feature fusion is adopted. By conducting dynamic magnetization multi-effect fusion detection of incremental magnetic permeability and tangential magnetic field strength for the workpiece to be detected, the multi-magnetic characteristic parameter set is extracted, and input it into the microstructure damage defect detection model for judgment.
The rapid, accurate and non-destructive assessment of the damage state of graphitized microstructure of carbon steel is achieved, avoiding damage to the workpiece and reducing the evaluation cost and cycle.
Smart Images
Figure CN119915891A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of material degradation assessment, and in particular to a multi-feature fusion graphitization damage state assessment method and device. Background Art
[0002] Graphitization is a kind of material deterioration damage commonly seen in high-temperature equipment such as the main steam pipes and tees of thermal power plants. Graphitization can reduce the performance of the equipment and may even cause dangerous accidents such as structural damage and leakage. The damage state of graphitization microstructure is an important indicator for evaluating the severity of damage to carbon steel materials. The commonly used measurement method is to take samples for microstructure detection and then compare them with standard diagrams for determination. However, this method is time-consuming, destructive to materials, and cannot be tested online. Another common method is to use hardness testing to compare data to measure the damage state of graphitization microstructure. Although it can be tested online, it is also a destructive detection method. The non-destructive graphitization grade measurement method mainly relies on ultrasonic testing for rating. However, ultrasonic testing requires the use of chemical coupling agents and other substances for detection, and there are detection blind spots, so damage near the surface is difficult to detect accurately. Therefore, how to provide a fast, accurate, non-destructive and blind spot-free carbon steel graphitization microstructure damage defect detection solution is very necessary for the accurate assessment of the severity of carbon steel material damage. Summary of the invention
[0003] The purpose of this application is to provide a multi-feature fusion graphitization damage state assessment method and device, which can quickly, accurately, non-destructively and without blind spots complete the assessment of carbon steel graphitization microstructure damage state.
[0004] To achieve the above objectives, this application provides the following solutions:
[0005] In a first aspect, the present application provides a multi-feature fusion graphitization damage state assessment method, comprising the following steps:
[0006] The workpiece to be inspected is subjected to a multi-effect fusion detection of incremental magnetic permeability and tangential magnetic field intensity dynamic magnetization, and a multi-magnetic characteristic parameter set is extracted; the multi-magnetic characteristic parameter set includes characteristic parameters of the tangential magnetic field intensity signal and characteristic parameters of the incremental magnetic permeability signal; the characteristic parameters of the tangential magnetic field intensity signal include the third harmonic amplitude A3, the fifth harmonic amplitude A5 and the sum of the higher harmonic amplitudes UHS in the tangential magnetic field intensity signal; the characteristic parameters of the incremental magnetic permeability signal include the amplitude mean Umean in the incremental magnetic permeability signal.
[0007] The multi-magnetic characteristic parameter set is input into the microstructure damage defect detection model to obtain the corresponding microstructure damage defect.
[0008] According to the microstructure damage defects, the graphitization microstructure damage state of the workpiece to be inspected is determined.
[0009] Optionally, the microstructure damage defect detection model is constructed based on a neural network algorithm, a gradient boosted tree regression algorithm or an adaptive boosted tree regression algorithm.
[0010] Optionally, before determining the graphitized microstructure damage state of the workpiece to be inspected according to the microstructure damage defect, the following steps are also included:
[0011] The standard specimen is prepared using the same material as the workpiece to be tested.
[0012] Grind the surface of the standard specimen to remove the oxide layer on the surface of the standard specimen until a smooth metal surface is exposed.
[0013] Use a microanalysis instrument to observe the metallographic microstructure of the smooth metal surface, and use image processing software to analyze the microstructure damage defects of the standard sample.
[0014] According to the microstructure damage defects, the graphitization microstructure damage state of the workpiece to be inspected is determined, which specifically includes the following steps:
[0015] According to the microstructure damage defects of the standard sample and the microstructure damage defects, the graphitization microstructure damage state of the workpiece to be tested is determined.
[0016] Optionally, the microstructure damage defects include the area ratio of spherical graphite, the length of chain graphite and the amount of graphite.
[0017] Optionally, the workpiece to be inspected is subjected to a multi-effect fusion inspection of incremental magnetic permeability and tangential magnetic field intensity dynamic magnetization to extract a multi-magnetic characteristic parameter set, specifically comprising the following steps:
[0018] A dynamic magnetization multi-effect fusion detection system is used to perform dynamic magnetization multi-effect fusion detection on the workpiece to be detected, so as to obtain a multi-magnetic characteristic parameter set of the workpiece to be detected.
[0019] In the second aspect, the present application provides a graphitization damage state assessment device based on multi-feature fusion, including: a dynamic magnetization multi-effect fusion number detection system, a microscopic tissue damage defect detection module and a microscopic tissue damage state determination module.
[0020] A dynamic magnetization multi-effect fusion digital detection system is used to perform dynamic magnetization multi-effect fusion detection on a workpiece to be detected to obtain a multi-magnetic characteristic parameter set of the workpiece to be detected; the multi-magnetic characteristic parameter set includes characteristic parameters of a tangential magnetic field intensity signal and characteristic parameters of an incremental magnetic permeability signal; the characteristic parameters of the tangential magnetic field intensity signal include the third harmonic amplitude A3, the fifth harmonic amplitude A5 and the sum of higher harmonic amplitudes UHS in the tangential magnetic field intensity signal; the characteristic parameters of the incremental magnetic permeability signal include the amplitude mean Umean in the incremental magnetic permeability signal.
[0021] The microstructure damage defect detection module is used to input the multi-magnetic characteristic parameter set into the microstructure damage defect detection model to obtain the corresponding microstructure damage defect.
[0022] The microstructure damage state determination module is used to determine the graphitization microstructure damage state of the workpiece to be inspected according to the microstructure damage defects.
[0023] Optionally, the dynamic magnetization multi-effect fusion number detection system includes: a control module, an excitation module, a sensor, a sampling module and a host computer display module.
[0024] The control module includes a computer and an FPGA main control chip. The computer and the FPGA main control chip are connected via a communication interface. The control module is used to trigger instructions through the computer to generate excitation signals, control signal collection of the sampling module, and control waveform signal display of the host computer display module.
[0025] The excitation module includes a signal generator and a power amplifier. The excitation module is connected to the control module and the sensor respectively. The signal generator is used to generate a corresponding waveform signal according to the instruction of the control module, and then the excitation amplification of the waveform signal is realized through the power amplifier.
[0026] The sampling module includes a filter, a signal amplifier and a data collector. The sampling module is connected to the sensor, the control module and the host computer display module respectively. The control module sends instructions to control the sampling module to collect the sensor signal. The collected signal is amplified by the filter and the signal amplifier, and enters the host computer display module for display.
[0027] The upper computer display module is connected to the sampling module and the control module respectively. The magnetic field signal collected by the sampling module is displayed on the upper computer display module under the control of the control module.
[0028] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the multi-feature fusion graphitization damage state assessment method described above.
[0029] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the multi-feature fusion graphitization damage state assessment method described above.
[0030] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the multi-feature fusion graphitization damage state assessment method described above.
[0031] According to the specific embodiments provided in this application, this application discloses the following technical effects:
[0032] The present application provides a method and device for evaluating the graphitization damage state by fusion of multiple features, and performs multi-effect fusion detection of incremental magnetic permeability and tangential magnetic field intensity dynamic magnetization on the workpiece to be inspected, and extracts a multi-magnetic feature parameter set including the third harmonic amplitude A3, the fifth harmonic amplitude A5 and the sum of high-order harmonic amplitudes UHS in the tangential magnetic field intensity signal, and the amplitude mean Umean in the incremental magnetic permeability signal, and inputs the multi-magnetic feature parameter set into the microstructure damage defect detection model to obtain the corresponding microstructure damage defect, and finally the graphitization microstructure damage state of the workpiece to be inspected can be determined according to the microstructure damage defect. The above scheme of the present application adopts a simple process to realize the rapid, accurate and non-destructive evaluation of the graphitization microstructure damage state of carbon steel, which can effectively solve the problems of high cost, long evaluation cycle and destructiveness to the workpiece in the existing method for evaluating the graphitization microstructure damage state of carbon steel parts. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0034] Figure 1 A schematic diagram of the technical concept of a multi-feature fusion graphitization damage state assessment method provided in one embodiment of the present application.
[0035] Figure 2 A flowchart of establishing a damage state assessment library in a multi-feature fusion graphitization damage state assessment method provided in another embodiment of the present application.
[0036] Figure 3 A schematic diagram of the functional modules of a graphitization damage state assessment device based on multi-feature fusion provided in one embodiment of the present application.
[0037] Figure 4 A structural schematic diagram of a dynamic magnetization multi-effect fusion number detection system in a graphitization damage state assessment device based on multi-feature fusion provided in one embodiment of the present application.
[0038] Figure 5 A schematic diagram of the structure of a computer device provided in one embodiment of the present application.
[0039] Explanation of symbols: S1: control module; S2: excitation module; S3: sampling module; S4: host computer display module. DETAILED DESCRIPTION
[0040] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0041] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.
[0042] In an exemplary embodiment, Figure 1 As shown, a multi-feature fusion graphitization damage state assessment method is provided, comprising the following steps:
[0043] Step 1: Perform incremental magnetic permeability and tangential magnetic field intensity dynamic magnetization multi-effect fusion detection on the workpiece to be inspected, and extract a multi-magnetic characteristic parameter set; the multi-magnetic characteristic parameter set includes tangential magnetic field intensity signal characteristic parameters and incremental magnetic permeability signal characteristic parameters. The tangential magnetic field intensity signal characteristic parameters include the third harmonic amplitude A3, the fifth harmonic amplitude A5 and the sum of high-order harmonic amplitudes UHS in the tangential magnetic field intensity signal. The incremental magnetic permeability signal characteristic parameters include the amplitude mean Umean in the incremental magnetic permeability signal.
[0044] The target sample was tested for incremental magnetic permeability and tangential magnetic field intensity using a dynamic magnetization multi-effect fusion detector. The third harmonic amplitude A3, the fifth harmonic amplitude A5, the sum of high-order harmonic amplitudes UHS and the amplitude mean Umean in the incremental magnetic permeability signal in the tangential magnetic field intensity signal were extracted as characteristic parameters. A3 and A5 here are both word characteristic parameters that are sensitive to microscopic tissue damage defects and are determined experimentally. There are multiple magnetic characteristic parameters, and only a few are sensitive to microscopic tissue damage defects. The magnetic characteristic parameters that are more conducive to evaluating microstructures are selected. A3 and A5 here are two types of magnetic characteristic parameters.
[0045] Specifically in this embodiment, in step 1, a dynamic magnetization multi-effect fusion detection system is used to perform dynamic magnetization multi-effect fusion detection on the workpiece to be detected to obtain a multi-magnetic feature parameter set of the workpiece to be detected.
[0046] Step 2: Input the multi-magnetic feature parameter set into the microstructure damage defect detection model to obtain the corresponding microstructure damage defect. The microstructure damage defect detection model is constructed based on a neural network algorithm, a gradient boosting tree regression algorithm or an adaptive boosting tree regression algorithm.
[0047] As an example embodiment, the algorithm used to construct the microstructure damage defect detection model is the BP neural network algorithm, which is a neural network trained using the back propagation algorithm and has strong nonlinear mapping and generalization capabilities. Its core idea is to apply the gradient descent algorithm to the weight update of the neural network, and to make the output of the network closer and closer to the target value by continuously adjusting the weights.
[0048] In the BP neural network, the output value of each neuron is calculated through the activation function. Common activation functions include Sigmoid function, ReLU function, etc. The output of the Sigmoid function is between 0 and 1 and can be used in the output layer; the output of the ReLU function is the non-negative part of the input value and can be used in the hidden layer. The backpropagation algorithm is divided into two stages: forward propagation and error backpropagation. In the forward propagation stage, the input data is passed forward through the network to calculate the output value; in the error backpropagation stage, according to the error between the output value and the target value, the error is backpropagated through the network to update the weight. The specific process is as follows:
[0049] Initialize the neural network weights and thresholds: Initialize the weights from the input layer to the hidden layer to ω1, with the initial value set randomly; Initialize the weights from the hidden layer to the output layer to ω2, with the initial value set randomly. Initialize the threshold of the hidden layer to b1, and the threshold of the output layer to b2.
[0050] Calculate forward propagation: Data passes through the hidden layer and the output layer, and the weighted sum of the nodes z = ω + b is calculated, where ω is the weight and b is the threshold. Use the activation function (Sigmoid or ReLU) to perform nonlinear transformation on the weight sum of each node to obtain the output of the node (y = f(z)). For the output layer, calculate the loss function according to the actual task.
[0051] Calculate backpropagation: Calculate the gradient of the loss function with respect to each weight, starting from the output layer, and use the chain rule to calculate the direction and magnitude of the weight update.
[0052] Weight update: Update the weights of all connections to the hidden layer and the output layer based on the gradient obtained through back propagation.
[0053] Iterative process: Repeat the forward propagation and back propagation calculations until the stopping condition is met (such as reaching the preset number of training rounds, loss function convergence, etc.).
[0054] Specifically in this embodiment, the multi-magnetic characteristic parameter set is used as the input of the model, and the measured carbon steel graphitization microstructure damage defect is used as the output, and the BP neural network algorithm is used for training to obtain a good microstructure damage defect detection model. The training and prediction process of the model can be calculated and processed using MATLAB software to obtain a microstructure damage defect detection model.
[0055] The MATLAB programming language and MATLAB function library are used to implement the prediction of carbon steel graphitization microstructure damage defects by BP neural network. First, the characteristic parameter data set is imported using the xlsread function. The characteristic parameters are the input characteristic parameters of the model, that is, the X characteristic matrix, and the carbon steel graphitization microstructure damage defects are the output prediction targets of the prediction model, that is, the Y target vector. Then, the randperm and res functions are used to shuffle the data set and divide the data set into a training set and a test set. The training set is used to train a good prediction model, and the test set is used to verify the accuracy and stability of the prediction model. Then, the training set and the test set are normalized, and the processed training data set is input into the newff function, and the relevant BP neural network algorithm model parameters such as the number of input layer nodes, the number of hidden layer nodes, the number of output layer nodes, and the number of training times are set. The trained model can obtain the distribution and error of the predicted value and the true value of the graphitization microstructure damage defect of carbon steel in the training set data, as well as the distribution and error of the predicted value and the true value of the graphitization microstructure damage defect of carbon steel in the test set data, so as to obtain the predicted value corresponding to the magnetic parameter data set, that is, the graphitization microstructure damage defect.
[0056] Step 3: Determine the graphitization microstructure damage state of the workpiece to be inspected based on the microstructure damage defects.
[0057] In another embodiment, before determining the graphitized microstructure damage state of the workpiece to be inspected in step 3, Figure 2 The method further comprises the following steps:
[0058] The standard specimen is prepared using the same material as the workpiece to be tested.
[0059] Grind the surface of the standard specimen to remove the oxide layer on the surface of the standard specimen until a smooth metal surface is exposed.
[0060] Use a microanalysis instrument to observe the metallographic microstructure of the smooth metal surface, and use image processing software to analyze the microstructure damage defects of the standard sample.
[0061] The purpose of this series of steps before step 3 is to establish a damage state assessment library, which is used in subsequent steps to determine the graphitization microstructure damage state of other samples with undetermined microstructure damage defects. After obtaining the library, step 3 is specifically as follows: according to the microstructure damage defects of the standard sample and the microstructure damage defects, the graphitization microstructure damage state of the workpiece to be tested is determined; the microstructure damage defects include the proportion of spherical graphite area, the length of chain graphite, and the number of graphite.
[0062] The present embodiment provides a multi-feature fusion graphitization damage state assessment method, which has at least the following beneficial effects compared with the prior art: the graphitization microstructure defects of carbon steel are assessed by using multiple parameters, which can analyze the problem more comprehensively, predict more accurately, improve the generalization ability of the model, and reduce the uncertainty and risk of decision-making compared with the single parameter assessment of graphitization microstructure defects; after completing the preliminary work, the graphitization microstructure defect assessment of in-service carbon steel can be quickly realized, and the graphitization microstructure defect assessment of in-service carbon steel can be realized; when testing the carbon steel to be tested, it is only necessary to remove the paint layer and the oxide layer on the surface of the carbon steel. The detection of the present invention does not need to destroy the detection object, and can be used to detect the workpiece on site; the present embodiment uses a dynamic magnetization multi-effect fusion detection probe, which does not require a coupling agent, and has some advantages: it reduces pollution to the environment and staff, makes detection faster and saves time, improves detection accuracy, and has a wider range of applications.
[0063] Based on the same inventive concept, the embodiment of the present application also provides a graphitization damage state assessment device based on multi-feature fusion for implementing the above-mentioned graphitization damage state assessment method based on multi-feature fusion. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more embodiments of the graphitization damage state assessment device based on multi-feature fusion provided below can refer to the limitations of the graphitization damage state assessment method based on multi-feature fusion above, and will not be repeated here.
[0064] In an exemplary embodiment, Figure 3 As shown, a graphitization damage state assessment device based on multi-feature fusion is provided, including: a dynamic magnetization multi-effect fusion number detection system, a microscopic tissue damage defect detection module and a microscopic tissue damage state determination module.
[0065] A dynamic magnetization multi-effect fusion digital detection system is used to perform dynamic magnetization multi-effect fusion detection on a workpiece to be detected to obtain a multi-magnetic characteristic parameter set of the workpiece to be detected; the multi-magnetic characteristic parameter set includes characteristic parameters of a tangential magnetic field intensity signal and characteristic parameters of an incremental magnetic permeability signal; the characteristic parameters of the tangential magnetic field intensity signal include the third harmonic amplitude A3, the fifth harmonic amplitude A5 and the sum of higher harmonic amplitudes UHS in the tangential magnetic field intensity signal; the characteristic parameters of the incremental magnetic permeability signal include the amplitude mean Umean in the incremental magnetic permeability signal.
[0066] The microstructure damage defect detection module is used to input the multi-magnetic characteristic parameter set into the microstructure damage defect detection model to obtain the corresponding microstructure damage defect.
[0067] The microstructure damage state determination module is used to determine the graphitization microstructure damage state of the workpiece to be inspected according to the microstructure damage defects.
[0068] certainly, Figure 3 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different functions. Figure 3 One or at least two components of the device shown.
[0069] Specifically in this embodiment, Figure 4 As shown, the dynamic magnetization multi-effect fusion number detection system includes: a control module S1, an excitation module S2, a sensor, a sampling module S3 and a host computer display module S4; the sensor is arranged above the detection sample.
[0070] The control module S1 includes a computer and an FPGA main control chip. The computer and the FPGA main control chip are connected via a communication interface. The control module S1 is used to trigger instructions through the computer to generate excitation signals, control signal acquisition of the sampling module S3, and control waveform signal display of the host computer display module S4.
[0071] The excitation module S2 includes a signal generator and a power amplifier. The excitation module S2 is connected to the control module S1 and the sensor respectively. The signal generator is used to generate a corresponding waveform signal according to the instruction of the control module S1, and then the waveform signal is amplified by the power amplifier.
[0072] The sampling module S3 includes a filter, a signal amplifier and a data collector. The sampling module S3 is connected to the sensor, the control module S1 and the upper computer display module S4 respectively. The control module S1 sends instructions to control the sampling module S3 to collect the sensor signal. The collected signal is amplified by the filter and the signal amplifier and enters the upper computer display module S4 for display. The signals collected by the collection module include tangential magnetic field intensity signals and incremental magnetic permeability signals; Figure 4The medium tangential magnetic field strength signal is composed of a test waveform, a basic waveform and a harmonic waveform. The characteristic parameters of the tangential magnetic field are extracted after frequency domain analysis. The incremental magnetic permeability butterfly curve signal shows the signal curves of four different states of graphitization (state 1 to state 4), which are used to extract the characteristic parameters of the incremental magnetic permeability signal.
[0073] The upper computer display module S4 is connected to the sampling module S3 and the control module S1 respectively. The magnetic field signal collected by the sampling module S3 is displayed on the upper computer display module S4 under the control of the control module S1. The upper computer display module S4 displays a graph including a tangential magnetic field intensity signal and an incremental magnetic permeability signal. The control module S1 extracts the third harmonic amplitude A3, the fifth harmonic amplitude A5, and the sum of the high harmonic amplitudes UHS from the displayed tangential magnetic field intensity signal as characteristic parameters of the tangential magnetic field intensity signal; and extracts the amplitude mean Umean from the displayed incremental magnetic permeability signal as a characteristic parameter of the incremental magnetic permeability signal.
[0074] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 5 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a multi-feature fusion graphitization damage state assessment method provided in the above embodiment is implemented.
[0075] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0076] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.
[0077] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.
[0078] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.
[0079] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).
[0080] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.
[0081] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0082] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.
Claims
1. A multi-feature fusion graphitization damage state assessment method, characterized in that: include: Perform incremental magnetic permeability and tangential magnetic field intensity dynamic magnetization multi-effect fusion detection on the workpiece to be inspected, and extract a multi-magnetic feature parameter set; The multi-magnetic characteristic parameter set includes tangential magnetic field intensity signal characteristic parameters and incremental magnetic permeability signal characteristic parameters; The characteristic parameters of the tangential magnetic field intensity signal include the third harmonic amplitude A3, the fifth harmonic amplitude A5 and the sum of the higher harmonic amplitudes UHS in the tangential magnetic field intensity signal; the characteristic parameters of the incremental magnetic permeability signal include the amplitude mean Umean in the incremental magnetic permeability signal; Inputting the multi-magnetic characteristic parameter set into a microscopic tissue damage defect detection model to obtain corresponding microscopic tissue damage defects; According to the microstructure damage defect, the graphitization microstructure damage state of the workpiece to be inspected is determined.
2. The multi-feature fusion graphitization damage state assessment method according to claim 1, characterized in that: The microstructure damage defect detection model is constructed based on a neural network algorithm, a gradient boosting tree regression algorithm or an adaptive boosting tree regression algorithm.
3. The multi-feature fusion graphitization damage state assessment method according to claim 1, characterized in that: Before determining the graphitized microstructure damage state of the workpiece to be inspected according to the microstructure damage defect, the method further includes: A standard sample is prepared by using the same material as the workpiece to be tested; Grinding the surface of the standard sample to remove the oxide layer on the surface of the standard sample until a smooth metal surface is exposed; Observe the metallographic microstructure of the smooth metal surface using a microscopic analysis instrument, and analyze the microstructure damage defects of the standard sample using a graphics processing software; According to the microscopic structural damage defect, determining the graphitization microscopic structural damage state of the workpiece to be inspected specifically includes: The graphitization microstructure damage state of the workpiece to be inspected is determined according to the microstructure damage defect of the standard sample and the microstructure damage defect.
4. The multi-feature fusion graphitization damage state assessment method according to claim 1, characterized in that: The microstructure damage defects include the area ratio of spherical graphite, the length of chain graphite and the amount of graphite.
5. The multi-feature fusion graphitization damage state assessment method according to claim 1, characterized in that: The workpiece to be inspected is subjected to a multi-effect fusion test of incremental magnetic permeability and tangential magnetic field intensity dynamic magnetization, and a multi-magnetic characteristic parameter set is extracted, including: A dynamic magnetization multi-effect fusion detection system is used to perform dynamic magnetization multi-effect fusion detection on the workpiece to be detected, so as to obtain a multi-magnetic characteristic parameter set of the workpiece to be detected.
6. A multi-feature fusion graphitization damage state assessment device, characterized in that: include: Dynamic magnetization multi-effect fusion number detection system, microscopic tissue damage defect detection module and microscopic tissue damage state determination module; The dynamic magnetization multi-effect fusion detection system is used to perform dynamic magnetization multi-effect fusion detection on the workpiece to be detected, and obtain a multi-magnetic characteristic parameter set of the workpiece to be detected; the multi-magnetic characteristic parameter set includes a tangential magnetic field intensity signal characteristic parameter and an incremental magnetic permeability signal characteristic parameter; the tangential magnetic field intensity signal characteristic parameter includes the third harmonic amplitude A3, the fifth harmonic amplitude A5 and the sum of high harmonic amplitudes UHS in the tangential magnetic field intensity signal; the incremental magnetic permeability signal characteristic parameter includes the amplitude mean Umean in the incremental magnetic permeability signal; The microscopic tissue damage defect detection module is used to input the multi-magnetic characteristic parameter set into the microscopic tissue damage defect detection model to obtain the corresponding microscopic tissue damage defect; The microstructure damage state determination module is used to determine the graphitized microstructure damage state of the workpiece to be detected according to the microstructure damage defect.
7. The graphitization damage state assessment device with multi-feature fusion according to claim 6 is characterized in that: The dynamic magnetization multi-effect fusion number detection system comprises: a control module, an excitation module, a sensor, a sampling module and a host computer display module; The control module includes a computer and an FPGA main control chip, the computer and the FPGA main control chip are connected via a communication interface, and the control module is used to trigger instructions through the computer to achieve the generation of excitation signals, control the signal collection of the sampling module, and control the waveform signal display of the upper computer display module; The excitation module includes a signal generator and a power amplifier, and the excitation module is connected to the control module and the sensor respectively; the signal generator is used to generate a corresponding waveform signal according to the instruction of the control module, and then realize the excitation amplification of the waveform signal through the power amplifier; The sampling module includes a filter, a signal amplifier and a data collector. The sampling module is connected to the sensor, the control module and the host computer display module respectively. The control module issues instructions to control the sampling module to collect the signal of the sensor. The collected signal is amplified by the filter and the signal amplifier, and enters the host computer display module for display; The host computer display module is connected to the sampling module and the control module respectively. The magnetic field signal collected by the sampling module is displayed on the host computer display module under the control of the control module.
8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the multi-feature fusion graphitization damage state assessment method according to any one of claims 1 to 5.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the graphitization damage state assessment method of multiple feature fusion described in any one of claims 1 to 5 is implemented.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the graphitization damage state assessment method of multiple feature fusion described in any one of claims 1 to 5 is implemented.