Intelligent detection method and system for impact performance of a forging blank

Abstract

The present application relates to the field of data processing, in particular to a kind of intelligent detection method and system of forging billet impact performance, the method first executes micro-impact and impact break test to sample forging, obtains the basic data set containing geometric dimension, force displacement curve, impact work etc.Parameter, group storage according to material type and shape.Secondly, based on each group of data, build inflection point size correlation model and target fracture energy impact work correlation model, respectively represent the correlation between inflection point coordinate and geometric dimension, fracture energy and impact work.Correlation storage of model and forging group identity mark to database.When receiving detection request, micro-impact test is carried out to the requested forging, and the impact performance parameters are predicted using the correlation model in the database.The method combines experimental data and intelligent model to realize efficient and accurate detection of forging impact performance, and is suitable for different material types and shapes of forging billet.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of material mechanical property detection, in particular to a method and system for intelligently detecting impact performance of a forging blank. BACKGROUND

[0002] Currently, in the field of forging blank impact performance detection, the mainstream technical solution mainly relies on analyzing the image data of the surface and cross section of the forged piece after being broken, extracting crack length, expansion direction, fracture morphology and other characteristic parameters through computer vision algorithm, and then evaluating the impact performance (such as the technology disclosed in patent document CN117451539A). Such method has obvious limitations: first, the destructive detection method of breaking the forged piece cannot preserve the integrity of the forged piece, and is not suitable for high-value or irreplaceable forged piece detection; second, the image analysis process involves steps such as manual annotation and feature extraction algorithm design, and has problems such as low data processing efficiency and poor model generalization ability. With the deep application of computer technology in the field of material detection, the industry urgently needs a forging blank impact performance detection scheme based on non-destructive detection data, which integrates computer programs and intelligent algorithms, and realizes rapid prediction of impact performance through automatic processing and modeling analysis of micro-impact experiment digital data (such as force-displacement curve and crack expansion area measurement value), thereby avoiding the destructive defects and low data processing efficiency of traditional methods. SUMMARY

[0003] To solve the above technical problems, the technical scheme adopted by the present application is as follows:

[0004] According to the first aspect of the present application, an intelligent detection method for impact performance of a forging blank is provided, which comprises the following steps:

[0005] S100, performing a micro-impact experiment and a breaking experiment on each forging in a sample forging, obtaining micro-impact record data and breaking record data of the forging, and constructing a basic data set based on the record data of all forgings; wherein the sample forgings include a group of forgings with the same material type but different shape types, and each forging group contains forgings with different geometric size data; the basic data set includes a plurality of record sets, each record set corresponds to a forging group and contains the identity of the forging group, the micro-impact record data and the breaking record data, the micro-impact record data includes geometric size data, force-displacement curve, crack expansion area measurement value and temperature increase value, and the breaking record data includes geometric size data and impact work measurement value, and the force-displacement curve is used to represent the numerical correspondence between impact force and pit depth.

[0006] S200, based on the micro-impact record data and the impact fracture record data corresponding to each group of forgings, obtain the inflection point size correlation model and the target fracture energy impact work correlation model corresponding to the group of forgings; wherein the inflection point size correlation model is used to represent the correlation between the inflection point coordinates and the geometric size data, and the target fracture energy impact work correlation model is used to represent the correlation between the fracture energy and the impact work.

[0007] S300, the identity of each group of forgings, the inflection point size correlation model and the target fracture energy impact work correlation model are associated, and stored in the current database.

[0008] S400, when receiving a forging performance detection request, performing a micro-impact experiment on the requested forging and predicting the impact work of the requested forging based on the inflection point size correlation model and the target fracture energy impact work correlation model in the current database.

[0009] According to the second aspect of the present application, an intelligent detection system for the impact performance of a forging blank is provided, and the system comprises:

[0010] The sample processing module is configured to perform a micro-impact experiment and an impact fracture experiment on the sample forgings, obtain micro-impact record data and impact fracture record data, and construct a basic data set; wherein the sample forgings include groups of forgings with the same material type but different shape types, and each group of forgings contains forgings with different geometric size data; the basic data set includes a plurality of record sets, each record set corresponding to a group of forgings and containing the identity of the group of forgings, the micro-impact record data and the impact fracture record data, the micro-impact record data including geometric size data, force displacement curve, crack propagation area measurement value and temperature increase value, and the impact fracture record data including geometric size data and impact work measurement value, the force displacement curve being used to represent the numerical correspondence between impact force and pit depth.

[0011] The model construction module is configured to obtain the inflection point size correlation model and the target fracture energy impact work correlation model corresponding to each group of forgings based on the micro-impact record data and the impact fracture record data corresponding to each group of forgings; wherein the inflection point size correlation model is used to represent the correlation between the inflection point coordinates and the geometric size data, and the target fracture energy impact work correlation model is used to represent the correlation between the fracture energy and the impact work.

[0012] The data storage module is configured to associate the identity of each group of forgings, the inflection point size correlation model and the target fracture energy impact work correlation model, and store them in the current database.

[0013] The prediction module is configured to, when receiving a forging performance detection request, perform a micro-impact experiment on the requested forging and predict the impact work of the requested forging based on the inflection point size correlation model and the target fracture energy impact work correlation model in the current database.

[0014] The present application has at least the following beneficial effects:

[0015] The intelligent detection method for impact performance of a forging blank provided by the embodiments of the present application breaks through the limitations of traditional destructive detection by constructing an inflection point size correlation model and a target fracture energy impact work correlation model, and fusing multi-dimensional physical performance data obtained through micro-impact experiments and impact fracture experiments. The method collects dynamic parameters such as force displacement curves and crack propagation areas in real time through non-destructive micro-impact experiments, combines key indicators such as impact work obtained through impact fracture experiments, and establishes a quantitative correlation between material performance parameters by using intelligent algorithms. Compared with traditional detection techniques, the method realizes a technological innovation from “post-event destructive analysis” to “real-time non-destructive prediction”, not only significantly improving detection efficiency and reducing experimental costs, but also providing key technical support for intelligent quality control of forging production lines through automatic data processing and model prediction.

[0016] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become apparent through the following description. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0018] Figure 1 The flowchart of the intelligent detection method for impact performance of a forging blank provided by the embodiments of the present application. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present application will be described clearly and completely in the following with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this description, the singular forms "a", "an" and "the" include plural references unless the context clearly dictates otherwise. The term "and / or" as used herein comprises any and all combinations of one or more of the associated listed items.

[0021] It is to be understood that some of the example embodiments are described in terms of a process or method depicted as a flowchart. Although a flowchart can describe a process as a sequential process, many of the steps can be performed in parallel, concurrently or simultaneously. In addition, the order of the steps can be re-arranged. A process can be terminated when its operations are completed, but could also occur intermittently during operations of another process or method. Processes can correspond in part to methods, functions, routines, sub-routines, sub-programs, etc.

[0022] The embodiment of the present application provides a kind of intelligent detection method for forging billet impact performance, as shown in Figure 1 The method comprises the following steps:

[0023] S100, micro-impact experiment and impact fracture experiment are carried out to each forging in sample forging, the micro-impact record data and impact fracture record data of the forging are obtained, and the basic data set is constructed based on the record data of all forgings.

[0024] In the embodiment of the present application, the sample forging includes a group of forgings with the same material type but different shape types, and each group of forgings contains forgings with different geometric size data.

[0025] In the embodiment of the present application, the material type can be determined based on the material suitable for preparing the forging, for example, it can include material types such as low carbon steel, aluminum alloy and cast iron. The shape type can be determined based on the common forging billet, for example, it can include shape types such as square, cylindrical and flat. Wherein, the geometric size data of each forging is used to characterize the geometric size specification of the forging, which can be determined based on the corresponding shape type, for example, the geometric size data of square forgings and flat forgings includes length, width and other data, and the geometric size data of cylindrical forgings includes length and diameter. The number of geometric size data of each shape type can be set based on actual needs, which can only be able to cover the common forging geometric size data.

[0026] Further, in the embodiment of the present application, the basic data set can include a plurality of record sets, which are stored in the form of structured record sets. Each record set corresponds to a group of forgings, and contains the identity of the group of forgings, the micro-impact record data and the impact fracture record data of each forging.

[0027] In the embodiment of the present application, the micro-impact record data can include geometric size data, force displacement curve, crack propagation area measurement value and temperature increase value, and the impact fracture record data can include geometric size data and impact work measurement value, wherein the force displacement curve is used to characterize the numerical correspondence of impact force and pit depth.

[0028] In the embodiment of the present application, the identity of each forging is encoded by a composite coding rule, which is generated based on the standardized coding combination of material type and shape type. Specifically, the material type and shape type are respectively encoded by independent character systems, wherein the material type coding complies with the national standards such as GB / T13304.1-2008 "Steel Classification", and the shape type coding is established according to the geometric characteristics of forgings to form a standardized coding mapping table stored in the system database. For example, the material type coding uses letter identification (such as A-Z), and the shape type coding uses numerical identification (such as 0-9), and the two are combined to form a unique identity. In an illustrative example, if the material type of a certain forging is 45# steel, its standardized material code is "C"; the shape type is cylindrical, and the corresponding shape code is "1", then the identity of the forging group is combined as "C1". Different material types (such as aluminum alloy, titanium alloy) or shape types (such as disc-shaped, rectangular) correspond to different codes, ensuring the uniqueness and scalability of the coding system.

[0029] In the embodiment of the present application, the micro-impact experiment refers to the pulse energy loading experiment performed on the requested forging using a drop hammer impact testing machine (such as INSTRON 9250HV) in an environment of 23±2℃. The specific implementation is as follows:

[0030] (1) Impact point layout

[0031] N impact positions (N≥3) are arranged along the length direction of the forging, and the distance between any two adjacent impact positions is a preset value ΔL (unit: mm), wherein ΔL satisfies the following conditions:

[0032] When the length L of the forging is ≤200mm, ΔL=10mm;

[0033] When the length L of the forging is >200mm, ΔL=20mm;

[0034] All impact positions are located within ±5mm of the center axis of the forging, ensuring uniform transmission of impact energy.

[0035] (2) Experimental parameters

[0036] Impact speed: 10±0.5m / s, precise speed adjustment is achieved by closed-loop control of a servo motor.

[0037] Impact energy: dynamically adjusted according to the yield strength σs of the forging material, satisfying E=0.1×σs×A, wherein E is the impact energy and A is the cross-sectional area of the impact position.

[0038] Sampling frequency: force-displacement curve sampling frequency ≥10kHz, 16-bit ADC module is configured to ensure data acquisition accuracy.

[0039] (3) Stepwise loading control

[0040] In the process of micro-impact experiment, the corresponding impact force is applied to each impact position by using an incremental impact force loading strategy to form a dent at the position. The impact force of each impact is increased by a fixed value ΔF (unit: N) compared to the previous impact. The fixed value can be pre-set according to experimental requirements. For example, the first impact force is F1, the second impact force is F1+ΔF, the third impact force is F1+2ΔF, and so on, to ensure that the load increment of each impact remains constant. In the specific experiment, the impact force is applied to the forging in sequence, and the impact force of the next impact is increased by the pre-set fixed value ΔF based on the impact force of the previous impact. The increment of each impact force is accurately adjusted by controlling the loading system to realize the step-by-step loading test of the forging.

[0041] (4) Data acquisition

[0042] The dent depth of each stamping position and the infrared thermal image data of the impact area are collected for temperature field analysis.

[0043] In the embodiment of the present application, the force-displacement curve is a two-dimensional curve with impact force as the horizontal axis and dent depth as the vertical axis. The force-displacement curve of each forging is constructed by the impact force and dent depth data of each impact position in the micro-impact experiment, and the specific implementation is as follows:

[0044] A rectangular coordinate system with impact force (unit: N) as the horizontal axis and dent depth (unit: mm) as the vertical axis is constructed, and the measured impact force value and the corresponding dent depth value of each impact position are mapped into discrete points in the coordinate system. The discrete points are fitted into a continuous curve by a smoothing interpolation algorithm, and the force-displacement curve of the forging is obtained. The force-displacement curve is stored as a two-dimensional array in the form of digital signal, and the array elements are coordinate pairs such as (F1, D1), (F2, D2), …, (Fn, Dn). This facilitates subsequent feature extraction and numerical calculation by computer programs, and n is the number of impact positions. n n

[0045] In the embodiment of the present application, the crack propagation area of each forging can be obtained by using non-contact image detection technology. Specifically, a high-resolution image scanner is used to digitally image the impact area of the forging to generate a gray-scale image with a precision of microns. Then, an image recognition algorithm based on deep learning is used to process the scanned image: first, a semantic segmentation model such as U-Net is used to automatically identify the crack contour, then morphological operations are used to remove noise interference, and finally based on pixel statistics and scale calibration, the crack area in the two-dimensional image is converted into actual physical size, so that the crack propagation area value is accurately obtained. The value is stored in a standardized data format for subsequent fracture energy calculation and model analysis.

[0046] ​​In the embodiment of the present application, the temperature increase value of each forging can be obtained through the recorded infrared thermal image data.

[0047] In the embodiment of the present application, the impact fracture record data of each forging is obtained through a standard impact fracture experiment, specifically in accordance with the national standard GB / T 229-2020 "Metallic Materials Charpy Pendulum Impact Test Method". During the experiment, the forging is processed into a standard impact specimen (such as a V-shaped notch or a U-shaped notch specimen), an impact load is applied using a pendulum impact testing machine, and load-displacement data during the impact process are collected in real time through a high-precision force sensor and a displacement encoder, while the impact absorbed work value is recorded. The final obtained impact fracture record data includes geometric size data and impact work measurement value, and all data are stored in a digital format after calibration, ensuring compatibility and traceability with the micro-impact experiment data.

[0048] S200, based on the micro-impact record data and the impact fracture record data corresponding to each forging group, obtaining the inflection point size correlation model and the target fracture energy impact work correlation model corresponding to the forging group; wherein the inflection point size correlation model is used to represent the correlation between the inflection point coordinates and the geometric size data, and the target fracture energy impact work correlation model is used to represent the correlation between the fracture energy and the impact work.

[0049] In the embodiment of the present application, the fracture energy is the energy absorbed per unit area during the material fracture process.

[0050] Further, S200 can specifically include:

[0051] S201, processing the force-displacement curve of the forging group to obtain the inflection point coordinates of the force-displacement curve and the area under the curve, and based on the pre-stored fracture energy calculation formula, obtaining the fracture energy corresponding to each forging of the forging group.

[0052] In the embodiment of the present application, the inflection point is the point where the curvature of the force-displacement curve changes abruptly, corresponding to the mechanical behavior such as material yield or fracture. The inflection point recognition adopts the second derivative sign mutation detection algorithm known in the art (such as the inflection point detection method based on finite difference method disclosed in the "Materials Mechanics Experiment Course"), which identifies the position of the curvature sign change by calculating the first derivative and the second derivative of the curve. The specific implementation steps are omitted here as they belong to the prior art.

[0053] In the embodiment of the present application, the area under the curve represents the energy absorbed by the material, which can be calculated by numerical integration method (such as trapezoidal method, Simpson method) or piecewise integration method. For example, when using the trapezoidal method, the force-displacement curve is discretized into several data points, and the total area is obtained by summing the areas of the trapezoids formed by adjacent points. The specific calculation steps are referred to the standard method for energy integration in GB / T228.1-2021 "Metallic Materials Tensile Test", which will not be described here.

[0054] In the embodiment of the present application, the pre-stored fracture energy calculation formula satisfies the following condition: Gc=Ac / Af•(1+k•△T); wherein, Gc is the fracture energy, the unit is J / m 2 , Ac is the area under the curve, the unit is N•mm. Af is the crack propagation area, the unit is mm 2 . k is the temperature correction coefficient, which can be determined based on the material type. △T is the temperature increase value, the unit is K.

[0055] In the embodiment of the present application, the fracture energy calculation formula introduces a temperature correction term (1+k•△T) to quantify the influence of temperature rise on material fracture energy during impact, which is suitable for micro-impact experimental scenarios with impact frequency higher than 10Hz or cumulative temperature rise exceeding 10K. The temperature correction coefficient is stored in the system database and can be automatically matched according to the material temperature variation performance data in GB / T229-2020 “Metallic Materials Charpy Pendulum Impact Test Method”.

[0056] S202, by inputting the fracture energy of each forging into the pre-stored initial fracture energy impact work correlation model, the impact work pre-estimation value of the forging is obtained.

[0057] In the embodiment of the present application, the pre-stored initial fracture energy impact work correlation model can be an empirical formula, a theoretical model or a simple model based on historical data. In one illustrative embodiment, the initial fracture energy impact work correlation model can be represented as: Epre=a×Gc+b, wherein Epre is the impact work pre-estimation value, and a and b are both fitting coefficients.

[0058] In one illustrative embodiment, the pre-stored initial fracture energy impact work correlation model can be obtained based on the initial received basic data set, specifically by using the least squares method to solve the parameters of the initial fracture energy impact work correlation model using the fracture energy and impact work measurement values corresponding to the initial received certain forging group, and verifying the model accuracy using the coefficient of determination and the mean square error to obtain the initial fracture energy impact work correlation model.

[0059] S203, regression analysis is performed on all inflection point coordinates and geometric size data of the forging group to establish an inflection point size correlation model between the inflection point coordinates and the geometric size data.

[0060] In the embodiment of the present application, the inflection point size correlation model includes a force size correlation model and a displacement size correlation model, the force size correlation model is used to represent the correlation between the impact force and the geometric size data, and the displacement size correlation model is used to represent the correlation between the displacement and the geometric size data.

[0061] In the embodiments of the present application, the existing regression analysis method can be used to establish the inflection point size correlation model between the inflection point coordinates and the geometric size data. For example, the inflection point coordinates (including force coordinates and displacement coordinates) and the corresponding geometric size data of the group of forgings are subjected to regression analysis, and the specific steps are as follows: first, the force coordinates, displacement coordinates, and geometric size data are subjected to standardization preprocessing, then the multivariate linear regression or polynomial regression algorithm is used to fit the mapping relationship between the inflection point coordinates and the geometric size data, the model parameters are solved by the least square method, and the model accuracy is verified by using the determination coefficient and the mean square error, and finally the inflection point size correlation model representing the correlation between the inflection point coordinates and the geometric size data is established, which can realize the prediction of the inflection point of the force-displacement curve of the forging based on the size of the forging.

[0062] In one illustrative embodiment, the inflection point size correlation model can be represented as: y = β0+ β1x1+ … + β z x z + γ; wherein y is the force coordinate or the displacement coordinate, x z is the zth size parameter in the geometric size data, z is the number of size parameters in the geometric size data, β0, β1, …, β z are regression coefficients, and γ is an error term.

[0063] In S204, based on the impact work pre-estimates and the impact work measured values of the group of forgings, a correction coefficient of the group of forgings is obtained, and the initial fracture energy-impact work correlation model is corrected based on the correction coefficient to obtain a correction result, and the correction result is taken as the target fracture energy-impact work correlation model of the group of forgings.

[0064] In one illustrative embodiment of the present application, the correction coefficient h of each group of forgings is the ratio of the average of all impact work measured values corresponding to the group of forgings to the average of all impact work pre-estimates, i.e., h = AvgEmea / AvgEpre.

[0065] Wherein, AvgEmea is the average of all impact work measured values corresponding to the group of forgings, and AvgEpre is the average of all impact work pre-estimates corresponding to the group of forgings.

[0066] In another embodiment of the present application, the correction coefficient of each group of forgings is obtained based on the least square method, and the obtained correction coefficient h satisfies the following condition: .

[0067] Wherein, is the impact work measured value of the uth forging in the group of forgings, u takes a value from 1 to Q, Q is the number of forgings in the group of forgings, is the impact work pre-estimate of the uth forging in the group of forgings.

[0068] In an embodiment of the present application, the target fracture energy-impact work correlation model can be expressed as: Ecorr=h•Epre, where Ecorr is the modified impact work evaluation value, and Epre represents the impact work evaluation value obtained based on the initial fracture energy-impact work correlation model.

[0069] In another embodiment of the present application, the target fracture energy-impact work correlation model can be expressed as: where h1=AvgEmea / AvgEpre, .

[0070] In an embodiment of the present application, the specific determination method of the target fracture energy-impact work correlation model can be determined based on error indicators such as mean square error, relative error, absolute error, etc., and the specific determination method can be a prior art.

[0071] As known by those skilled in the art, in actual application scenarios, the target fracture energy-impact work correlation model can be dynamically updated during use, and the specific updating method can use existing methods, for example, when 100 valid data are cumulatively processed, the new data are used to automatically recalculate the correction coefficient, and if the prediction accuracy of the new model is higher than the prediction accuracy of the original model by a preset value, the current effective model is updated.

[0072] S300, the identity of each group of forgings, the inflection point size correlation model and the target fracture energy-impact work correlation model are associated, and stored in the current database.

[0073] In an embodiment of the present application, the identity of each group of forgings, the inflection point size correlation model and the target fracture energy-impact work correlation model can be stored as a record, and the specific storage method can be a prior art.

[0074] S400, when receiving a forging performance detection request, performing a micro-impact experiment on the requested forging and predicting the impact work of the requested forging based on the inflection point size correlation model and the target fracture energy-impact work correlation model in the current database.

[0075] Further, S400 specifically includes:

[0076] S401, performing a micro-impact experiment on the requested forging to obtain micro-impact record data of the requested forging.

[0077] The specific implementation of performing a micro-impact experiment on the requested forging can refer to the foregoing content.

[0078] S402, processing the force-displacement curve in the micro-impact record data of the requested forging to obtain the corresponding inflection point coordinates and area under the curve, and taking the obtained inflection point coordinates as the coordinates to be processed.

[0079] S403, performing a query operation in the current database with the identity of the requested forging as input, if the corresponding identity is queried, i.e., the same identity is queried, S404 is performed.

[0080] In the embodiment of the present application, if the corresponding identity cannot be queried, prompt information such as "no identity corresponding to the requested data in the database" can be output.

[0081] S404, inputting the requested global corresponding geometric size data into the inflection point size association model corresponding to the queried identity to obtain the corresponding inflection point coordinates as reference coordinates.

[0082] S405, obtaining the difference value between the to-be-processed coordinates and the reference coordinates, if the difference value is less than a set value, S406 is performed, otherwise, prompt information indicating that the force displacement curve in the requested data is abnormal is output.

[0083] In the embodiment of the present application, the difference value between the to-be-processed coordinates and the reference coordinates satisfies the following condition:

[0084] △d= ( ( (F p -F c ) / F c ) 2 + ( (δ p -δ c ) / δ c ) 2 ) 1 / 2 ; wherein, △d is the difference value between the to-be-processed coordinates and the reference coordinates, F p is the force coordinate in the to-be-processed coordinates, F c is the force coordinate in the reference coordinates, δ p is the displacement coordinate in the to-be-processed coordinates, and δ c is the displacement coordinate in the reference coordinates.

[0085] In the embodiment of the present application, the set value can be determined based on at least one of the following ways: (1) the measurement accuracy and safety factor of the force sensor and the displacement sensor; (2) the historical statistical distribution (such as the 95% quantile) of the normal forging force displacement curve coordinate difference; (3) the mechanical property tolerance requirement of the target forging material; (4) the coordinate difference critical value obtained by finite element simulation. Generally speaking, in a high-precision testing scene, the set value will be smaller, such as 0.05; while in a general precision testing, the set value can be relaxed to 0.1.

[0086] Since the force-displacement curve has some key feature points, such as the elastic limit point, the yield point, the fracture point and the like. By comparing the key point coordinates of the to-be-processed curve and the reference curve, if the force value or the displacement value of the key point has a large deviation, it can be judged that the key point and the nearby region have an anomaly. For example, the yield point displacement value of the to-be-processed curve is much earlier than that of the reference curve, which indicates that the material may start to yield at a lower displacement, and the anomaly is in the vicinity of the yield point, which may imply that the internal structure or performance of the material has a problem.

[0087] In the embodiment of the present application, the output prompt information includes but is not limited to "force-displacement curve data anomaly, difference value exceeds the set range", and the current calculated difference value and the set value are displayed at the same time, which facilitates the operator to quickly understand the abnormal situation.

[0088] In addition, the prompt information can be popped up in the form of a pop-up window in a prominent position of the operation interface, and the time of the occurrence of the anomaly, the source of the request data and the specific anomaly information are recorded in the system log. In addition, an alarm notification can be sent to the relevant technical personnel through email or instant messaging tools to ensure that the abnormal situation can be handled in a timely manner.

[0089] S406, based on the pre-stored fracture energy calculation formula, obtaining the fracture energy corresponding to the requested forging, and inputting the obtained fracture energy of the requested forging into the target fracture energy impact work correlation model corresponding to the identity tag, to obtain the impact work corresponding to the requested forging.

[0090] As known by those skilled in the art, the impact work value directly reflects the ability of the material to absorb energy under impact load, and plays a key role in many actual scenarios, especially in the detection performance of forgings, such as forging material quality evaluation, production process optimization, failure analysis and life prediction, new product research and development and material selection, and quality certification and standard setting. Therefore, based on actual needs, the impact performance of the requested forging can be analyzed using the impact work obtained by S406.

[0091] Further, S406 can also include storing the output impact work into the current database, and classifying and storing according to the identity tag, detection time and the like, to facilitate subsequent query and traceability. At the same time, the output impact work data can also be shared through an API interface to related systems, such as a quality management system, a production scheduling system and the like, so as to facilitate the departments to work and make decisions based on the data.

[0092] In summary, the intelligent detection method for the impact performance of the forging blank provided in the embodiment of the present application has at least the following advantages by fusing the micro-impact test data and the impact fracture test data to construct the inflection point size correlation model and the target fracture energy impact work correlation model:

[0093] (1) Non-destructive testing and efficient modeling

[0094] The embodiment of the present application breaks through the destructive limitation of the traditional impact test, and only needs a small amount of micro-impact test data (including force-displacement curve, crack propagation area, etc.) and corresponding impact data of the forging sample, so as to automatically construct a high-precision prediction model through a computer program. Compared with the traditional method of obtaining the cross-sectional image of the forging by impact, the scheme can greatly improve the detection efficiency, and avoid the destructive loss of high-value forgings.

[0095] (2) Data-driven accurate prediction of impact performance

[0096] The embodiment of the present application is based on the deep mining of the micro-impact test data by the machine learning algorithm, the model can automatically extract the mapping relationship between the inflection point features of the force-displacement curve and the size of the forging, and combine the dynamic correction model of the fracture energy impact work, so as to reduce the impact work prediction error.

[0097] (3) Intelligentization and automation of detection process

[0098] The embodiment of the present application can automatically analyze the digital force-displacement curve of the micro-impact test without manual annotation of feature points, and based on the pre-stored material type-shape type association model in the database, the impact performance of the new forging can be predicted in seconds.

[0099] (4) Support batch detection of multiple batches of forgings

[0100] The embodiment of the present application can construct the corresponding inflection point size association model and the target fracture energy impact work association model based on the micro-impact test data and the impact data of a small amount of forging sample data, so as to obtain the impact work similar to the impact data based on the micro-impact test data of the forging in actual application, analyze the detection performance of the forging, and provide the detection efficiency and data processing efficiency of the forging detection performance.

[0101] Based on the same inventive concept, the embodiment of the present application provides an intelligent detection system for the impact performance of a forging blank, which comprises:

[0102] The sample processing module is configured to perform a micro-impact experiment and a notching experiment on a sample forging, obtain micro-impact record data and notching record data, and construct a basic data set; wherein the sample forging includes a forging group having the same material type but different shape types, and each forging group contains forgings having different geometric size data; the basic data set includes a plurality of record sets, each record set corresponding to a forging group and containing an identity of the forging group, micro-impact record data and notching record data, the micro-impact record data including geometric size data, a force-displacement curve, a crack propagation area measurement value and a temperature increase value, and the notching record data including geometric size data and an impact work measurement value, and the force-displacement curve is used to represent the numerical correspondence between impact force and pit depth.

[0103] In the embodiment of the application, the sample processing module is configured to perform a micro-impact experiment and a notching experiment on a sample forging, which means that the sample processing module is configured to perform a micro-impact experiment and a notching experiment on a sample forging by sending corresponding control instructions to experimental equipment, for example, including: sending impact parameter control instructions (impact speed, energy, etc.) to a drop hammer impact testing machine (such as INSTRON 9250HV) through a GPIB / USB interface; receiving experimental data such as a force-displacement curve (sampling frequency ≥ 10 kHz) and an infrared thermal image via a 16-bit ADC data acquisition card; and storing the experimental data in a structured record set according to the forging group.

[0104] The model construction module is configured to obtain a turning point size correlation model and a target fracture energy impact work correlation model corresponding to each forging group based on the micro-impact record data and the notching record data corresponding to the forging group; wherein the turning point size correlation model is used to represent the correlation between the turning point coordinates and the geometric size data, and the target fracture energy impact work correlation model is used to represent the correlation between the fracture energy and the impact work.

[0105] The data storage module is configured to associate the identity of each forging group, the turning point size correlation model and the target fracture energy impact work correlation model, and store them in the current database.

[0106] The prediction module is configured to perform a micro-impact experiment on a requested forging when receiving a forging performance detection request, and predict the impact work of the requested forging based on the turning point size correlation model and the target fracture energy impact work correlation model in the current database.

[0107] In the embodiment of the application, the modules of the system interact in the following ways: the sample processing module transmits the structured record set to the input queue of the model construction module; the model construction module registers the trained model to the data storage module through an API interface; and the prediction module pulls the model from the data storage module and performs impact work prediction in combination with real-time experimental data.

[0108] The system can be used to performFigure 1 The method shown in the embodiment shown, therefore, the functions that can be achieved by each functional module of the device, etc. can be referred to Figure 1 The description of the embodiment shown, no more.

[0109] The embodiment of the application also provides an electronic device, comprising: at least one processor; and, memory connected with the at least one processor; wherein, the memory stores instructions executable by the at least one processor, the instructions are set to execute the method described in the embodiment of the application.

[0110] The embodiment of the application also provides a computer readable storage medium, which stores computer executable instructions, the computer instructions are used to execute the method described in the embodiment of the application.

[0111] It should be understood that the steps can be reordered, added or deleted using the various forms of flow shown above. For example, each step described in the present application can be executed in parallel, can be executed sequentially, or can be executed in different order, as long as the desired results of the technical solutions disclosed in the present application can be achieved, which is not limited herein.

[0112] The above specific embodiments do not constitute a limitation on the scope of protection of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent replacement and improvement within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. An intelligent detection method for the impact properties of forging blanks, characterized in that, The method includes the following steps: S100, perform micro-impact and fracture tests on each forging in the sample forgings to obtain micro-impact and fracture record data for that forging, and construct a basic dataset based on the record data of all forgings; wherein, the sample forgings include forging groups with the same material type but different shape types, and each forging group contains forgings with different geometric dimensions; the basic dataset includes multiple record sets, each record set corresponding to a forging group, containing the identification of the forging group, micro-impact record data, and fracture record data. The micro-impact record data includes geometric dimension data, force-displacement curves, crack propagation area measurements, and temperature increase values. The fracture record data includes geometric dimension data and impact energy measurements. The force-displacement curve is used to characterize the numerical correspondence between impact force and dent depth; S200: Based on the micro-impact record data and fracture record data corresponding to each forging group, obtain the inflection point size correlation model and the target fracture energy impact work correlation model corresponding to the forging group; wherein, the inflection point size correlation model is used to characterize the correlation between inflection point coordinates and geometric size data, and the target fracture energy impact work correlation model is used to characterize the correlation between fracture energy and impact work. S300 associates the identity identifier, inflection point size correlation model, and target fracture energy impact work correlation model of each forging group and stores them in the current database; S400: When a forging performance testing request is received, a micro-impact test is performed on the requested forging and the impact energy of the requested forging is predicted based on the inflection point size correlation model and the target fracture energy impact energy correlation model in the current database. S200 specifically includes: S201, process the force-displacement curve of the forging group to obtain the inflection point coordinates and the area under the curve, and obtain the fracture energy corresponding to each forging in the forging group based on the pre-stored fracture energy calculation formula. S202, input the fracture energy of each forging into the pre-stored initial fracture energy impact energy correlation model to obtain the estimated impact energy of the forging; S203, perform regression analysis on all inflection point coordinates and geometric dimensions of the forging group to establish an inflection point dimension correlation model between inflection point coordinates and geometric dimensions; S204. Based on the estimated and measured impact energy values ​​of the forging group, obtain the correction coefficient of the forging group, and correct the initial fracture energy impact energy correlation model based on the correction coefficient to obtain the corresponding correction result. The correction result is then used as the target fracture energy impact energy correlation model for the forging group. The pre-stored formula for calculating fracture energy satisfies the following condition: Gc = Ac / Af•(1+k•ΔT); where Gc is the fracture energy, in J / m. 2 Ac is the area under the curve, in N·mm, and Af is the crack propagation area, in mm. 2 k is the temperature correction factor, and ΔT is the temperature increase in K.

2. The method according to claim 1, characterized in that, The identification of each forging group is determined based on the corresponding material type and shape type.

3. The method according to claim 2, characterized in that, in, The S400 specifically includes: S401, Perform a micro-impact test on the requested forging to obtain micro-impact recording data of the requested forging; S402, process the force-displacement curve in the micro-impact record data of the requested forging to obtain the corresponding inflection point coordinates and the area under the curve, and use the obtained inflection point coordinates as the coordinates to be processed; S403, Using the identity identifier of the requested forging as input, perform a query operation in the current database. If the corresponding identity identifier is found, proceed to S404. S404, input the geometric dimension data corresponding to the requested forging into the inflection point dimension association model corresponding to the queried identity identifier to obtain the corresponding inflection point coordinates, which are used as reference coordinates; S405, obtain the difference value between the coordinates to be processed and the reference coordinates. If the difference value is less than the set value, execute S406. Otherwise, output a prompt message indicating that the force-displacement curve of the requested forging is abnormal. S406. Based on the pre-stored fracture energy calculation formula, obtain the fracture energy corresponding to the requested forging, and input the obtained fracture energy of the requested forging into the target fracture energy impact energy association model corresponding to the queried identity identifier to obtain the impact energy corresponding to the requested forging.

4. The method according to claim 3, characterized in that, The difference between the coordinates to be processed and the reference coordinates must satisfy the following condition: △d=(((F p -F c ) / F c ) 2 +(δ p -δ c ) / δ c ) 2 ) 1 / 2 Where △d is the difference between the coordinates to be processed and the reference coordinates, and F p F represents the force coordinates in the coordinate system to be processed. c For the force coordinates in the reference coordinate system, δ p Let δ be the displacement coordinate in the coordinate system to be processed. c These are the displacement coordinates in the reference coordinate system.

5. The method according to claim 1, characterized in that, The correction factor for each forging group satisfies the following condition: h = AvgEmea / AvgEpre; Where h is the correction factor for the forging group, AvgEmea is the mean of all impact energy measurements for the forging group, and AvgEpre is the mean of all impact energy assessments for the forging group.

6. The method according to claim 1, characterized in that, The correction factor for each forging group satisfies the following condition: ； Where h is the correction factor for this forging group. Let u be the measured impact energy of the u-th forging in this forging group, where u ranges from 1 to Q, and Q is the number of forgings in this forging group. This is the impact energy evaluation value of the u-th forging in this forging group.

7. An intelligent testing system for the impact properties of forging blanks, characterized in that, The system includes: The sample processing module is configured to perform micro-impact and impact fracture experiments on sample forgings, acquire micro-impact and impact fracture record data, and construct a basic dataset. The sample forgings include groups of forgings with the same material type but different shapes, each group containing forgings with different geometric dimensions. The basic dataset includes multiple record sets, each corresponding to a forging group, containing the forging group's identifier, micro-impact record data, and impact fracture record data. The micro-impact record data includes geometric dimensions, force-displacement curves, crack propagation area measurements, and temperature increase values. The impact fracture record data includes geometric dimensions and impact energy measurements. The force-displacement curves characterize the numerical correspondence between impact force and dent depth. The model building module is configured to obtain the inflection point size correlation model and the target fracture energy impact work correlation model for each forging group based on the micro-impact record data and fracture record data corresponding to that forging group. The inflection point size correlation model is used to characterize the correlation between inflection point coordinates and geometric dimension data, and the target fracture energy impact work correlation model is used to characterize the correlation between fracture energy and impact work. The data storage module is configured to associate the identity identifier, inflection point size association model, and target fracture energy impact work association model of each forging group and store them in the current database; The prediction module is configured to perform a micro-impact test on the requested forging when a forging performance testing request is received, and predict the impact energy of the requested forging based on the inflection point size correlation model and the target fracture energy impact energy correlation model in the current database. Specifically, the model building module is used to perform operations: The force-displacement curve of the forging group is processed to obtain the inflection point coordinates and the area under the curve, and the fracture energy corresponding to each forging in the forging group is obtained based on the pre-stored fracture energy calculation formula. The fracture energy of each forging is input into the pre-stored initial fracture energy impact energy correlation model to obtain the estimated impact energy of the forging. Regression analysis was performed on all inflection point coordinates and geometric dimensions of the forging group to establish an inflection point dimension correlation model between inflection point coordinates and geometric dimensions. Based on the estimated and measured impact energy values ​​of the forging group, the correction coefficient of the forging group is obtained, and the initial fracture energy impact energy correlation model is corrected based on the correction coefficient to obtain the corresponding correction result. The correction result is then used as the target fracture energy impact energy correlation model for the forging group. The pre-stored formula for calculating fracture energy satisfies the following condition: Gc = Ac / Af•(1+k•ΔT); where Gc is the fracture energy, in J / m. 2 Ac is the area under the curve, in N·mm, and Af is the crack propagation area, in mm. 2 k is the temperature correction factor, and ΔT is the temperature increase in K.

Images