A method, apparatus, equipment, medium, and procedure for detecting delamination based on curing mold temperature.

Abstract

This application provides a method, apparatus, equipment, medium, and program product for delamination detection based on the temperature of a curing mold. This application relates to the field of pultrusion product manufacturing technology. The method includes: collecting temperature data at multiple preset locations distributed along the pultrusion direction within the curing mold; establishing temperature gradient data to be measured; acquiring the composition and shape parameters of the pultruded product, and determining a theoretical temperature gradient model based on the composition and shape parameters; inputting the preset locations into the theoretical temperature gradient model and outputting theoretical temperature gradient data; calculating the gradient deviation rate between the measured temperature gradient data and the theoretical temperature gradient data; if the gradient deviation rate exceeds a set deviation rate threshold, it is determined that the pultruded product has a risk of delamination anomaly. This technical solution can identify the risk of delamination defects in real time during the pultrusion production process without damaging the product, effectively reducing waste and raw material waste, and ensuring product quality.

Description

Technical Field

[0001] This application relates to the field of pultrusion product manufacturing technology, and in particular to a method, apparatus, equipment, medium and program product for detecting delamination based on the temperature of the curing mold. Background Technology

[0002] Pultrusion technology for composite materials is widely used in the manufacture of products such as insulating strips and structural profiles due to the excellent insulation properties and high production efficiency of the products. Delamination defects are a key quality hazard in the pultrusion production process, directly affecting the structural stability and service life of the products. Therefore, delamination defect detection is a core aspect of pultrusion quality control.

[0003] In existing technologies, delamination defect detection mainly relies on destructive observation methods after product molding, i.e., cutting the finished product to observe whether delamination exists in the cross-section. This method not only cannot achieve comprehensive inspection of batch products, but also suffers from serious detection lag, resulting in a large number of scraps and wasted raw materials by the time defects are discovered. Other solutions, such as non-destructive testing, are not only time-consuming but also have low accuracy, leading to significant biases in product quality evaluation. Therefore, how to achieve real-time and accurate detection of delamination anomalies in pultruded products is a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0004] This application provides a delamination detection method, apparatus, equipment, medium, and program product based on the curing mold temperature, aiming to solve the technical problems of lag, destructiveness, or insufficient detection accuracy in existing pultrusion product delamination defect detection.

[0005] In a first aspect, embodiments of this application provide a delamination detection method based on the temperature of a curing mold, the method comprising: During the manufacturing process of pultruded products, temperature data are collected at multiple preset locations distributed along the pultrusion direction within the curing mold; Based on the temperature data and the preset location, establish the temperature gradient data to be measured; Obtain the composition and shape parameters of the pultruded product, and determine the theoretical temperature gradient model based on the composition and shape parameters; The preset position is input into the theoretical temperature gradient model, so that the theoretical temperature gradient model outputs theoretical temperature gradient data. Calculate the gradient deviation rate between the measured temperature gradient data and the theoretical temperature gradient data; If the gradient deviation rate of any two preset position intervals exceeds the set deviation rate threshold, it is determined that the pultruded product has a risk of layering anomaly.

[0006] In one feasible embodiment, the process of constructing the theoretical temperature gradient model includes: Collect the composition and shape parameters of the pultruded product, wherein the composition parameters include resin type, fiber content and resin curing kinetics parameters, and the shape parameters include cross-sectional dimensions and thickness; The basic heat transfer equation, the composition parameters, and the shape parameters are imported into the simulation system to establish an initial simulation model; wherein, the basic heat transfer equation is obtained by conducting heat transfer simulation experiments under the same environment within the curing mold; Based on historical production data, with the location information of preset monitoring points as input variables, and with the difference between the simulated temperature gradient data output by the initial simulation model and the actual temperature gradient data included in the historical production data as the optimization objective, the parameters of the initial simulation model are optimized to obtain the optimized theoretical temperature gradient model.

[0007] In one feasible embodiment, the method further includes: Obtain the dielectric constant data for each of the preset positions; The curing degree parameters at each preset position are determined based on the dielectric constant data and the curing degree mapping curve corresponding to each preset position. If the curing degree parameter exceeds the preset curing degree range, it is determined that the pultruded product has a risk of delamination.

[0008] In one feasible embodiment, the process of constructing the curing degree curve includes: Composite resin samples were prepared based on resin samples of the same type as those used in pultrusion production, according to the fiber content ratio in actual production. The composite resin sample was placed in a control curing mold, and the control curing mold was heated. The curing degree data of the sample at different positions was measured in real time. The dielectric constant data corresponding to each position was collected using a dielectric sensor. The control curing mold has the same structure and heating method as the curing mold in the actual pultrusion operation. Using the collected dielectric constant data as the abscissa and the corresponding curing degree data as the ordinate, a scatter plot of data at each location is constructed, and curve fitting is performed to obtain the curing degree mapping curve at each location.

[0009] In one feasible embodiment, the composition parameters and shape parameters of the pultruded product are obtained, and a theoretical temperature gradient model is determined based on the composition parameters and the shape parameters, including: The composition and shape parameters of the pultruded product are used to construct screening features; Based on the screening features, parameter matching is performed with the obtained theoretical temperature gradient model to obtain a theoretical temperature gradient model that is compatible with the screening features.

[0010] In one feasible embodiment, the preset positions include a plurality of preset positions distributed along the pultrusion direction within the curing mold, and at least include a curing mold inlet position and a curing mold outlet position.

[0011] Secondly, embodiments of this application provide a delamination detection device based on the temperature of a curing mold, the device comprising: The temperature data acquisition module is used to collect temperature data at multiple preset locations distributed along the pultrusion direction within the curing mold during the manufacturing process of pultruded products. The temperature gradient data construction module is used to build the temperature gradient data to be measured based on the temperature data and the preset position. The model matching module is used to obtain the composition parameters and shape parameters of the pultruded product, and determine the theoretical temperature gradient model based on the composition parameters and shape parameters. The theoretical data output module is used to input the preset position into the theoretical temperature gradient model, so that the theoretical temperature gradient model outputs theoretical temperature gradient data. The gradient deviation rate calculation module is used to calculate the gradient deviation rate between the measured temperature gradient data and the theoretical temperature gradient data. The layered anomaly risk determination module is used to determine that the pultruded product has a layered anomaly risk if the gradient deviation rate of any two preset position intervals exceeds a set deviation rate threshold.

[0012] Thirdly, embodiments of this application provide a delamination detection device based on the temperature of a cured mold. The device includes a processor and a memory storing computer program instructions. The processor reads and executes the computer program instructions to implement any of the delamination detection methods based on the temperature of a cured mold in the above embodiments.

[0013] Fourthly, embodiments of this application provide a computer storage medium storing computer program instructions, which, when executed by a processor, implement any of the layer detection methods based on the temperature of the curing mold described above.

[0014] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements any of the delamination detection methods based on the temperature of the curing mold described above.

[0015] This application presents a delamination detection method, apparatus, equipment, medium, and program product based on curing mold temperature. It constructs a temperature gradient to be measured by collecting temperature data from multiple preset locations within the curing mold, establishes a theoretical temperature gradient model by combining product composition and shape parameters, and achieves delamination anomaly detection through deviation rate comparison. This solution does not damage the product and can identify delamination defect risks in real time during pultrusion production, effectively reducing scrap and raw material waste, and ensuring product quality. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a schematic flowchart of a delamination detection method based on the temperature of a curing mold provided in an embodiment of this application; Figure 2 This is a schematic diagram of the process for detecting delamination defects and controlling the curing state provided in the embodiments of this application; Figure 3 This is a schematic diagram of a delamination detection device based on the temperature of a curing mold provided in an embodiment of this application; Figure 4 This is a schematic diagram of the hardware structure of the layer detection device based on the temperature of the curing mold provided in this application embodiment. Detailed Implementation

[0018] The features and exemplary embodiments of various aspects of the present invention will now be described in detail. To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are merely intended to explain the present invention and not to limit it. For those skilled in the art, the present invention can be practiced without some of these specific details. The following description of the embodiments is merely to provide a better understanding of the present invention by illustrating examples of the invention.

[0019] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0020] To address the problems of existing technologies, this application provides a method, apparatus, equipment, medium, and program product for delamination detection based on the temperature of a curing mold. This technical solution involves deploying thermocouples in multiple sections of the curing mold and dielectric sensors and thermocouples within the mold to simultaneously collect temperature and dielectric constant data. A theoretical temperature gradient model is constructed based on product parameters. Delamination defects are detected by comparing the actual and theoretical gradient deviation rate. The degree of curing is calculated using the dielectric constant, and a predictive model is used to predict the final product quality. This technical solution achieves online non-destructive testing of delamination defects and precise control of the curing state, enabling early detection of anomalies, reducing waste, significantly improving raw material utilization, and greatly enhancing production efficiency and product quality consistency.

[0021] The following section first introduces the delamination detection method based on the temperature of the curing mold provided in the embodiments of this application.

[0022] Figure 1 This is a schematic flowchart of a delamination detection method based on the temperature of a curing mold provided in an embodiment of this application. Figure 1 As shown, the method may include the following steps: S101, during the manufacturing process of pultruded products, temperature data are collected at multiple preset locations distributed along the pultrusion direction inside the curing mold; Pultruded products can be composite material products manufactured using pultrusion molding technology, such as pultruded products of glass fiber and polyester resin, pultruded products of carbon fiber and epoxy resin, etc., and can specifically include insulating strips, structural profiles and ladder rungs, etc.

[0023] A curing mold is a special mold used in the pultrusion manufacturing process to cure composite materials. Its structure and heating method must be adapted to the requirements of the pultrusion production process.

[0024] The preset location can be a temperature sampling point pre-set along the pultrusion direction inside the curing mold, such as the inlet, middle section and outlet of the curing mold, and multiple points can be evenly distributed in the middle section.

[0025] Temperature data can be real-time temperature values ​​at preset locations, with a measurement range covering 0-300℃.

[0026] This solution can be achieved by deploying high-precision thermocouple sensors at preset locations, such as Omega K-type thermocouple sensors. The sampling frequency can be set, for example, to 5Hz, to acquire temperature data at each preset location in real time and transmit it to the data processing system.

[0027] S102, Based on the temperature data and the preset position, establish the temperature gradient data to be measured; The temperature gradient data to be measured can be a sequence of data reflecting the temperature change trend along the pultrusion direction inside the curing mold, consisting of the temperature difference between adjacent preset positions.

[0028] This method can calculate the temperature difference between two adjacent preset locations based on the collected temperature data, and arrange all temperature differences in the order of their distribution to form the temperature gradient data to be measured. For example, the preset locations include inlet T1, middle section T1, etc. 2-1 T 2-2 For export T3, calculate ΔT1=T 2-1 -T1, ΔT2=T 2-2 -T 2-1 And ΔT3=T3-T 2-2 The temperature gradient data to be measured [ΔT1, ΔT2, ΔT3] are obtained.

[0029] S103, Obtain the composition parameters and shape parameters of the pultruded product, and determine the theoretical temperature gradient model based on the composition parameters and shape parameters; Compositional parameters can be key parameters characterizing the material composition of pultruded products, including resin type, fiber content, and resin curing kinetic parameters.

[0030] Shape parameters can be parameters that characterize the appearance and structure of pultruded products, such as cross-sectional shape and size.

[0031] The theoretical temperature gradient model can be a temperature gradient calculation model built based on the characteristics of pultruded products under the condition of no delamination defects, and can output theoretical temperature gradient data for the corresponding preset position.

[0032] In this solution, the composition and shape parameters of pultruded products can be obtained by querying production process documents and reading product design drawings. For example, the composition parameters of epoxy resin and 60% fiber content can be retrieved from the production technology archives, and the shape parameters of a thin plate with a cross-sectional size of 50mm×10mm can be obtained from the design drawings.

[0033] This solution can use ANSYS thermal simulation software, input relevant parameters to perform simulation calculations, and obtain a theoretical temperature gradient model.

[0034] S104, input the preset position into the theoretical temperature gradient model, so that the theoretical temperature gradient model outputs theoretical temperature gradient data; Specifically, the location information of preset positions can be organized according to a preset format and transmitted to the theoretical temperature gradient model. The built-in calculation logic then performs calculations and outputs the corresponding theoretical temperature gradient data. For example, the input inlet and middle section T... 2-1 T 2-2 The location information of the exit, the model output [ΔT] 10 ,ΔT 20 ,ΔT 30 Theoretical temperature gradient data.

[0035] S105, Calculate the gradient deviation rate between the measured temperature gradient data and the theoretical temperature gradient data; Gradient deviation rate is an indicator of the degree of difference between the measured temperature gradient data and the theoretical temperature gradient data, used to determine whether the actual temperature gradient deviates from the normal range.

[0036] This solution can calculate the gradient deviation rate according to a preset formula, such as the following formula: ; Where i is the preset position interval number, ΔT i Let ΔT be the i-th temperature difference value in the temperature gradient data to be measured. i0 This represents the i-th temperature difference value in the theoretical temperature gradient data. For example, ΔT1 = 15℃, ΔT 10 =12℃, then the gradient deviation rate η=|15-12| / 12×100%=25%.

[0037] S106, if the gradient deviation rate of any two preset position intervals exceeds the set deviation rate threshold, it is determined that the pultruded product has a risk of layering abnormality.

[0038] The preset location range can be the temperature gradient detection range formed by two adjacent preset locations, such as the inlet-middle section T. 2-1 The interval is the distance between point A and point B, with the middle segment T. 2-1 -Mid-section T 2-2 The interval is the distance between point B and point C, with the middle segment T. 2-2 - The exit range is the section between point C and point D.

[0039] Setting a deviation rate threshold can be a pre-defined critical value for judging stratification anomalies. For example, it can be determined based on a large amount of experimental data and production experience, such as setting it to 10%.

[0040] Delamination anomaly risk can be an indication of the probability that delamination defects may occur in pultruded products during the curing process. The existence of this risk indicates that the product may have a delamination problem.

[0041] This solution compares the calculated gradient deviation rate of each preset position interval with the set deviation rate threshold. If the gradient deviation rate of any interval exceeds the set threshold, it is determined that the pultruded product has a risk of layering abnormality and an abnormality prompt message is generated.

[0042] This technical solution collects temperature data from multiple preset locations within the curing mold in real time during the pultrusion process. Combined with the product's own parameters, a theoretical temperature gradient model is constructed, and delamination anomaly detection is achieved through deviation rate comparison. The detection can be completed without damaging the product, covering the entire production process of batch products. This solves the lag problem of traditional destructive testing. Furthermore, the theoretical model built based on product characteristics makes the detection results more closely reflect actual production conditions, significantly improving the accuracy of delamination defect detection, effectively reducing scrap losses due to delamination defects, and ensuring product quality stability.

[0043] In one feasible embodiment, the process of constructing the theoretical temperature gradient model includes: Collect the composition and shape parameters of the pultruded product, wherein the composition parameters include resin type, fiber content and resin curing kinetics parameters, and the shape parameters include cross-sectional dimensions and thickness; The basic heat transfer equation, the composition parameters, and the shape parameters are imported into the simulation system to establish an initial simulation model; wherein, the basic heat transfer equation is obtained by conducting heat transfer simulation experiments under the same environment within the curing mold; Based on historical production data, with the location information of preset monitoring points as input variables, and with the difference between the simulated temperature gradient data output by the initial simulation model and the actual temperature gradient data included in the historical production data as the optimization objective, the parameters of the initial simulation model are optimized to obtain the optimized theoretical temperature gradient model.

[0044] The resin type can refer to the specific type of resin used in pultrusion products, such as polyester resin, epoxy resin, etc.

[0045] Fiber content can be the proportion of fiber material in the total mass or volume of the composite material in a pultruded product, such as 55%, 60%, etc.

[0046] Resin curing kinetic parameters can be parameters that characterize the resin curing reaction rate, degree of reaction, etc., such as the activation energy of the curing reaction and the reaction order.

[0047] The cross-sectional dimensions can be the external dimensions of the cross-section of the pultruded product, such as the length and width of a square cross-section, or the diameter of a circular cross-section.

[0048] In this scheme, the resin type can be determined to be polyester resin in the pultrusion product design scheme, the fiber content and resin content can be obtained from the process specifications, and the cross-sectional dimensions can be read from the design drawings.

[0049] The basic heat transfer equation can be a mathematical equation that describes the heat transfer law in the composite material within the curing mold. It is derived through heat transfer simulation experiments in an environment equivalent to actual production, such as the heat conduction equation based on Fourier's law.

[0050] The simulation system can be a specialized software system used for thermal simulation analysis, such as ANSYS thermal simulation software, ABAQUS simulation software, etc.

[0051] The initial simulation model can be an unoptimized temperature gradient simulation model built after importing relevant parameters, which can initially simulate the temperature gradient distribution when there are no layered defects.

[0052] This approach allows you to organize the mathematical expression of the basic heat transfer equation, along with the collected composition and shape parameters, according to the simulation system's required format, and then input them into the simulation system. After inputting the parameters, the built-in modeling algorithm constructs an initial simulation model to simulate the heat transfer process during curing.

[0053] Historical production data can be relevant data recorded during the production of the same or similar pultruded products in the past, including the location information of preset monitoring points, actual temperature gradient data, product quality test results, etc., such as containing 1000+ sets of production data records.

[0054] The preset monitoring point can be the temperature monitoring location set in the curing mold during the historical production process, which is consistent with the preset location for current detection.

[0055] Input variables can be independent variables used for model optimization, such as the location coordinates and distribution spacing of preset monitoring points.

[0056] The optimization objective can be the core requirement that model optimization needs to achieve, namely, minimizing the difference between the simulated temperature gradient data output by the initial simulation model and the historical real temperature gradient data, so that the model output is closer to the actual situation.

[0057] Parameter optimization can be achieved by adjusting relevant parameters in the initial simulation model, such as thermal conductivity and boundary conditions, to reduce the deviation between simulation data and real data.

[0058] This approach uses the optimization algorithm of the simulation system to adjust the parameters of the initial simulation model until the difference between the simulated temperature gradient data and the historical real temperature gradient data meets the preset requirements, thus obtaining the optimized theoretical temperature gradient model.

[0059] This technical solution clarifies the specific construction process of the theoretical temperature gradient model. By collecting precise product parameters and combining them with the fundamental heat transfer equations derived from the actual environment, an initial model is constructed. Historical production data is then used to optimize the parameters, making the constructed theoretical temperature gradient model more closely resemble the actual production scenario and resulting in more accurate theoretical temperature gradient data. By comparing the deviation rate based on this model, the accuracy of layered defect detection can be further improved, reducing false positives and false negatives, and providing reliable model support for layered anomaly detection.

[0060] In one feasible embodiment, the method further includes: Obtain the dielectric constant data for each of the preset positions; The curing degree parameters at each preset position are determined based on the dielectric constant data and the curing degree mapping curve corresponding to each preset position. If the curing degree parameter exceeds the preset curing degree range, it is determined that the pultruded product has a risk of delamination.

[0061] Dielectric constant data can be physical quantity data that characterizes the dielectric properties of resin at a preset location. The measurement range can cover 1-1000pF and can reflect the degree of resin curing.

[0062] This solution can collect dielectric constant data in real time by deploying high-temperature resistant dielectric sensors at each preset location, such as the HBM1-C100 dielectric sensor, which can work continuously at 250℃ and has a sampling frequency of 10Hz, and transmit the dielectric constant data to the data processing system.

[0063] The curing degree mapping curve can be a curve that characterizes the correspondence between dielectric constant data and curing degree parameters. Each preset position corresponds to a dedicated curve, and the fitting accuracy R²≥0.98.

[0064] Curing degree parameter can be a parameter that characterizes the degree of resin curing. The value range is 0-1, where 1 indicates that the resin is fully cured and 0 indicates that curing has not started.

[0065] Specifically, the curing degree mapping curve corresponding to each preset location can be called, and the collected dielectric constant data can be substituted into the curve to calculate the corresponding curing degree parameter through interpolation. For example, if the dielectric constant data of a preset location is 500pF, substituting it into the curing degree mapping curve of that location will yield a curing degree parameter of 0.65.

[0066] The preset curing degree range can be a reasonable range of curing degree parameters for each preset position based on product quality requirements and production experience. For example, the preset range is 0.3-0.4 for the last 1 / 3 of the inlet, 0.6-0.7 for the middle section, and 0.9-1.0 for the first 1 / 3 of the outlet.

[0067] In this solution, the curing degree parameters at each preset location can be compared with the corresponding preset curing degree range. If the curing degree parameter at any preset location exceeds the range, it is determined that the pultruded product has a risk of delamination.

[0068] This technical solution, based on temperature gradient detection, adds correlation detection between dielectric constant data and cure degree parameters, achieving a comprehensive assessment of delamination anomaly risks through dual-dimensional detection. Furthermore, the dielectric constant data directly reflects the resin's curing state, and combined with the cure degree parameters determined by a dedicated cure degree mapping curve, it further enriches the basis for delamination detection, effectively improving the comprehensiveness and accuracy of delamination anomaly risk assessment, reducing the potential for misjudgment from single temperature gradient detection, and providing a more reliable guarantee for pultrusion product quality control.

[0069] In one feasible embodiment, the process of constructing the curing degree curve includes: Composite resin samples were prepared based on resin samples of the same type as those used in pultrusion production, according to the fiber content ratio in actual production. The composite resin sample was placed in a control curing mold, and the control curing mold was heated. The curing degree data of the sample at different positions was measured in real time. The dielectric constant data corresponding to each position was collected using a dielectric sensor. The control curing mold has the same structure and heating method as the curing mold in the actual pultrusion operation. Using the collected dielectric constant data as the abscissa and the corresponding curing degree data as the ordinate, a scatter plot of data at each location is constructed, and curve fitting is performed to obtain the curing degree mapping curve at each location.

[0070] The resin sample can be a resin material that is exactly the same type of resin used in the actual pultrusion production. For example, if epoxy resin is used in the actual production, then the resin sample is also epoxy resin.

[0071] Composite resin samples can be prepared by mixing resin samples with fiber materials according to the actual fiber content ratio in production. They are used to simulate the material properties of actual products. For example, if the actual fiber content in production is 60%, then a composite resin sample is prepared with a ratio of 40% resin and 60% fiber.

[0072] This method employs the same mixing process as actual production, uniformly mixing the resin sample with the fiber material to create a composite resin sample with the same cross-sectional dimensions as the actual product. Furthermore, it allows for the preparation of samples with various proportions and interface sizes in a single experiment.

[0073] The reference curing mold can be a special mold used for experiments, whose structure (such as internal cavity size and shape) and heating method (such as heating power and heating area distribution) are completely consistent with the curing mold used in actual pultrusion production, ensuring that the experimental environment is equivalent to the actual production environment.

[0074] This method allows heating of the curing mold according to the actual curing process curve of pultrusion production, so that the composite resin sample undergoes the same temperature change process as in actual production, for example, heating to 180°C at a heating rate of 5°C / min and holding at that temperature for 2 hours.

[0075] Curing degree data refers to the degree of curing of the composite resin sample at different times and locations during the heating process, obtained through measurement using specialized testing equipment, such as a Differential Scanning Calorimeter (DSC). This solution uses a DSC to monitor the curing degree changes at different locations of the composite resin sample in real time and record the curing degree data at different times. Dielectric sensors are deployed at different locations on the composite resin sample to synchronously collect dielectric constant data at each location at different times, with the acquisition frequency consistent with actual production.

[0076] A data scatter plot is a graph formed by plotting dielectric constant data and curing degree data collected at the same location and time in a Cartesian coordinate system. It can intuitively reflect the correspondence between the two.

[0077] Curve fitting can be achieved by using mathematical fitting algorithms, such as the least squares method, to fit the coordinate points in the data scatter plot and obtain a continuous curve that can characterize the relationship between dielectric constant data and curing degree data.

[0078] This solution uses data processing software, such as Origin and Matlab, to perform curve fitting on the scatter plots of data at each location, ensuring a fitting accuracy of R² ≥ 0.98, and ultimately obtaining a unique curing degree mapping curve for each location.

[0079] This technical solution employs experiments using resin type, fiber content, mold structure, and heating method consistent with actual production to ensure a high degree of correlation and accuracy between the collected dielectric constant data and cure degree data. The cure degree mapping curve constructed based on this data accurately reflects the correspondence between the two in actual production, providing a reliable basis for subsequently determining cure degree parameters using dielectric constant data. This further ensures the accuracy of delamination anomaly risk detection, making the detection method more practical and operable.

[0080] In one feasible embodiment, the composition parameters and shape parameters of the pultruded product are obtained, and a theoretical temperature gradient model is determined based on the composition parameters and the shape parameters, including: The composition and shape parameters of the pultruded product are used to construct screening features; Based on the screening features, parameter matching is performed with the obtained theoretical temperature gradient model to obtain a theoretical temperature gradient model that is compatible with the screening features.

[0081] Screening features can be a set of features formed by integrating the composition and shape parameters of pultruded products. These features are used to match suitable theoretical temperature gradient models in an existing model library. For example, the feature set could be {resin type: epoxy resin, fiber content: 60%, cross-sectional dimensions: 50mm × 10mm, resin curing kinetics parameter: activation energy 85kJ / mol}. This solution can organize the acquired composition and shape parameters according to preset feature coding rules to form standardized screening features.

[0082] The obtained theoretical temperature gradient models can be verified and optimized theoretical temperature gradient models built in the past when producing the same or similar pultruded products, and are stored in the model library.

[0083] Then, the constructed screening features are compared with the parameter features of each theoretical temperature gradient model in the model library to calculate the feature similarity and select the model with the highest similarity. Then, a preset matching algorithm is used to compare the screening features with the model parameters in the model library, and the model with the similarity reaching the preset threshold is selected as the suitable theoretical temperature gradient model; if there is no suitable model in the model library, the new model construction process is triggered.

[0084] This technical solution provides an efficient method for determining theoretical temperature gradient models. By constructing screening features and matching parameters with an existing model library, it eliminates the need to rebuild a model for each new pultruded product, significantly shortening the model determination time and improving the efficiency of stratified detection. Furthermore, matching based on existing validated models ensures model reliability and accuracy, reduces the risk of errors that may arise from building new models, and makes the detection method more suitable for multi-variety, small-batch pultruded product production scenarios.

[0085] In one feasible embodiment, the preset positions include a plurality of preset positions distributed along the pultrusion direction within the curing mold, and at least include a curing mold inlet position and a curing mold outlet position.

[0086] The curing mold inlet position can be the initial position where the pultruded product enters the curing mold. The temperature data at this position can reflect the initial temperature state of the composite material entering the curing environment.

[0087] The exit position of the curing mold can be the final position where the pultruded product leaves the curing mold. The temperature data at this position can reflect the temperature state of the composite material after curing.

[0088] Multiple preset positions can be added between the inlet and outlet of the curing mold to collect several temperature data points. For example, preset positions can be added at the 1 / 3 of the inlet, the middle of the mold, and the 1 / 3 of the outlet, so that the temperature data collection is more comprehensive and can more accurately reflect the temperature change gradient along the pultrusion direction.

[0089] This technical solution ensures the comprehensiveness and continuity of temperature data acquisition by including at least inlet and outlet locations and adding multiple intermediate points. Multiple preset locations distributed along the pultrusion direction can construct more complete temperature gradient data, avoiding the problem of inaccurate temperature gradient reflection due to insufficient points. This provides a more reliable data foundation for subsequent deviation rate calculation and stratification anomaly judgment, further improving the stability and accuracy of the stratification detection method.

[0090] To enable those skilled in the art to more clearly understand the technical solutions provided in this application, this application also provides a preferred embodiment. Figure 2 This is a schematic diagram of the process for detecting delamination defects and controlling the curing state provided in an embodiment of this application. For example... Figure 2 As shown, the specific implementation method is as follows: Step 1: Deploy the sensing equipment and set the data acquisition parameters; Specifically, Omega K-type high-precision thermocouple sensors are deployed at the inlet, middle section, and outlet of the curing mold, respectively. The sensor measurement range is set to 0-300℃ to collect temperature data at each location in real time.

[0091] In key heating areas within the curing mold, such as the last third of the inlet, the middle section, and the first third of the outlet, HBM1-C100 high-temperature dielectric sensors and matching thermocouples are deployed. The dielectric sensors can operate continuously at 250°C, and the thermocouples have the same sampling frequency as the curing mold, enabling synchronous acquisition of the resin dielectric constant and the corresponding temperature data.

[0092] Additionally, a high-resolution industrial camera and a laser dimension measuring instrument can be optionally installed at the mold exit for subsequent quality verification.

[0093] Step 2: Collect multi-dimensional production data; Temperature data acquisition: Real-time data acquisition is achieved using the curing mold and thermocouple sensors deployed within the mold, including the inlet temperature T1 and the temperatures at two monitoring points in the middle section of the curing mold. 2-1 T 2-2 The outlet temperature T3 and the temperature data of the three key heating zones inside the mold are continuously transmitted to the data processing system.

[0094] The dielectric constant data of the resin in the three key heating zones are collected synchronously by the dielectric sensor inside the mold and stored in correspondence with the temperature data.

[0095] By reviewing production process documents and design drawings, we can obtain the material composition parameters (resin type, fiber content, resin curing kinetic parameters) and shape parameters (cross-sectional dimensions, thickness) of pultruded products.

[0096] More than 1,000 sets of historical production data were retrieved from the database, including data on the distribution of curing degree inside the mold and the corresponding export quality inspection results.

[0097] Step 3: Construct the theoretical model and calibration curves; Based on ANSYS thermal simulation software, the product's material composition parameters, shape parameters, and heat transfer equations are input. Combined with the exothermic characteristics of resin curing, the theoretical temperature gradient sequence [ΔT10, ΔT20, ΔT30] under no delamination defects is used. Then, the actual temperature gradient data in historical production data is used as a reference to optimize the parameters of the initial model and improve the model's accuracy.

[0098] The degree of curing during the resin curing process was measured using a differential scanning calorimeter, and the corresponding dielectric constant was recorded simultaneously. A scatter plot of data was constructed with the dielectric constant as the abscissa and the degree of curing as the ordinate. A calibration curve was obtained by curve fitting to ensure that the fitting accuracy R²≥0.98.

[0099] The random forest algorithm is adopted, with the solidification distribution data [α1, α2, α3] in the historical production data as input, the corresponding export quality inspection results as labels, and the model output as the export quality level, such as excellent, good, qualified and unqualified, and outputs key quality indicators.

[0100] Step 4: Online detection of layered defects; Based on the collected temperature data, the temperature difference between adjacent monitoring points is calculated to form the temperature gradient sequence to be measured [ΔT1, ΔT2, ΔT3].

[0101] Calculate the deviation rate between the actual temperature gradient sequence and the theoretical temperature gradient sequence. If the deviation rate η > η0 at any monitoring point, a threshold is set, and a stratification anomaly is determined to exist. The location of the anomaly is then output.

[0102] In addition, based on the dielectric constant-curing degree calibration curve, the collected dielectric constant data can be converted into curing degree parameters [α1, α2, α3] for each key heating zone. If the curing degree parameters deviate from the preset range (α1∈[0.3-0.4], α2∈[0.6-0.7], α3∈[0.9-1.0]), the risk of stratification anomaly can be further confirmed.

[0103] Step 5, predictive control of curing quality; Input the calculated solidification degree distribution data [α1, α2, α3] into the trained prediction model to obtain the export quality prediction results.

[0104] If the prediction model indicates an abnormality in the export quality, adjust the temperature of each section inside the mold according to the type of abnormality: if the degree of curing is too low, increase the temperature of the corresponding heating zone by 5-10℃; if the degree of curing is uneven, fine-tune the temperature of the corresponding section by 3-8℃ to ensure that the adjustment response delay is ≤200ms.

[0105] Step 6: Closed-loop optimization of model parameters.

[0106] Industrial cameras and laser dimension measuring instruments at the export point are used to inspect the surface quality and dimensional accuracy of the products, verify the accuracy of the prediction model, and record the verification results.

[0107] For every 100 sets of new verification data accumulated, they are fed back into the prediction model to continuously optimize the mapping relationship between curing degree and export quality, update model parameters, and improve detection and control accuracy.

[0108] This preferred embodiment achieves online non-destructive testing of delamination defects in pultruded products and precise control of the curing state through a multi-source collaborative data acquisition, theoretical modeling, and intelligent prediction process. The detection accuracy of delamination defects is high and the effect is excellent. Timely detection of delamination anomalies effectively reduces the number of defective products, indirectly improving raw material utilization. Simultaneously, through a closed-loop optimization mechanism, it adapts to the production needs of products with different materials and specifications, improving production efficiency and product quality consistency.

[0109] Figure 3 This is a schematic diagram of a delamination detection device based on the temperature of a curing mold, provided in an embodiment of this application. Figure 3 As shown, the delamination detection device based on the temperature of the curing mold includes: The temperature data acquisition module 310 is used to collect temperature data at multiple preset locations distributed along the pultrusion direction within the curing mold during the manufacturing process of pultruded products. The temperature gradient data construction module 320 is used to build the temperature gradient data to be measured based on the temperature data and the preset position. The model matching module 330 is used to obtain the composition parameters and shape parameters of the pultruded product, and determine the theoretical temperature gradient model based on the composition parameters and shape parameters. Theoretical data output module 340 is used to input the preset position into the theoretical temperature gradient model, so that the theoretical temperature gradient model outputs theoretical temperature gradient data. Gradient deviation rate calculation module 350 is used to calculate the gradient deviation rate between the measured temperature gradient data and the theoretical temperature gradient data. The layered anomaly risk determination module 360 ​​is used to determine that the pultruded product has a layered anomaly risk if the gradient deviation rate of any two preset position intervals exceeds the set deviation rate threshold.

[0110] The delamination detection device based on the curing mold temperature provided in this embodiment has the same functional modules and beneficial effects as the delamination detection method based on the curing mold temperature described above. To avoid repetition, it will not be described again here.

[0111] Figure 4 This is a schematic diagram of the hardware structure of a delamination detection device based on the temperature of a cured mold, provided in an embodiment of this application. The delamination detection device based on the temperature of a cured mold may include a processor 401 and a memory 402 storing computer program instructions.

[0112] Specifically, the processor 401 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0113] Memory 402 may include mass storage for data or instructions. For example, and not limitingly, memory 402 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. In one instance, memory 402 may include removable or non-removable (or fixed) media, or memory 402 may be non-volatile solid-state memory. Memory 402 may be internal or external to the integrated gateway disaster recovery device.

[0114] In one instance, memory 402 may be read-only memory (ROM). In one instance, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or flash memory, or a combination of two or more of these.

[0115] The processor 401 reads and executes computer program instructions stored in the memory 402 to achieve... Figure 1 The illustrated embodiment shows a delamination detection method based on the temperature of the curing mold.

[0116] Furthermore, in conjunction with the delamination detection method based on curing mold temperature in the above embodiments, this invention can be implemented using a computer storage medium. This computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the delamination detection methods based on curing mold temperature in the above embodiments.

[0117] This application also provides a computer program product, including a computer program that, when executed by a processor, implements any of the delamination detection methods based on the temperature of the curing mold described above.

[0118] It should be clarified that the present invention is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of the present invention.

[0119] The functional blocks shown in the above-described structural diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this invention are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, read-only memory (ROM), flash memory, erasable read-only memory (EROM), floppy disks, compact disc read-only memory (CD-ROM), optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0120] It should also be noted that the exemplary embodiments mentioned in this invention describe methods or systems based on a series of steps or apparatus. However, this invention is not limited to the order of the steps described above; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0121] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to create a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0122] The above description is merely a specific embodiment of the present invention. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the protection scope of the present invention.

Claims

1. A method for detecting delamination based on the temperature of a curing mold, characterized in that, The method includes: During the manufacturing process of pultruded products, temperature data are collected at multiple preset locations distributed along the pultrusion direction within the curing mold; Based on the temperature data and the preset location, establish the temperature gradient data to be measured; Obtain the composition and shape parameters of the pultruded product, and determine the theoretical temperature gradient model based on the composition and shape parameters; The preset position is input into the theoretical temperature gradient model, so that the theoretical temperature gradient model outputs theoretical temperature gradient data. Calculate the gradient deviation rate between the measured temperature gradient data and the theoretical temperature gradient data; If the gradient deviation rate of any two preset position intervals exceeds the set deviation rate threshold, it is determined that the pultruded product has a risk of layering anomaly.

2. The delamination detection method based on curing mold temperature according to claim 1, characterized in that, The construction process of the theoretical temperature gradient model includes: Collect the composition and shape parameters of the pultruded product, wherein the composition parameters include resin type, fiber content and resin curing kinetics parameters, and the shape parameters include cross-sectional dimensions and thickness; The basic heat transfer equation, the composition parameters, and the shape parameters are imported into the simulation system to establish an initial simulation model; wherein, the basic heat transfer equation is obtained by conducting heat transfer simulation experiments under the same environment within the curing mold; Based on historical production data, with the location information of preset monitoring points as input variables, and with the difference between the simulated temperature gradient data output by the initial simulation model and the actual temperature gradient data included in the historical production data as the optimization objective, the parameters of the initial simulation model are optimized to obtain the optimized theoretical temperature gradient model.

3. The delamination detection method based on curing mold temperature according to claim 1, characterized in that, The method further includes: Obtain the dielectric constant data for each of the preset positions; The curing degree parameters at each preset position are determined based on the dielectric constant data and the curing degree mapping curve corresponding to each preset position. If the curing degree parameter exceeds the preset curing degree range, it is determined that the pultruded product has a risk of delamination.

4. The delamination detection method based on the temperature of the curing mold according to claim 3, characterized in that, The process of constructing the curing degree mapping curve includes: Composite resin samples were prepared based on resin samples of the same type as those used in pultrusion production, according to the fiber content ratio in actual production. The composite resin sample was placed in a control curing mold, and the control curing mold was heated. The curing degree data of the sample at different positions was measured in real time. The dielectric constant data corresponding to each position was collected using a dielectric sensor. The control curing mold has the same structure and heating method as the curing mold in the actual pultrusion operation. Using the collected dielectric constant data as the abscissa and the corresponding curing degree data as the ordinate, a scatter plot of data at each location is constructed, and curve fitting is performed to obtain the curing degree mapping curve at each location.

5. The delamination detection method based on the temperature of the curing mold according to claim 1, characterized in that, Obtain the composition and shape parameters of the pultruded product, and determine the theoretical temperature gradient model based on the composition and shape parameters, including: The composition and shape parameters of the pultruded product are used to construct screening features; Based on the screening features, parameter matching is performed with the obtained theoretical temperature gradient model to obtain a theoretical temperature gradient model that is compatible with the screening features.

6. The delamination detection method based on curing mold temperature according to claim 1, characterized in that, The preset positions include multiple preset positions distributed along the pultrusion direction inside the curing mold, and at least include the curing mold inlet position and the curing mold outlet position.

7. A delamination detection device based on the temperature of a curing mold, characterized in that, The device includes: The temperature data acquisition module is used to collect temperature data at multiple preset locations distributed along the pultrusion direction within the curing mold during the manufacturing process of pultruded products. The temperature gradient data construction module is used to build the temperature gradient data to be measured based on the temperature data and the preset position. The model matching module is used to obtain the composition parameters and shape parameters of the pultruded product, and determine the theoretical temperature gradient model based on the composition parameters and shape parameters. The theoretical data output module is used to input the preset position into the theoretical temperature gradient model, so that the theoretical temperature gradient model outputs theoretical temperature gradient data. The gradient deviation rate calculation module is used to calculate the gradient deviation rate between the measured temperature gradient data and the theoretical temperature gradient data. The layered anomaly risk determination module is used to determine that the pultruded product has a layered anomaly risk if the gradient deviation rate of any two preset position intervals exceeds a set deviation rate threshold.

8. A delamination detection device based on the temperature of a cured mold, characterized in that, The device includes: a processor and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement the delamination detection method based on the temperature of the curing mold as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the delamination detection method based on the temperature of the curing mold as described in any one of claims 1-6.

10. A computer program product, characterized in that, It includes a computer program, which, when executed by a processor, implements the delamination detection method based on the temperature of the curing mold as described in any one of claims 1-6.

Images